{"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":"2026-10-22T11:27:37Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:2986083ea30f5f36","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":10.427439999999999},"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":3.2723400000000002},"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":1.9134899999999997},"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":10.427439999999999}},"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":15.613270000000005},"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":89.72694999649005,"highest":94.48096600068062,"medium":89.67652143287098,"none":85.02336255591855},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":88.66262682166757,"score":88.66262682166757},"GB2-02":{"attempts":3,"playable":83.08402995870553,"score":83.08402995870553},"GB2-03":{"attempts":3,"playable":89.28779393998764,"score":89.28779393998764},"GB2-04":{"attempts":3,"playable":89.67683503890204,"score":89.67683503890204},"GB2-05":{"attempts":3,"playable":95.38602667016316,"score":95.38602667016316},"GB2-06":{"attempts":3,"playable":86.70400633432003,"score":86.70400633432003},"GB2-07":{"attempts":3,"playable":96.32185782892412,"score":96.32185782892412},"GB2-08":{"attempts":3,"playable":88.69242337925033,"score":88.69242337925033}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":96.98236362091885,"score":96.98236362091885},"GB2-02":{"attempts":1,"playable":95.90145858688511,"score":95.90145858688511},"GB2-03":{"attempts":1,"playable":97.58485139460286,"score":97.58485139460286},"GB2-04":{"attempts":1,"playable":92.48053609371028,"score":92.48053609371028},"GB2-05":{"attempts":1,"playable":98.85211617832984,"score":98.85211617832984},"GB2-06":{"attempts":1,"playable":88.07766704375915,"score":88.07766704375915},"GB2-07":{"attempts":1,"playable":97.6839209398181,"score":97.6839209398181},"GB2-08":{"attempts":1,"playable":88.2848141474208,"score":88.2848141474208}},"medium":{"GB2-01":{"attempts":1,"playable":76.12994095332793,"score":76.12994095332793},"GB2-02":{"attempts":1,"playable":81.089000619173,"score":81.089000619173},"GB2-03":{"attempts":1,"playable":94.82350599076405,"score":94.82350599076405},"GB2-04":{"attempts":1,"playable":92.31790850632258,"score":92.31790850632258},"GB2-05":{"attempts":1,"playable":92.86887794820855,"score":92.86887794820855},"GB2-06":{"attempts":1,"playable":88.63978276857463,"score":88.63978276857463},"GB2-07":{"attempts":1,"playable":96.86485907884945,"score":96.86485907884945},"GB2-08":{"attempts":1,"playable":94.6782955977477,"score":94.6782955977477}},"none":{"GB2-01":{"attempts":1,"playable":92.87557589075594,"score":92.87557589075594},"GB2-02":{"attempts":1,"playable":72.2616306700585,"score":72.2616306700585},"GB2-03":{"attempts":1,"playable":75.45502443459601,"score":75.45502443459601},"GB2-04":{"attempts":1,"playable":84.23206051667329,"score":84.23206051667329},"GB2-05":{"attempts":1,"playable":94.4370858839511,"score":94.4370858839511},"GB2-06":{"attempts":1,"playable":83.39456919062633,"score":83.39456919062633},"GB2-07":{"attempts":1,"playable":94.41679346810483,"score":94.41679346810483},"GB2-08":{"attempts":1,"playable":83.11416039258248,"score":83.11416039258248}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-10-22T10:58:58Z","match_totals_all":{"draws":825,"losses":792,"wins":9983},"match_totals_tracks":{"highest":{"draws":90,"losses":163,"wins":3609},"medium":{"draws":248,"losses":278,"wins":3344},"none":{"draws":487,"losses":351,"wins":3030}},"model_slug":"gpt-6-astra","overall":{"max":98.85211617832984,"mean":89.72694999649006,"min":72.2616306700585},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":96.98236362091885,"GB2-02":95.90145858688511,"GB2-03":97.58485139460286,"GB2-04":92.48053609371028,"GB2-05":98.85211617832984,"GB2-06":88.07766704375915,"GB2-07":97.6839209398181,"GB2-08":88.2848141474208},"per_game_all":{"GB2-01":88.66262682166757,"GB2-02":83.08402995870553,"GB2-03":89.28779393998764,"GB2-04":89.67683503890204,"GB2-05":95.38602667016316,"GB2-06":86.70400633432003,"GB2-07":96.32185782892412,"GB2-08":88.69242337925033},"per_game_match_totals_all":{"GB2-01":{"draws":59,"losses":145,"wins":1260},"GB2-02":{"draws":383,"losses":48,"wins":935},"GB2-03":{"draws":162,"losses":80,"wins":1164},"GB2-04":{"draws":144,"losses":79,"wins":1189},"GB2-05":{"draws":0,"losses":66,"wins":1452},"GB2-06":{"draws":77,"losses":154,"wins":1203},"GB2-07":{"draws":0,"losses":44,"wins":1440},"GB2-08":{"draws":0,"losses":176,"wins":1340}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":15,"wins":473},"GB2-02":{"draws":23,"losses":6,"wins":425},"GB2-03":{"draws":8,"losses":6,"wins":454},"GB2-04":{"draws":31,"losses":21,"wins":420},"GB2-05":{"draws":0,"losses":3,"wins":501},"GB2-06":{"draws":28,"losses":43,"wins":407},"GB2-07":{"draws":0,"losses":8,"wins":484},"GB2-08":{"draws":0,"losses":61,"wins":445}},"medium":{"GB2-01":{"draws":35,"losses":105,"wins":348},"GB2-02":{"draws":149,"losses":15,"wins":292},"GB2-03":{"draws":6,"losses":21,"wins":441},"GB2-04":{"draws":38,"losses":18,"wins":414},"GB2-05":{"draws":0,"losses":35,"wins":473},"GB2-06":{"draws":20,"losses":45,"wins":413},"GB2-07":{"draws":0,"losses":12,"wins":484},"GB2-08":{"draws":0,"losses":27,"wins":479}},"none":{"GB2-01":{"draws":24,"losses":25,"wins":439},"GB2-02":{"draws":211,"losses":27,"wins":218},"GB2-03":{"draws":148,"losses":53,"wins":269},"GB2-04":{"draws":75,"losses":40,"wins":355},"GB2-05":{"draws":0,"losses":28,"wins":478},"GB2-06":{"draws":29,"losses":66,"wins":383},"GB2-07":{"draws":0,"losses":24,"wins":472},"GB2-08":{"draws":0,"losses":88,"wins":416}}},"per_game_raw_elo_all":{"GB2-01":2025.0671112667194,"GB2-02":1857.567044526356,"GB2-03":2109.120578791395,"GB2-04":1929.7262323454463,"GB2-05":2607.8761799300387,"GB2-06":2096.5942434985895,"GB2-07":2542.358934969274,"GB2-08":2118.666344601908},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2259.176880087731,"GB2-02":2135.2431093483483,"GB2-03":2413.1136726962363,"GB2-04":1988.2237505649596,"GB2-05":2937.067099318221,"GB2-06":2127.526449338271,"GB2-07":2649.28221668512,"GB2-08":2084.7368597005434},"medium":{"GB2-01":1747.9008424655044,"GB2-02":1771.1749133089172,"GB2-03":2212.3744463863873,"GB2-04":1983.5665528286847,"GB2-05":2398.3583737087192,"GB2-06":2141.7826618543404,"GB2-07":2573.9046441008413,"GB2-08":2322.647388948712},"none":{"GB2-01":2068.123611246923,"GB2-02":1666.2831109218037,"GB2-03":1701.873617291561,"GB2-04":1817.3883936426942,"GB2-05":2488.2030667631757,"GB2-06":2020.4736193031572,"GB2-07":2403.88994412186,"GB2-08":1948.6147851564679}},"per_game_tracks":{"highest":{"GB2-01":96.98236362091885,"GB2-02":95.90145858688511,"GB2-03":97.58485139460286,"GB2-04":92.48053609371028,"GB2-05":98.85211617832984,"GB2-06":88.07766704375915,"GB2-07":97.6839209398181,"GB2-08":88.2848141474208},"medium":{"GB2-01":76.12994095332793,"GB2-02":81.089000619173,"GB2-03":94.82350599076405,"GB2-04":92.31790850632258,"GB2-05":92.86887794820855,"GB2-06":88.63978276857463,"GB2-07":96.86485907884945,"GB2-08":94.6782955977477},"none":{"GB2-01":92.87557589075594,"GB2-02":72.2616306700585,"GB2-03":75.45502443459601,"GB2-04":84.23206051667329,"GB2-05":94.4370858839511,"GB2-06":83.39456919062633,"GB2-07":94.41679346810483,"GB2-08":83.11416039258248}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-20T11:44:13Z","reasoning":{"highest":94.48096600068062,"medium":89.67652143287098,"none":85.02336255591855},"reasoning_agg":{"highest":{"max":98.85211617832984,"mean":94.48096600068062,"min":88.07766704375915},"medium":{"max":96.86485907884945,"mean":89.67652143287098,"min":76.12994095332793},"none":{"max":94.4370858839511,"mean":85.02336255591855,"min":72.2616306700585}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.457603444762071}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:3c83eaa852eeb416","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":17.677192},"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":3.0063079999999998},"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":1.0527920000000002}},"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":3.0063080000000006},"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":21.736292000000002},"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":88.67506622287367,"highest":95.14599863097473,"medium":92.86273256159828,"none":78.01646747604799},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":2}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":2}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":89.48933555358697,"score":89.48933555358697},"GB2-02":{"attempts":3,"playable":90.40278473915139,"score":90.40278473915139},"GB2-03":{"attempts":3,"playable":80.83123101588792,"score":80.83123101588792},"GB2-04":{"attempts":3,"playable":84.55747515214046,"score":84.55747515214046},"GB2-05":{"attempts":3,"playable":93.4387572242203,"score":93.4387572242203},"GB2-06":{"attempts":3,"playable":89.33267430595596,"score":89.33267430595596},"GB2-07":{"attempts":3,"playable":94.36369488781379,"score":94.36369488781379},"GB2-08":{"attempts":5,"playable":86.98457690423258,"score":86.98457690423258}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.0965979608449,"score":84.0965979608449},"GB2-02":{"attempts":1,"playable":95.70583650457732,"score":95.70583650457732},"GB2-03":{"attempts":1,"playable":97.25802231969577,"score":97.25802231969577},"GB2-04":{"attempts":1,"playable":94.82513868442955,"score":94.82513868442955},"GB2-05":{"attempts":1,"playable":98.1187730527003,"score":98.1187730527003},"GB2-06":{"attempts":1,"playable":99.32809674450233,"score":99.32809674450233},"GB2-07":{"attempts":1,"playable":97.89767775966322,"score":97.89767775966322},"GB2-08":{"attempts":1,"playable":93.93784602138442,"score":93.93784602138442}},"medium":{"GB2-01":{"attempts":1,"playable":93.5063967086133,"score":93.5063967086133},"GB2-02":{"attempts":1,"playable":95.39078641016926,"score":95.39078641016926},"GB2-03":{"attempts":1,"playable":92.3651724667543,"score":92.3651724667543},"GB2-04":{"attempts":1,"playable":89.18159395772547,"score":89.18159395772547},"GB2-05":{"attempts":1,"playable":90.20203355716399,"score":90.20203355716399},"GB2-06":{"attempts":1,"playable":91.37085428895585,"score":91.37085428895585},"GB2-07":{"attempts":1,"playable":93.64694889789642,"score":93.64694889789642},"GB2-08":{"attempts":2,"playable":97.23807420550776,"score":97.23807420550776}},"none":{"GB2-01":{"attempts":1,"playable":90.86501199130272,"score":90.86501199130272},"GB2-02":{"attempts":1,"playable":80.11173130270757,"score":80.11173130270757},"GB2-03":{"attempts":1,"playable":52.87049826121367,"score":52.87049826121367},"GB2-04":{"attempts":1,"playable":69.66569281426634,"score":69.66569281426634},"GB2-05":{"attempts":1,"playable":91.99546506279658,"score":91.99546506279658},"GB2-06":{"attempts":1,"playable":77.29907188440974,"score":77.29907188440974},"GB2-07":{"attempts":1,"playable":91.54645800588172,"score":91.54645800588172},"GB2-08":{"attempts":2,"playable":69.77781048580559,"score":69.77781048580559}}},"id":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:56:24Z","match_totals_all":{"draws":908,"losses":1062,"wins":10642},"match_totals_tracks":{"highest":{"draws":73,"losses":145,"wins":3646},"medium":{"draws":121,"losses":231,"wins":4024},"none":{"draws":714,"losses":686,"wins":2972}},"model_slug":"claude-opus-5-5","overall":{"max":99.32809674450233,"mean":88.67506622287367,"min":52.87049826121367},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.0965979608449,"GB2-02":95.70583650457732,"GB2-03":97.25802231969577,"GB2-04":94.82513868442955,"GB2-05":98.1187730527003,"GB2-06":99.32809674450233,"GB2-07":97.89767775966322,"GB2-08":93.93784602138442},"per_game_all":{"GB2-01":89.48933555358697,"GB2-02":90.40278473915139,"GB2-03":80.83123101588792,"GB2-04":84.55747515214046,"GB2-05":93.4387572242203,"GB2-06":89.33267430595596,"GB2-07":94.36369488781379,"GB2-08":86.98457690423258},"per_game_match_totals_all":{"GB2-01":{"draws":61,"losses":130,"wins":1273},"GB2-02":{"draws":135,"losses":65,"wins":1162},"GB2-03":{"draws":342,"losses":118,"wins":954},"GB2-04":{"draws":288,"losses":80,"wins":1042},"GB2-05":{"draws":0,"losses":99,"wins":1413},"GB2-06":{"draws":58,"losses":128,"wins":1246},"GB2-07":{"draws":0,"losses":75,"wins":1421},"GB2-08":{"draws":24,"losses":367,"wins":2131}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":78,"wins":402},"GB2-02":{"draws":23,"losses":7,"wins":424},"GB2-03":{"draws":3,"losses":10,"wins":455},"GB2-04":{"draws":38,"losses":5,"wins":427},"GB2-05":{"draws":0,"losses":7,"wins":497},"GB2-06":{"draws":1,"losses":0,"wins":475},"GB2-07":{"draws":0,"losses":7,"wins":493},"GB2-08":{"draws":0,"losses":31,"wins":473}},"medium":{"GB2-01":{"draws":32,"losses":17,"wins":439},"GB2-02":{"draws":11,"losses":15,"wins":428},"GB2-03":{"draws":23,"losses":26,"wins":423},"GB2-04":{"draws":34,"losses":36,"wins":400},"GB2-05":{"draws":0,"losses":51,"wins":453},"GB2-06":{"draws":21,"losses":32,"wins":425},"GB2-07":{"draws":0,"losses":28,"wins":472},"GB2-08":{"draws":0,"losses":26,"wins":984}},"none":{"GB2-01":{"draws":21,"losses":35,"wins":432},"GB2-02":{"draws":101,"losses":43,"wins":310},"GB2-03":{"draws":316,"losses":82,"wins":76},"GB2-04":{"draws":216,"losses":39,"wins":215},"GB2-05":{"draws":0,"losses":41,"wins":463},"GB2-06":{"draws":36,"losses":96,"wins":346},"GB2-07":{"draws":0,"losses":40,"wins":456},"GB2-08":{"draws":24,"losses":310,"wins":674}}},"per_game_raw_elo_all":{"GB2-01":1987.9815679716878,"GB2-02":1997.5933551094938,"GB2-03":1978.022440664715,"GB2-04":1872.5070045918262,"GB2-05":2478.477607477071,"GB2-06":2309.0674041548277,"GB2-07":2427.613590765188,"GB2-08":2158.199774971138},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1865.6328154499806,"GB2-02":2125.1726118881033,"GB2-03":2382.409041861418,"GB2-04":2067.3864960160663,"GB2-05":2813.3730334292977,"GB2-06":2810.9547651261046,"GB2-07":2671.9975294521664,"GB2-08":2286.981384006885},"medium":{"GB2-01":2089.7911573745114,"GB2-02":2109.760690256386,"GB2-03":2093.823362448269,"GB2-04":1906.953815039115,"GB2-05":2268.7190590531245,"GB2-06":2218.3224073786278,"GB2-07":2359.3619821625693,"GB2-08":2510.237275084183},"none":{"GB2-01":2008.5207310905719,"GB2-02":1757.846763183992,"GB2-03":1457.834917684458,"GB2-04":1643.1807027202967,"GB2-05":2353.340729948792,"GB2-06":1897.9250399597513,"GB2-07":2251.481260680828,"GB2-08":1677.3806658223466}},"per_game_tracks":{"highest":{"GB2-01":84.0965979608449,"GB2-02":95.70583650457732,"GB2-03":97.25802231969577,"GB2-04":94.82513868442955,"GB2-05":98.1187730527003,"GB2-06":99.32809674450233,"GB2-07":97.89767775966322,"GB2-08":93.93784602138442},"medium":{"GB2-01":93.5063967086133,"GB2-02":95.39078641016926,"GB2-03":92.3651724667543,"GB2-04":89.18159395772547,"GB2-05":90.20203355716399,"GB2-06":91.37085428895585,"GB2-07":93.64694889789642,"GB2-08":97.23807420550776},"none":{"GB2-01":90.86501199130272,"GB2-02":80.11173130270757,"GB2-03":52.87049826121367,"GB2-04":69.66569281426634,"GB2-05":91.99546506279658,"GB2-06":77.29907188440974,"GB2-07":91.54645800588172,"GB2-08":69.77781048580559}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-20T11:37:56Z","reasoning":{"highest":95.14599863097473,"medium":92.86273256159828,"none":78.01646747604799},"reasoning_agg":{"highest":{"max":99.32809674450233,"mean":95.14599863097473,"min":84.0965979608449},"medium":{"max":97.23807420550776,"mean":92.86273256159828,"min":89.18159395772547},"none":{"max":91.99546506279658,"mean":78.01646747604799,"min":52.87049826121367}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.129531154926738}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:27235abc8664b630","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.73911793121369},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"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":true,"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":true,"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},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"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":6.339052010326091},"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":64.31171957781584},"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":88.46928992061162,"highest":94.09286112095916,"medium":84.7824963380544,"none":86.53251230282129},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":11,"evaluated_cells":11,"first_pass_admitted":9,"first_pass_rate":0.8181818181818182,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":1,"infra_failures_excluded":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":85.06146503699152,"score":85.06146503699152},"GB2-02":{"attempts":3,"playable":89.7040613576347,"score":89.7040613576347},"GB2-03":{"attempts":4,"playable":93.73621794856619,"score":93.73621794856619},"GB2-04":{"attempts":4,"playable":74.58790791782339,"score":74.58790791782339},"GB2-05":{"attempts":3,"playable":91.28222929775002,"score":91.28222929775002},"GB2-06":{"attempts":3,"playable":89.53877806006558,"score":89.53877806006558},"GB2-07":{"attempts":4,"playable":92.21850342503713,"score":92.21850342503713},"GB2-08":{"attempts":3,"playable":91.62515632102439,"score":91.62515632102439}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":92.64270067939906,"score":92.64270067939906},"GB2-02":{"attempts":1,"playable":94.09000178870048,"score":94.09000178870048},"GB2-03":{"attempts":2,"playable":95.48355837151614,"score":95.48355837151614},"GB2-04":{"attempts":2,"playable":87.3622515851607,"score":87.3622515851607},"GB2-05":{"attempts":1,"playable":93.4077600763684,"score":93.4077600763684},"GB2-06":{"attempts":1,"playable":98.19022383237156,"score":98.19022383237156},"GB2-07":{"attempts":2,"playable":94.01705846683498,"score":94.01705846683498},"GB2-08":{"attempts":1,"playable":97.54933416732183,"score":97.54933416732183}},"medium":{"GB2-01":{"attempts":1,"playable":73.66707913785471,"score":73.66707913785471},"GB2-02":{"attempts":1,"playable":92.08122065501242,"score":92.08122065501242},"GB2-03":{"attempts":1,"playable":91.95134391486242,"score":91.95134391486242},"GB2-04":{"attempts":1,"playable":63.75471525634321,"score":63.75471525634321},"GB2-05":{"attempts":1,"playable":88.60168005635472,"score":88.60168005635472},"GB2-06":{"attempts":1,"playable":86.60287585551546,"score":86.60287585551546},"GB2-07":{"attempts":1,"playable":93.81612414068607,"score":93.81612414068607},"GB2-08":{"attempts":1,"playable":87.7849316878062,"score":87.7849316878062}},"none":{"GB2-01":{"attempts":1,"playable":88.87461529372077,"score":88.87461529372077},"GB2-02":{"attempts":1,"playable":82.94096162919116,"score":82.94096162919116},"GB2-03":{"attempts":1,"playable":93.77375155931999,"score":93.77375155931999},"GB2-04":{"attempts":1,"playable":72.64675691196624,"score":72.64675691196624},"GB2-05":{"attempts":1,"playable":91.83724776052696,"score":91.83724776052696},"GB2-06":{"attempts":1,"playable":83.8232344923097,"score":83.8232344923097},"GB2-07":{"attempts":1,"playable":88.82232766759032,"score":88.82232766759032},"GB2-08":{"attempts":1,"playable":89.54120310794515,"score":89.54120310794515}}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-10-22T10:59:24Z","match_totals_all":{"draws":746,"losses":1100,"wins":11190},"match_totals_tracks":{"highest":{"draws":122,"losses":270,"wins":4906},"medium":{"draws":292,"losses":462,"wins":3119},"none":{"draws":332,"losses":368,"wins":3165}},"model_slug":"claude-fable-5-1","overall":{"max":98.19022383237156,"mean":88.46928992061162,"min":63.75471525634321},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":92.64270067939906,"GB2-02":94.09000178870048,"GB2-03":95.48355837151614,"GB2-04":87.3622515851607,"GB2-05":93.4077600763684,"GB2-06":98.19022383237156,"GB2-07":94.01705846683498,"GB2-08":97.54933416732183},"per_game_all":{"GB2-01":85.06146503699152,"GB2-02":89.7040613576347,"GB2-03":93.73621794856619,"GB2-04":74.58790791782339,"GB2-05":91.28222929775002,"GB2-06":89.53877806006558,"GB2-07":92.21850342503713,"GB2-08":91.62515632102439},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":35,"wins":453},"GB2-02":{"draws":26,"losses":13,"wins":419},"GB2-03":{"draws":3,"losses":22,"wins":443},"GB2-04":{"draws":45,"losses":28,"wins":397},"GB2-05":{"draws":0,"losses":32,"wins":474},"GB2-06":{"draws":3,"losses":5,"wins":470},"GB2-07":{"draws":0,"losses":27,"wins":465},"GB2-08":{"draws":0,"losses":11,"wins":495}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":35,"wins":453},"GB2-02":{"draws":26,"losses":13,"wins":419},"GB2-03":{"draws":3,"losses":22,"wins":443},"GB2-04":{"draws":45,"losses":28,"wins":397},"GB2-05":{"draws":0,"losses":32,"wins":474},"GB2-06":{"draws":3,"losses":5,"wins":470},"GB2-07":{"draws":0,"losses":27,"wins":465},"GB2-08":{"draws":0,"losses":11,"wins":495}}},"per_game_raw_elo_all":{"GB2-01":1912.3228814178292,"GB2-02":1946.5476436119004,"GB2-03":2162.324064722056,"GB2-04":1711.996420703039,"GB2-05":2324.488223853276,"GB2-06":2237.2395524570857,"GB2-07":2295.373985271322,"GB2-08":2236.7240503571716},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2060.538375505906,"GB2-02":2054.4815676078406,"GB2-03":2252.650067374254,"GB2-04":1873.8522830521533,"GB2-05":2427.731561305049,"GB2-06":2590.2434967011613,"GB2-07":2380.3901083786413,"GB2-08":2517.068930485359},"medium":{"GB2-01":1716.9366158813586,"GB2-02":1987.0724612757926,"GB2-03":2076.9676537850587,"GB2-04":1589.2632530108815,"GB2-05":2200.2494103203,"GB2-06":2091.845290121125,"GB2-07":2368.8904727382524,"GB2-08":2070.266096982883},"none":{"GB2-01":1959.4936528662226,"GB2-02":1798.0889019520678,"GB2-03":2157.3544730068543,"GB2-04":1672.8737260460825,"GB2-05":2345.4836999344784,"GB2-06":2029.6298705489703,"GB2-07":2136.841374697072,"GB2-08":2122.837123603273}},"per_game_tracks":{"highest":{"GB2-01":92.64270067939906,"GB2-02":94.09000178870048,"GB2-03":95.48355837151614,"GB2-04":87.3622515851607,"GB2-05":93.4077600763684,"GB2-06":98.19022383237156,"GB2-07":94.01705846683498,"GB2-08":97.54933416732183},"medium":{"GB2-01":73.66707913785471,"GB2-02":92.08122065501242,"GB2-03":91.95134391486242,"GB2-04":63.75471525634321,"GB2-05":88.60168005635472,"GB2-06":86.60287585551546,"GB2-07":93.81612414068607,"GB2-08":87.7849316878062},"none":{"GB2-01":88.87461529372077,"GB2-02":82.94096162919116,"GB2-03":93.77375155931999,"GB2-04":72.64675691196624,"GB2-05":91.83724776052696,"GB2-06":83.8232344923097,"GB2-07":88.82232766759032,"GB2-08":89.54120310794515}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-20T11:49:26Z","reasoning":{"highest":94.09286112095916,"medium":84.7824963380544,"none":86.53251230282129},"reasoning_agg":{"highest":{"max":98.19022383237156,"mean":94.09286112095916,"min":87.3622515851607},"medium":{"max":93.81612414068607,"mean":84.7824963380544,"min":63.75471525634321},"none":{"max":93.77375155931999,"mean":86.53251230282129,"min":72.64675691196624}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.310364782904756}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:8978743dc552e304","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":0.355686,"mean":0.2665285,"median":0.263151,"min":0.174431,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.132228},"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":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.674699},"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":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.38850799999999996}},"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":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6746989999999999},"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":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.38850799999999996},"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":0.355686,"mean":0.2665285,"median":0.263151,"min":0.174431,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.132228}},"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":0.355686,"mean":0.133143125,"median":0.0768835,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":3.195435},"codegen_latency_ms":{"attempt_count":25,"max_ms":926657,"mean_ms":272565.25,"min_ms":42196,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":926657,"mean_ms":625149.0,"min_ms":331732,"run_count":8},"medium":{"attempt_count":9,"max_ms":198934,"mean_ms":135760.75,"min_ms":63072,"run_count":8},"none":{"attempt_count":8,"max_ms":73464,"mean_ms":56786.0,"min_ms":42196,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":33557,"output_mean":11287.458333333334,"output_min":2159,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":33557,"output_mean":24715.125,"output_min":14936,"run_count":8},"medium":{"attempt_count":9,"output_max":9484,"output_mean":6228.625,"output_min":3242,"run_count":8},"none":{"attempt_count":8,"output_max":3711,"output_mean":2918.625,"output_min":2159,"run_count":8}},"display_name":"GPT-6.1 Sol","economics":{"all":85.83216818185463,"highest":92.68284832188934,"medium":87.298426970645,"none":77.5152292530295},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[128000],"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":[128000],"total_output_tokens":270899,"total_reasoning_output_tokens":149779,"total_visible_output_tokens":121120,"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":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":67.74003065584262,"score":67.74003065584262},"GB2-02":{"attempts":3,"playable":79.32432080414604,"score":79.32432080414604},"GB2-03":{"attempts":3,"playable":93.59065852723188,"score":93.59065852723188},"GB2-04":{"attempts":3,"playable":85.083744797908,"score":85.083744797908},"GB2-05":{"attempts":3,"playable":94.84190030310238,"score":94.84190030310238},"GB2-06":{"attempts":3,"playable":86.82801805254438,"score":86.82801805254438},"GB2-07":{"attempts":3,"playable":95.34271149433857,"score":95.34271149433857},"GB2-08":{"attempts":3,"playable":83.90596081972302,"score":83.90596081972302}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.29801798423388,"score":76.29801798423388},"GB2-02":{"attempts":1,"playable":94.51092023180135,"score":94.51092023180135},"GB2-03":{"attempts":1,"playable":98.0483368856607,"score":98.0483368856607},"GB2-04":{"attempts":1,"playable":95.18274101790296,"score":95.18274101790296},"GB2-05":{"attempts":1,"playable":98.0843623695457,"score":98.0843623695457},"GB2-06":{"attempts":1,"playable":89.75784068537422,"score":89.75784068537422},"GB2-07":{"attempts":1,"playable":95.78654909579892,"score":95.78654909579892},"GB2-08":{"attempts":1,"playable":93.79401830479691,"score":93.79401830479691}},"medium":{"GB2-01":{"attempts":1,"playable":75.36473929089426,"score":75.36473929089426},"GB2-02":{"attempts":1,"playable":79.1563545473246,"score":79.1563545473246},"GB2-03":{"attempts":1,"playable":96.96728334716104,"score":96.96728334716104},"GB2-04":{"attempts":1,"playable":86.9797553916504,"score":86.9797553916504},"GB2-05":{"attempts":1,"playable":94.97744878647988,"score":94.97744878647988},"GB2-06":{"attempts":1,"playable":90.73568256887557,"score":90.73568256887557},"GB2-07":{"attempts":1,"playable":95.82370704560776,"score":95.82370704560776},"GB2-08":{"attempts":1,"playable":78.38244478716653,"score":78.38244478716653}},"none":{"GB2-01":{"attempts":1,"playable":51.557334692399714,"score":51.557334692399714},"GB2-02":{"attempts":1,"playable":64.30568763331216,"score":64.30568763331216},"GB2-03":{"attempts":1,"playable":85.75635534887392,"score":85.75635534887392},"GB2-04":{"attempts":1,"playable":73.08873798417065,"score":73.08873798417065},"GB2-05":{"attempts":1,"playable":91.46388975328158,"score":91.46388975328158},"GB2-06":{"attempts":1,"playable":79.99053090338334,"score":79.99053090338334},"GB2-07":{"attempts":1,"playable":94.41787834160905,"score":94.41787834160905},"GB2-08":{"attempts":1,"playable":79.5414193672056,"score":79.5414193672056}}},"id":"gpt-6.1-sol","is_recent_addition":false,"last_measured_at":"2026-10-22T10:44:36Z","match_totals_all":{"draws":873,"losses":1249,"wins":9462},"match_totals_tracks":{"highest":{"draws":105,"losses":228,"wins":3533},"medium":{"draws":214,"losses":396,"wins":3246},"none":{"draws":554,"losses":625,"wins":2683}},"model_slug":"gpt-6-1-sol","overall":{"max":98.0843623695457,"mean":85.83216818185463,"min":51.557334692399714},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.29801798423388,"GB2-02":94.51092023180135,"GB2-03":98.0483368856607,"GB2-04":95.18274101790296,"GB2-05":98.0843623695457,"GB2-06":89.75784068537422,"GB2-07":95.78654909579892,"GB2-08":93.79401830479691},"per_game_all":{"GB2-01":67.74003065584262,"GB2-02":79.32432080414604,"GB2-03":93.59065852723188,"GB2-04":85.083744797908,"GB2-05":94.84190030310238,"GB2-06":86.82801805254438,"GB2-07":95.34271149433857,"GB2-08":83.90596081972302},"per_game_match_totals_all":{"GB2-01":{"draws":69,"losses":459,"wins":936},"GB2-02":{"draws":428,"losses":77,"wins":857},"GB2-03":{"draws":34,"losses":78,"wins":1292},"GB2-04":{"draws":232,"losses":101,"wins":1077},"GB2-05":{"draws":0,"losses":75,"wins":1437},"GB2-06":{"draws":108,"losses":142,"wins":1178},"GB2-07":{"draws":0,"losses":60,"wins":1426},"GB2-08":{"draws":2,"losses":257,"wins":1259}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":120,"wins":368},"GB2-02":{"draws":30,"losses":10,"wins":414},"GB2-03":{"draws":2,"losses":7,"wins":459},"GB2-04":{"draws":34,"losses":6,"wins":430},"GB2-05":{"draws":0,"losses":7,"wins":497},"GB2-06":{"draws":39,"losses":29,"wins":408},"GB2-07":{"draws":0,"losses":18,"wins":484},"GB2-08":{"draws":0,"losses":31,"wins":473}},"medium":{"GB2-01":{"draws":11,"losses":120,"wins":357},"GB2-02":{"draws":130,"losses":34,"wins":290},"GB2-03":{"draws":4,"losses":11,"wins":453},"GB2-04":{"draws":36,"losses":46,"wins":388},"GB2-05":{"draws":0,"losses":23,"wins":481},"GB2-06":{"draws":33,"losses":30,"wins":413},"GB2-07":{"draws":0,"losses":17,"wins":475},"GB2-08":{"draws":0,"losses":115,"wins":389}},"none":{"GB2-01":{"draws":58,"losses":219,"wins":211},"GB2-02":{"draws":268,"losses":33,"wins":153},"GB2-03":{"draws":28,"losses":60,"wins":380},"GB2-04":{"draws":162,"losses":49,"wins":259},"GB2-05":{"draws":0,"losses":45,"wins":459},"GB2-06":{"draws":36,"losses":83,"wins":357},"GB2-07":{"draws":0,"losses":25,"wins":467},"GB2-08":{"draws":2,"losses":111,"wins":397}}},"per_game_raw_elo_all":{"GB2-01":1657.9997941341892,"GB2-02":1802.439085229631,"GB2-03":2235.9609251596066,"GB2-04":1874.4192404305259,"GB2-05":2552.912268833878,"GB2-06":2107.0993947827433,"GB2-07":2463.568674712776,"GB2-08":1996.528762607382},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1750.084650362304,"GB2-02":2071.1025581838335,"GB2-03":2462.653185282222,"GB2-04":2082.1265232015253,"GB2-05":2808.5729802721735,"GB2-06":2171.4734969228857,"GB2-07":2492.076788632153,"GB2-08":2280.4413883932248},"medium":{"GB2-01":1738.0786985088862,"GB2-02":1745.3261079867277,"GB2-03":2357.3254678283392,"GB2-04":1863.6735492859116,"GB2-05":2522.8965930000377,"GB2-06":2199.211938866347,"GB2-07":2494.6743296996938,"GB2-08":1842.1227120506298},"none":{"GB2-01":1485.8360335313778,"GB2-02":1590.8885895183323,"GB2-03":1887.9041223682584,"GB2-04":1677.4576488041407,"GB2-05":2327.2672332294223,"GB2-06":1950.612748558998,"GB2-07":2403.954905806482,"GB2-08":1867.0221873782912}},"per_game_tracks":{"highest":{"GB2-01":76.29801798423388,"GB2-02":94.51092023180135,"GB2-03":98.0483368856607,"GB2-04":95.18274101790296,"GB2-05":98.0843623695457,"GB2-06":89.75784068537422,"GB2-07":95.78654909579892,"GB2-08":93.79401830479691},"medium":{"GB2-01":75.36473929089426,"GB2-02":79.1563545473246,"GB2-03":96.96728334716104,"GB2-04":86.9797553916504,"GB2-05":94.97744878647988,"GB2-06":90.73568256887557,"GB2-07":95.82370704560776,"GB2-08":78.38244478716653},"none":{"GB2-01":51.557334692399714,"GB2-02":64.30568763331216,"GB2-03":85.75635534887392,"GB2-04":73.08873798417065,"GB2-05":91.46388975328158,"GB2-06":79.99053090338334,"GB2-07":94.41787834160905,"GB2-08":79.5414193672056}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-20T11:37:59Z","reasoning":{"highest":92.68284832188934,"medium":87.298426970645,"none":77.5152292530295},"reasoning_agg":{"highest":{"max":98.0843623695457,"mean":92.68284832188934,"min":76.29801798423388},"medium":{"max":96.96728334716104,"mean":87.298426970645,"min":75.36473929089426},"none":{"max":94.41787834160905,"mean":77.5152292530295,"min":51.557334692399714}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":15.167619068859835}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-4-argon:0859c5f87f0c4cf2","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":0.582036,"mean":0.440512,"median":0.446556,"min":0.29813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":3.5240959999999997},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.22172,"mean":0.09679175,"median":0.079292,"min":0.064396,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.774334},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124048,"mean":0.08425525,"median":0.081095,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.674042}},"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":true,"evidence_basis":"Standard list-price estimate","max":0.22172,"mean":0.09679175,"median":0.079292,"min":0.064396,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7743340000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124048,"mean":0.08425525,"median":0.081095,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.674042},"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":0.582036,"mean":0.440512,"median":0.446556,"min":0.29813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":3.5240959999999997}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.582036,"mean":0.20718633333333333,"median":0.09228,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":4.972472000000002},"codegen_latency_ms":{"attempt_count":28,"max_ms":633783,"mean_ms":198313.91666666666,"min_ms":46974,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":633783,"mean_ms":450301.75,"min_ms":322608,"run_count":8},"medium":{"attempt_count":9,"max_ms":152424,"mean_ms":70572.25,"min_ms":46974,"run_count":8},"none":{"attempt_count":8,"max_ms":113522,"mean_ms":74067.75,"min_ms":52299,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":54729,"output_mean":18449.125,"output_min":4647,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":54729,"output_mean":41092.75,"output_min":28061,"run_count":8},"medium":{"attempt_count":9,"output_max":17530,"output_mean":7576.5,"output_min":4801,"run_count":8},"none":{"attempt_count":8,"output_max":10605,"output_mean":6678.125,"output_min":4647,"run_count":8}},"display_name":"Gemini 4 Argon","economics":{"all":82.88237303334637,"highest":89.36932224165065,"medium":78.2955336394559,"none":80.98226321893257},"first_seen_at":"2026-10-22T11:01:24Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[943718],"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,"requested_max_output_token_observations":28,"requested_max_output_tokens":[943718],"total_output_tokens":442779,"total_reasoning_output_tokens":206667,"total_visible_output_tokens":236112,"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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-4-argon","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"google","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":93.21370722739994,"score":93.21370722739994},"GB2-02":{"attempts":3,"playable":78.95158142126775,"score":78.95158142126775},"GB2-03":{"attempts":3,"playable":84.73073975397223,"score":84.73073975397223},"GB2-04":{"attempts":3,"playable":71.59160968261817,"score":71.59160968261817},"GB2-05":{"attempts":3,"playable":92.12447083393427,"score":92.12447083393427},"GB2-06":{"attempts":3,"playable":92.99516849832366,"score":92.99516849832366},"GB2-07":{"attempts":3,"playable":73.19521538555652,"score":73.19521538555652},"GB2-08":{"attempts":3,"playable":76.25649146369842,"score":76.25649146369842}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":95.50530753979888,"score":95.50530753979888},"GB2-02":{"attempts":1,"playable":94.49894507083326,"score":94.49894507083326},"GB2-03":{"attempts":1,"playable":90.6305256344094,"score":90.6305256344094},"GB2-04":{"attempts":1,"playable":68.1411372260694,"score":68.1411372260694},"GB2-05":{"attempts":1,"playable":95.73524924978136,"score":95.73524924978136},"GB2-06":{"attempts":1,"playable":97.33479876028103,"score":97.33479876028103},"GB2-07":{"attempts":1,"playable":83.6576566568642,"score":83.6576566568642},"GB2-08":{"attempts":1,"playable":89.45095779516777,"score":89.45095779516777}},"medium":{"GB2-01":{"attempts":1,"playable":92.5432439174945,"score":92.5432439174945},"GB2-02":{"attempts":1,"playable":65.60920218613754,"score":65.60920218613754},"GB2-03":{"attempts":1,"playable":78.9507671660973,"score":78.9507671660973},"GB2-04":{"attempts":1,"playable":69.18111948409256,"score":69.18111948409256},"GB2-05":{"attempts":1,"playable":91.40238034289673,"score":91.40238034289673},"GB2-06":{"attempts":1,"playable":91.36675432421674,"score":91.36675432421674},"GB2-07":{"attempts":1,"playable":76.04298018756417,"score":76.04298018756417},"GB2-08":{"attempts":1,"playable":61.26782150714766,"score":61.26782150714766}},"none":{"GB2-01":{"attempts":1,"playable":91.59257022490641,"score":91.59257022490641},"GB2-02":{"attempts":1,"playable":76.74659700683246,"score":76.74659700683246},"GB2-03":{"attempts":1,"playable":84.61092646141005,"score":84.61092646141005},"GB2-04":{"attempts":1,"playable":77.45257233769254,"score":77.45257233769254},"GB2-05":{"attempts":1,"playable":89.23578290912474,"score":89.23578290912474},"GB2-06":{"attempts":1,"playable":90.28395241047323,"score":90.28395241047323},"GB2-07":{"attempts":1,"playable":59.88500931224119,"score":59.88500931224119},"GB2-08":{"attempts":1,"playable":78.05069508877986,"score":78.05069508877986}}},"id":"gemini-4-argon","is_recent_addition":true,"last_measured_at":"2026-10-22T11:01:24Z","match_totals_all":{"draws":506,"losses":822,"wins":4754},"match_totals_tracks":{"highest":{"draws":96,"losses":159,"wins":1759},"medium":{"draws":244,"losses":358,"wins":1440},"none":{"draws":166,"losses":305,"wins":1555}},"model_slug":"gemini-4-argon","overall":{"max":97.33479876028103,"mean":82.88237303334637,"min":59.88500931224119},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.50530753979888,"GB2-02":94.49894507083326,"GB2-03":90.6305256344094,"GB2-04":68.1411372260694,"GB2-05":95.73524924978136,"GB2-06":97.33479876028103,"GB2-07":83.6576566568642,"GB2-08":89.45095779516777},"per_game_all":{"GB2-01":93.21370722739994,"GB2-02":78.95158142126775,"GB2-03":84.73073975397223,"GB2-04":71.59160968261817,"GB2-05":92.12447083393427,"GB2-06":92.99516849832366,"GB2-07":73.19521538555652,"GB2-08":76.25649146369842},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":63,"wins":701},"GB2-02":{"draws":186,"losses":77,"wins":527},"GB2-03":{"draws":95,"losses":71,"wins":586},"GB2-04":{"draws":202,"losses":137,"wins":449},"GB2-05":{"draws":0,"losses":54,"wins":764},"GB2-06":{"draws":23,"losses":53,"wins":758},"GB2-07":{"draws":0,"losses":182,"wins":480},"GB2-08":{"draws":0,"losses":185,"wins":489}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":16,"wins":242},"GB2-02":{"draws":26,"losses":0,"wins":228},"GB2-03":{"draws":27,"losses":6,"wins":213},"GB2-04":{"draws":39,"losses":68,"wins":153},"GB2-05":{"draws":0,"losses":6,"wins":262},"GB2-06":{"draws":4,"losses":3,"wins":271},"GB2-07":{"draws":0,"losses":33,"wins":189},"GB2-08":{"draws":0,"losses":27,"wins":201}},"medium":{"GB2-01":{"draws":0,"losses":25,"wins":227},"GB2-02":{"draws":80,"losses":56,"wins":132},"GB2-03":{"draws":57,"losses":31,"wins":164},"GB2-04":{"draws":95,"losses":44,"wins":137},"GB2-05":{"draws":0,"losses":20,"wins":252},"GB2-06":{"draws":12,"losses":20,"wins":240},"GB2-07":{"draws":0,"losses":58,"wins":162},"GB2-08":{"draws":0,"losses":104,"wins":126}},"none":{"GB2-01":{"draws":0,"losses":22,"wins":232},"GB2-02":{"draws":80,"losses":21,"wins":167},"GB2-03":{"draws":11,"losses":34,"wins":209},"GB2-04":{"draws":68,"losses":25,"wins":159},"GB2-05":{"draws":0,"losses":28,"wins":250},"GB2-06":{"draws":7,"losses":30,"wins":247},"GB2-07":{"draws":0,"losses":91,"wins":129},"GB2-08":{"draws":0,"losses":54,"wins":162}}},"per_game_raw_elo_all":{"GB2-01":2086.3907112948114,"GB2-02":1796.2519427498462,"GB2-03":1881.4577018962948,"GB2-04":1664.3668726336734,"GB2-05":2375.728173766204,"GB2-06":2302.0615490988716,"GB2-07":1790.7689943398445,"GB2-08":1833.525824935248},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2173.1327215245065,"GB2-02":2070.614637011382,"GB2-03":2027.66940466307,"GB2-04":1628.7177673606748,"GB2-05":2576.2131129315185,"GB2-06":2501.822855559233,"GB2-07":1978.3561425435464,"GB2-08":2120.009112271718},"medium":{"GB2-01":2057.3610848991443,"GB2-02":1602.4635634004655,"GB2-03":1754.9645271928975,"GB2-04":1638.535510110877,"GB2-05":2324.3080938555227,"GB2-06":2218.195910895929,"GB2-07":1818.4036347501658,"GB2-08":1545.4453370401425},"none":{"GB2-01":2028.6783274607847,"GB2-02":1715.677627837691,"GB2-03":1861.7391738329168,"GB2-04":1725.847340429468,"GB2-05":2226.6633145115693,"GB2-06":2186.1658808414536,"GB2-07":1575.547205725821,"GB2-08":1835.1230254938832}},"per_game_tracks":{"highest":{"GB2-01":95.50530753979888,"GB2-02":94.49894507083326,"GB2-03":90.6305256344094,"GB2-04":68.1411372260694,"GB2-05":95.73524924978136,"GB2-06":97.33479876028103,"GB2-07":83.6576566568642,"GB2-08":89.45095779516777},"medium":{"GB2-01":92.5432439174945,"GB2-02":65.60920218613754,"GB2-03":78.9507671660973,"GB2-04":69.18111948409256,"GB2-05":91.40238034289673,"GB2-06":91.36675432421674,"GB2-07":76.04298018756417,"GB2-08":61.26782150714766},"none":{"GB2-01":91.59257022490641,"GB2-02":76.74659700683246,"GB2-03":84.61092646141005,"GB2-04":77.45257233769254,"GB2-05":89.23578290912474,"GB2-06":90.28395241047323,"GB2-07":59.88500931224119,"GB2-08":78.05069508877986}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":89.36932224165065,"medium":78.2955336394559,"none":80.98226321893257},"reasoning_agg":{"highest":{"max":97.33479876028103,"mean":89.36932224165065,"min":68.1411372260694},"medium":{"max":92.5432439174945,"mean":78.2955336394559,"min":61.26782150714766},"none":{"max":91.59257022490641,"mean":80.98226321893257,"min":59.88500931224119}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":11.073788602194753}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:996469692da43622","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":7.138875},"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":4.570125}},"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":7.1388750000000005},"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":22.074450000000002}},"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":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":77.42216825386893,"highest":86.11148917086817,"medium":76.5339300349533,"none":72.00240545974616},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"first_pass_admitted":14,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"performance_rejections":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":2},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"first_pass_admitted":14,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"performance_rejections":1},"GB2-07":{"admitted":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"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},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":2},"intensive":{"admitted_plugins":13,"evaluated_cells":16,"first_pass_admitted":13,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"performance_rejections":2},"GB2-07":{"admitted":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"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},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":3}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":72.33902726977627,"score":72.33902726977627},"GB2-02":{"attempts":6,"playable":75.30511938207782,"score":75.30511938207782},"GB2-03":{"attempts":6,"playable":77.93881843668005,"score":77.93881843668005},"GB2-04":{"attempts":6,"playable":57.767413337907016,"score":57.767413337907016},"GB2-05":{"attempts":6,"playable":90.63864036336383,"score":90.63864036336383},"GB2-06":{"attempts":1,"playable":88.67164478747198,"score":88.67164478747198},"GB2-07":{"attempts":4,"playable":85.5574092396566,"score":85.5574092396566},"GB2-08":{"attempts":6,"playable":82.40874974762099,"score":82.40874974762099}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":69.52904704327482,"score":69.52904704327482},"GB2-02":{"attempts":2,"playable":83.4587817187461,"score":83.4587817187461},"GB2-03":{"attempts":2,"playable":95.18592255261042,"score":95.18592255261042},"GB2-04":{"attempts":2,"playable":80.30485322186144,"score":80.30485322186144},"GB2-05":{"attempts":2,"playable":93.4990006003388,"score":93.4990006003388},"GB2-07":{"attempts":1,"playable":95.96817677781134,"score":95.96817677781134},"GB2-08":{"attempts":2,"playable":84.83464228143428,"score":84.83464228143428}},"medium":{"GB2-01":{"attempts":2,"playable":71.5641400777784,"score":71.5641400777784},"GB2-02":{"attempts":2,"playable":70.49310016546755,"score":70.49310016546755},"GB2-03":{"attempts":2,"playable":86.6147576086781,"score":86.6147576086781},"GB2-04":{"attempts":2,"playable":44.26190041589739,"score":44.26190041589739},"GB2-05":{"attempts":2,"playable":89.22514593592935,"score":89.22514593592935},"GB2-07":{"attempts":2,"playable":84.30942667679942,"score":84.30942667679942},"GB2-08":{"attempts":2,"playable":89.26903936412288,"score":89.26903936412288}},"none":{"GB2-01":{"attempts":2,"playable":75.92389468827557,"score":75.92389468827557},"GB2-02":{"attempts":2,"playable":71.96347626201978,"score":71.96347626201978},"GB2-03":{"attempts":2,"playable":52.01577514875164,"score":52.01577514875164},"GB2-04":{"attempts":2,"playable":48.73548637596222,"score":48.73548637596222},"GB2-05":{"attempts":2,"playable":89.19177455382331,"score":89.19177455382331},"GB2-06":{"attempts":1,"playable":88.67164478747198,"score":88.67164478747198},"GB2-07":{"attempts":1,"playable":76.39462426435905,"score":76.39462426435905},"GB2-08":{"attempts":2,"playable":73.12256759730579,"score":73.12256759730579}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:37:00Z","match_totals_all":{"draws":2567,"losses":3345,"wins":13915},"match_totals_tracks":{"highest":{"draws":353,"losses":768,"wins":5165},"medium":{"draws":924,"losses":1162,"wins":4691},"none":{"draws":1290,"losses":1415,"wins":4059}},"model_slug":"claude-opus-5","overall":{"max":95.96817677781134,"mean":78.2159415551892,"min":44.26190041589739},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":69.52904704327482,"GB2-02":83.4587817187461,"GB2-03":95.18592255261042,"GB2-04":80.30485322186144,"GB2-05":93.4990006003388,"GB2-07":95.96817677781134,"GB2-08":84.83464228143428},"per_game_all":{"GB2-01":72.33902726977627,"GB2-02":75.30511938207782,"GB2-03":77.93881843668005,"GB2-04":57.767413337907016,"GB2-05":90.63864036336383,"GB2-07":85.5574092396566,"GB2-08":82.40874974762099},"per_game_match_totals_all":{"GB2-01":{"draws":460,"losses":609,"wins":1863},"GB2-02":{"draws":930,"losses":237,"wins":1568},"GB2-03":{"draws":152,"losses":588,"wins":2072},"GB2-04":{"draws":953,"losses":747,"wins":1122},"GB2-05":{"draws":0,"losses":284,"wins":2744},"GB2-06":{"draws":30,"losses":44,"wins":408},"GB2-07":{"draws":0,"losses":291,"wins":1687},"GB2-08":{"draws":42,"losses":545,"wins":2451}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":299,"wins":662},"GB2-02":{"draws":181,"losses":65,"wins":666},"GB2-03":{"draws":8,"losses":42,"wins":888},"GB2-04":{"draws":149,"losses":119,"wins":674},"GB2-05":{"draws":0,"losses":64,"wins":948},"GB2-07":{"draws":0,"losses":17,"wins":477},"GB2-08":{"draws":0,"losses":162,"wins":850}},"medium":{"GB2-01":{"draws":95,"losses":241,"wins":642},"GB2-02":{"draws":384,"losses":91,"wins":440},"GB2-03":{"draws":16,"losses":129,"wins":793},"GB2-04":{"draws":427,"losses":324,"wins":189},"GB2-05":{"draws":0,"losses":111,"wins":897},"GB2-07":{"draws":0,"losses":155,"wins":829},"GB2-08":{"draws":2,"losses":111,"wins":901}},"none":{"GB2-01":{"draws":350,"losses":69,"wins":559},"GB2-02":{"draws":365,"losses":81,"wins":462},"GB2-03":{"draws":128,"losses":417,"wins":391},"GB2-04":{"draws":377,"losses":304,"wins":259},"GB2-05":{"draws":0,"losses":109,"wins":899},"GB2-06":{"draws":30,"losses":44,"wins":408},"GB2-07":{"draws":0,"losses":119,"wins":381},"GB2-08":{"draws":40,"losses":272,"wins":700}}},"per_game_raw_elo_all":{"GB2-01":1742.2141488401278,"GB2-02":1709.3044103444493,"GB2-03":1864.6085668999829,"GB2-04":1558.531239430642,"GB2-05":2347.660109989915,"GB2-07":2124.9151974762153,"GB2-08":1963.2029987193716},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1736.8958351717806,"GB2-02":1813.8028398980027,"GB2-03":2234.571369391374,"GB2-04":1773.5178517778822,"GB2-05":2575.57166530668,"GB2-07":2504.9012431480646,"GB2-08":2015.1894025841125},"medium":{"GB2-01":1705.903570289186,"GB2-02":1648.411242411341,"GB2-03":1908.899645715759,"GB2-04":1433.4806022258815,"GB2-05":2242.5687644701984,"GB2-07":2045.1130015833303,"GB2-08":2134.1808605975934},"none":{"GB2-01":1783.8430410594171,"GB2-02":1665.6991487240039,"GB2-03":1450.3546855928153,"GB2-04":1468.5952642881623,"GB2-05":2224.8399001928665,"GB2-06":2142.6031665934815,"GB2-07":1824.7313476972508,"GB2-08":1740.2387329764092}},"per_game_tracks":{"highest":{"GB2-01":69.52904704327482,"GB2-02":83.4587817187461,"GB2-03":95.18592255261042,"GB2-04":80.30485322186144,"GB2-05":93.4990006003388,"GB2-07":95.96817677781134,"GB2-08":84.83464228143428},"medium":{"GB2-01":71.5641400777784,"GB2-02":70.49310016546755,"GB2-03":86.6147576086781,"GB2-04":44.26190041589739,"GB2-05":89.22514593592935,"GB2-07":84.30942667679942,"GB2-08":89.26903936412288},"none":{"GB2-01":75.92389468827557,"GB2-02":71.96347626201978,"GB2-03":52.01577514875164,"GB2-04":48.73548637596222,"GB2-05":89.19177455382331,"GB2-06":88.67164478747198,"GB2-07":76.39462426435905,"GB2-08":73.12256759730579}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-20T11:39:05Z","reasoning":{"highest":86.11148917086817,"medium":76.5339300349533,"none":72.00240545974616},"reasoning_agg":{"highest":{"max":95.96817677781134,"mean":86.11148917086817,"min":69.52904704327482},"medium":{"max":89.26903936412288,"mean":76.5339300349533,"min":44.26190041589739},"none":{"max":89.19177455382331,"mean":72.00240545974616,"min":48.73548637596222}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.109083711122011}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:786a870023383395","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":1.6543579999999998},"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":0.345568},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.10943510416666667,"median":0.0772785,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":2.6264425},"codegen_output_tokens":{"attempt_count":25,"output_max":20604,"output_mean":8932.083333333334,"output_min":1527,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":20604,"output_mean":18742.75,"output_min":16066,"run_count":8},"medium":{"attempt_count":9,"output_max":7600,"output_mean":5670.625,"output_min":3698,"run_count":8},"none":{"attempt_count":8,"output_max":3203,"output_mean":2382.875,"output_min":1527,"run_count":8}},"display_name":"GPT-6 Sol","economics":{"all":74.55110552839074,"highest":80.4747311859286,"medium":76.27707871288867,"none":66.90150668635498},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":37.493096457562,"score":37.493096457562},"GB2-02":{"attempts":3,"playable":68.19479658406593,"score":68.19479658406593},"GB2-03":{"attempts":3,"playable":83.67553387201245,"score":83.67553387201245},"GB2-04":{"attempts":3,"playable":68.69322378238401,"score":68.69322378238401},"GB2-05":{"attempts":3,"playable":87.8558540551702,"score":87.8558540551702},"GB2-06":{"attempts":3,"playable":81.70537994917393,"score":81.70537994917393},"GB2-07":{"attempts":3,"playable":82.2520806725301,"score":82.2520806725301},"GB2-08":{"attempts":3,"playable":86.53887885422733,"score":86.53887885422733}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":10.386376300158082,"score":10.386376300158082},"GB2-02":{"attempts":1,"playable":83.15632164945426,"score":83.15632164945426},"GB2-03":{"attempts":1,"playable":94.06413888574136,"score":94.06413888574136},"GB2-04":{"attempts":1,"playable":88.47758801995356,"score":88.47758801995356},"GB2-05":{"attempts":1,"playable":93.72920600940776,"score":93.72920600940776},"GB2-06":{"attempts":1,"playable":89.63890172201879,"score":89.63890172201879},"GB2-07":{"attempts":1,"playable":94.79578183197358,"score":94.79578183197358},"GB2-08":{"attempts":1,"playable":89.54953506872145,"score":89.54953506872145}},"medium":{"GB2-01":{"attempts":1,"playable":40.10856644892073,"score":40.10856644892073},"GB2-02":{"attempts":1,"playable":69.18155899345648,"score":69.18155899345648},"GB2-03":{"attempts":1,"playable":74.52834832026495,"score":74.52834832026495},"GB2-04":{"attempts":1,"playable":73.65183009590339,"score":73.65183009590339},"GB2-05":{"attempts":1,"playable":91.5922255745075,"score":91.5922255745075},"GB2-06":{"attempts":1,"playable":81.49371638721978,"score":81.49371638721978},"GB2-07":{"attempts":1,"playable":94.25843028560105,"score":94.25843028560105},"GB2-08":{"attempts":1,"playable":85.4019535972354,"score":85.4019535972354}},"none":{"GB2-01":{"attempts":1,"playable":61.98434662360719,"score":61.98434662360719},"GB2-02":{"attempts":1,"playable":52.24650910928704,"score":52.24650910928704},"GB2-03":{"attempts":1,"playable":82.43411441003106,"score":82.43411441003106},"GB2-04":{"attempts":1,"playable":43.95025323129512,"score":43.95025323129512},"GB2-05":{"attempts":1,"playable":78.24613058159532,"score":78.24613058159532},"GB2-06":{"attempts":1,"playable":73.98352173828323,"score":73.98352173828323},"GB2-07":{"attempts":1,"playable":57.70202990001565,"score":57.70202990001565},"GB2-08":{"attempts":1,"playable":84.66514789672517,"score":84.66514789672517}}},"id":"gpt-6-sol","is_recent_addition":false,"last_measured_at":"2026-10-22T10:42:49Z","match_totals_all":{"draws":1528,"losses":2264,"wins":7802},"match_totals_tracks":{"highest":{"draws":235,"losses":646,"wins":2981},"medium":{"draws":613,"losses":639,"wins":2620},"none":{"draws":680,"losses":979,"wins":2201}},"model_slug":"gpt-6-sol","overall":{"max":94.79578183197358,"mean":74.55110552839075,"min":10.386376300158082},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":10.386376300158082,"GB2-02":83.15632164945426,"GB2-03":94.06413888574136,"GB2-04":88.47758801995356,"GB2-05":93.72920600940776,"GB2-06":89.63890172201879,"GB2-07":94.79578183197358,"GB2-08":89.54953506872145},"per_game_all":{"GB2-01":37.493096457562,"GB2-02":68.19479658406593,"GB2-03":83.67553387201245,"GB2-04":68.69322378238401,"GB2-05":87.8558540551702,"GB2-06":81.70537994917393,"GB2-07":82.2520806725301,"GB2-08":86.53887885422733},"per_game_match_totals_all":{"GB2-01":{"draws":204,"losses":832,"wins":428},"GB2-02":{"draws":612,"losses":143,"wins":607},"GB2-03":{"draws":75,"losses":213,"wins":1120},"GB2-04":{"draws":499,"losses":206,"wins":707},"GB2-05":{"draws":0,"losses":186,"wins":1326},"GB2-06":{"draws":118,"losses":216,"wins":1102},"GB2-07":{"draws":0,"losses":265,"wins":1221},"GB2-08":{"draws":20,"losses":203,"wins":1291}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":426,"wins":33},"GB2-02":{"draws":123,"losses":17,"wins":314},"GB2-03":{"draws":4,"losses":26,"wins":440},"GB2-04":{"draws":52,"losses":30,"wins":388},"GB2-05":{"draws":0,"losses":32,"wins":472},"GB2-06":{"draws":27,"losses":38,"wins":415},"GB2-07":{"draws":0,"losses":23,"wins":469},"GB2-08":{"draws":0,"losses":54,"wins":450}},"medium":{"GB2-01":{"draws":159,"losses":220,"wins":109},"GB2-02":{"draws":208,"losses":43,"wins":203},"GB2-03":{"draws":38,"losses":113,"wins":319},"GB2-04":{"draws":152,"losses":53,"wins":265},"GB2-05":{"draws":0,"losses":41,"wins":463},"GB2-06":{"draws":47,"losses":69,"wins":362},"GB2-07":{"draws":0,"losses":26,"wins":476},"GB2-08":{"draws":9,"losses":74,"wins":423}},"none":{"GB2-01":{"draws":16,"losses":186,"wins":286},"GB2-02":{"draws":281,"losses":83,"wins":90},"GB2-03":{"draws":33,"losses":74,"wins":361},"GB2-04":{"draws":295,"losses":123,"wins":54},"GB2-05":{"draws":0,"losses":113,"wins":391},"GB2-06":{"draws":44,"losses":109,"wins":325},"GB2-07":{"draws":0,"losses":216,"wins":276},"GB2-08":{"draws":11,"losses":75,"wins":418}}},"per_game_raw_elo_all":{"GB2-01":1318.965416555615,"GB2-02":1643.034959673794,"GB2-03":1892.530466372953,"GB2-04":1668.9790006176365,"GB2-05":2218.9434490391864,"GB2-06":1994.7163910444294,"GB2-07":2122.7629274232086,"GB2-08":2038.4663546924205},"per_game_raw_elo_tracks":{"highest":{"GB2-01":992.6160983246139,"GB2-02":1801.3763358071742,"GB2-03":2171.826500101289,"GB2-04":1892.380079990882,"GB2-05":2445.9407123504743,"GB2-06":2168.2206858720556,"GB2-07":2427.002286218496,"GB2-08":2123.098992925061},"medium":{"GB2-01":1376.217020993092,"GB2-02":1635.612179076792,"GB2-03":1688.9543851687242,"GB2-04":1683.3732321960294,"GB2-05":2333.478897196481,"GB2-06":1980.9162142558093,"GB2-07":2394.4773808047084,"GB2-08":2005.558592052005},"none":{"GB2-01":1588.063130349139,"GB2-02":1492.1163641374155,"GB2-03":1816.810513848845,"GB2-04":1431.1836896659981,"GB2-05":1877.4107375706035,"GB2-06":1835.0122730054227,"GB2-07":1546.809115246421,"GB2-08":1986.7414791001954}},"per_game_tracks":{"highest":{"GB2-01":10.386376300158082,"GB2-02":83.15632164945426,"GB2-03":94.06413888574136,"GB2-04":88.47758801995356,"GB2-05":93.72920600940776,"GB2-06":89.63890172201879,"GB2-07":94.79578183197358,"GB2-08":89.54953506872145},"medium":{"GB2-01":40.10856644892073,"GB2-02":69.18155899345648,"GB2-03":74.52834832026495,"GB2-04":73.65183009590339,"GB2-05":91.5922255745075,"GB2-06":81.49371638721978,"GB2-07":94.25843028560105,"GB2-08":85.4019535972354},"none":{"GB2-01":61.98434662360719,"GB2-02":52.24650910928704,"GB2-03":82.43411441003106,"GB2-04":43.95025323129512,"GB2-05":78.24613058159532,"GB2-06":73.98352173828323,"GB2-07":57.70202990001565,"GB2-08":84.66514789672517}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-20T11:13:33Z","reasoning":{"highest":80.4747311859286,"medium":76.27707871288867,"none":66.90150668635498},"reasoning_agg":{"highest":{"max":94.79578183197358,"mean":80.4747311859286,"min":10.386376300158082},"medium":{"max":94.25843028560105,"mean":76.27707871288867,"min":40.10856644892073},"none":{"max":84.66514789672517,"mean":66.90150668635498,"min":43.95025323129512}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.573224499573627}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:a538ccbf5604603f","codegen_cost_by_reasoning":{"highest":{"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":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":true,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.8325049999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"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}},"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":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.8325049999999998},"historical-provider-setting-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":0.15394249999999998,"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":true,"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":6.372553749999999}},"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":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.227983750000002},"codegen_output_tokens":{"attempt_count":25,"output_max":35149,"output_mean":11102.833333333334,"output_min":1851,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":35149,"output_mean":24638.75,"output_min":19522,"run_count":8},"medium":{"attempt_count":8,"output_max":6769,"output_mean":6021.5,"output_min":5176,"run_count":8},"none":{"attempt_count":8,"output_max":3391,"output_mean":2648.25,"output_min":1851,"run_count":8}},"display_name":"GPT-5.6 Sol","economics":{"all":68.43396635547548,"highest":81.16575944615268,"medium":67.03140762061258,"none":57.104731999661155},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":74.86479230868642,"score":74.86479230868642},"GB2-02":{"attempts":3,"playable":62.649804256001865,"score":62.649804256001865},"GB2-03":{"attempts":3,"playable":65.74258203909787,"score":65.74258203909787},"GB2-04":{"attempts":3,"playable":68.09567038088936,"score":68.09567038088936},"GB2-05":{"attempts":3,"playable":68.84858794033669,"score":68.84858794033669},"GB2-06":{"attempts":3,"playable":62.59435299167095,"score":62.59435299167095},"GB2-07":{"attempts":3,"playable":69.1195464638449,"score":69.1195464638449},"GB2-08":{"attempts":3,"playable":75.55639446327574,"score":75.55639446327574}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":75.66730112990825,"score":75.66730112990825},"GB2-02":{"attempts":1,"playable":75.16968223767152,"score":75.16968223767152},"GB2-03":{"attempts":1,"playable":81.3163218314743,"score":81.3163218314743},"GB2-04":{"attempts":1,"playable":84.38643106680976,"score":84.38643106680976},"GB2-05":{"attempts":1,"playable":75.54269509925251,"score":75.54269509925251},"GB2-06":{"attempts":1,"playable":85.53276108471499,"score":85.53276108471499},"GB2-07":{"attempts":1,"playable":89.06942258948536,"score":89.06942258948536},"GB2-08":{"attempts":1,"playable":82.64146052990473,"score":82.64146052990473}},"medium":{"GB2-01":{"attempts":1,"playable":68.86043931016313,"score":68.86043931016313},"GB2-02":{"attempts":1,"playable":66.83756148527324,"score":66.83756148527324},"GB2-03":{"attempts":1,"playable":62.4803819854241,"score":62.4803819854241},"GB2-04":{"attempts":1,"playable":78.44454605688966,"score":78.44454605688966},"GB2-05":{"attempts":1,"playable":77.07833911936564,"score":77.07833911936564},"GB2-06":{"attempts":1,"playable":41.01070767905789,"score":41.01070767905789},"GB2-07":{"attempts":1,"playable":71.44964700577215,"score":71.44964700577215},"GB2-08":{"attempts":1,"playable":70.08963832295487,"score":70.08963832295487}},"none":{"GB2-01":{"attempts":1,"playable":80.06663648598786,"score":80.06663648598786},"GB2-02":{"attempts":1,"playable":45.94216904506083,"score":45.94216904506083},"GB2-03":{"attempts":1,"playable":53.43104230039521,"score":53.43104230039521},"GB2-04":{"attempts":1,"playable":41.456034018968666,"score":41.456034018968666},"GB2-05":{"attempts":1,"playable":53.92472960239192,"score":53.92472960239192},"GB2-06":{"attempts":1,"playable":61.23959021124,"score":61.23959021124},"GB2-07":{"attempts":1,"playable":46.839569796277175,"score":46.839569796277175},"GB2-08":{"attempts":1,"playable":73.93808453696764,"score":73.93808453696764}}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-10-22T10:59:24Z","match_totals_all":{"draws":1629,"losses":3008,"wins":6965},"match_totals_tracks":{"highest":{"draws":287,"losses":620,"wins":2959},"medium":{"draws":542,"losses":1065,"wins":2263},"none":{"draws":800,"losses":1323,"wins":1743}},"model_slug":"gpt-5-6-sol","overall":{"max":89.06942258948536,"mean":68.43396635547548,"min":41.01070767905789},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":75.66730112990825,"GB2-02":75.16968223767152,"GB2-03":81.3163218314743,"GB2-04":84.38643106680976,"GB2-05":75.54269509925251,"GB2-06":85.53276108471499,"GB2-07":89.06942258948536,"GB2-08":82.64146052990473},"per_game_all":{"GB2-01":74.86479230868642,"GB2-02":62.649804256001865,"GB2-03":65.74258203909787,"GB2-04":68.09567038088936,"GB2-05":68.84858794033669,"GB2-06":62.59435299167095,"GB2-07":69.1195464638449,"GB2-08":75.55639446327574},"per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":327,"wins":1019},"GB2-02":{"draws":723,"losses":165,"wins":480},"GB2-03":{"draws":189,"losses":429,"wins":788},"GB2-04":{"draws":501,"losses":214,"wins":699},"GB2-05":{"draws":0,"losses":489,"wins":1027},"GB2-06":{"draws":26,"losses":556,"wins":852},"GB2-07":{"draws":0,"losses":471,"wins":1011},"GB2-08":{"draws":72,"losses":357,"wins":1089}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":119,"wins":356},"GB2-02":{"draws":174,"losses":31,"wins":251},"GB2-03":{"draws":5,"losses":95,"wins":370},"GB2-04":{"draws":78,"losses":37,"wins":355},"GB2-05":{"draws":0,"losses":129,"wins":375},"GB2-06":{"draws":17,"losses":64,"wins":397},"GB2-07":{"draws":0,"losses":53,"wins":441},"GB2-08":{"draws":0,"losses":92,"wins":414}},"medium":{"GB2-01":{"draws":104,"losses":106,"wins":278},"GB2-02":{"draws":206,"losses":52,"wins":198},"GB2-03":{"draws":48,"losses":167,"wins":253},"GB2-04":{"draws":120,"losses":46,"wins":306},"GB2-05":{"draws":0,"losses":121,"wins":385},"GB2-06":{"draws":6,"losses":297,"wins":175},"GB2-07":{"draws":0,"losses":145,"wins":351},"GB2-08":{"draws":58,"losses":131,"wins":317}},"none":{"GB2-01":{"draws":1,"losses":102,"wins":385},"GB2-02":{"draws":343,"losses":82,"wins":31},"GB2-03":{"draws":136,"losses":167,"wins":165},"GB2-04":{"draws":303,"losses":131,"wins":38},"GB2-05":{"draws":0,"losses":239,"wins":267},"GB2-06":{"draws":3,"losses":195,"wins":280},"GB2-07":{"draws":0,"losses":273,"wins":219},"GB2-08":{"draws":14,"losses":134,"wins":358}}},"per_game_raw_elo_all":{"GB2-01":1734.9727866128226,"GB2-02":1584.8559623516205,"GB2-03":1602.5145332199006,"GB2-04":1656.4633048293351,"GB2-05":1719.382225636515,"GB2-06":1654.9425854746708,"GB2-07":1765.6670370308377,"GB2-08":1790.9591760610792},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1741.9393154335069,"GB2-02":1697.5544250690025,"GB2-03":1795.7808038513028,"GB2-04":1819.8083677372101,"GB2-05":1818.3005724565273,"GB2-06":2067.2330797298837,"GB2-07":2146.179782603119,"GB2-08":1937.353480584635},"medium":{"GB2-01":1661.0195511107454,"GB2-02":1613.6094983396447,"GB2-03":1548.8775740701792,"GB2-04":1737.7864252854981,"GB2-05":1850.9708665568846,"GB2-06":1289.210257354544,"GB2-07":1741.4025727704786,"GB2-08":1682.747070648418},"none":{"GB2-01":1801.959493294216,"GB2-02":1443.4039636462148,"GB2-03":1462.8852217382196,"GB2-04":1411.7951214652967,"GB2-05":1488.875237896133,"GB2-06":1608.3844193395846,"GB2-07":1409.4187557189164,"GB2-08":1752.776976950185}},"per_game_tracks":{"highest":{"GB2-01":75.66730112990825,"GB2-02":75.16968223767152,"GB2-03":81.3163218314743,"GB2-04":84.38643106680976,"GB2-05":75.54269509925251,"GB2-06":85.53276108471499,"GB2-07":89.06942258948536,"GB2-08":82.64146052990473},"medium":{"GB2-01":68.86043931016313,"GB2-02":66.83756148527324,"GB2-03":62.4803819854241,"GB2-04":78.44454605688966,"GB2-05":77.07833911936564,"GB2-06":41.01070767905789,"GB2-07":71.44964700577215,"GB2-08":70.08963832295487},"none":{"GB2-01":80.06663648598786,"GB2-02":45.94216904506083,"GB2-03":53.43104230039521,"GB2-04":41.456034018968666,"GB2-05":53.92472960239192,"GB2-06":61.23959021124,"GB2-07":46.839569796277175,"GB2-08":73.93808453696764}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-20T07:18:35Z","reasoning":{"highest":81.16575944615268,"medium":67.03140762061258,"none":57.104731999661155},"reasoning_agg":{"highest":{"max":89.06942258948536,"mean":81.16575944615268,"min":75.16968223767152},"medium":{"max":78.44454605688966,"mean":67.03140762061258,"min":41.01070767905789},"none":{"max":80.06663648598786,"mean":57.104731999661155,"min":41.456034018968666}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.061027446491522}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:16bb97ce85baad85","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"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":true,"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":2.3088499999999996}},"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":true,"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":4.187100000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"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":2.3088499999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"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":true,"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":67.04533810724868,"highest":75.14517509809103,"medium":65.78362337122489,"none":60.2072158524301},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":77.98606018385944,"score":77.98606018385944},"GB2-02":{"attempts":3,"playable":60.66194575657284,"score":60.66194575657284},"GB2-03":{"attempts":3,"playable":47.45269672739576,"score":47.45269672739576},"GB2-04":{"attempts":3,"playable":59.10399210491306,"score":59.10399210491306},"GB2-05":{"attempts":3,"playable":64.66257361889579,"score":64.66257361889579},"GB2-06":{"attempts":3,"playable":81.62077666705653,"score":81.62077666705653},"GB2-07":{"attempts":3,"playable":67.25790102955362,"score":67.25790102955362},"GB2-08":{"attempts":3,"playable":77.61675876974236,"score":77.61675876974236}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":86.34554581920891,"score":86.34554581920891},"GB2-02":{"attempts":1,"playable":80.04156412405737,"score":80.04156412405737},"GB2-03":{"attempts":1,"playable":86.8404674823811,"score":86.8404674823811},"GB2-04":{"attempts":1,"playable":84.33285273025258,"score":84.33285273025258},"GB2-05":{"attempts":1,"playable":56.36299662967902,"score":56.36299662967902},"GB2-06":{"attempts":1,"playable":86.68146869508746,"score":86.68146869508746},"GB2-07":{"attempts":1,"playable":65.86974846343398,"score":65.86974846343398},"GB2-08":{"attempts":1,"playable":54.686756840627815,"score":54.686756840627815}},"medium":{"GB2-01":{"attempts":1,"playable":76.09912799769837,"score":76.09912799769837},"GB2-02":{"attempts":1,"playable":58.52115572424561,"score":58.52115572424561},"GB2-03":{"attempts":1,"playable":20.586202730012847,"score":20.586202730012847},"GB2-04":{"attempts":1,"playable":54.222777685015586,"score":54.222777685015586},"GB2-05":{"attempts":1,"playable":69.21392269433903,"score":69.21392269433903},"GB2-06":{"attempts":1,"playable":81.25722032151543,"score":81.25722032151543},"GB2-07":{"attempts":1,"playable":73.86164291358662,"score":73.86164291358662},"GB2-08":{"attempts":1,"playable":92.50693690338561,"score":92.50693690338561}},"none":{"GB2-01":{"attempts":1,"playable":71.51350673467105,"score":71.51350673467105},"GB2-02":{"attempts":1,"playable":43.42311742141556,"score":43.42311742141556},"GB2-03":{"attempts":1,"playable":34.93141996979333,"score":34.93141996979333},"GB2-04":{"attempts":1,"playable":38.756345899470986,"score":38.756345899470986},"GB2-05":{"attempts":1,"playable":68.4108015326693,"score":68.4108015326693},"GB2-06":{"attempts":1,"playable":76.92364098456672,"score":76.92364098456672},"GB2-07":{"attempts":1,"playable":62.04231171164029,"score":62.04231171164029},"GB2-08":{"attempts":1,"playable":85.65658256521364,"score":85.65658256521364}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:59:23Z","match_totals_all":{"draws":2068,"losses":2919,"wins":6621},"match_totals_tracks":{"highest":{"draws":479,"losses":785,"wins":2606},"medium":{"draws":716,"losses":992,"wins":2162},"none":{"draws":873,"losses":1142,"wins":1853}},"model_slug":"claude-fable-5","overall":{"max":92.50693690338561,"mean":67.04533810724867,"min":20.586202730012847},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":86.34554581920891,"GB2-02":80.04156412405737,"GB2-03":86.8404674823811,"GB2-04":84.33285273025258,"GB2-05":56.36299662967902,"GB2-06":86.68146869508746,"GB2-07":65.86974846343398,"GB2-08":54.686756840627815},"per_game_all":{"GB2-01":77.98606018385944,"GB2-02":60.66194575657284,"GB2-03":47.45269672739576,"GB2-04":59.10399210491306,"GB2-05":64.66257361889579,"GB2-06":81.62077666705653,"GB2-07":67.25790102955362,"GB2-08":77.61675876974236},"per_game_match_totals_all":{"GB2-01":{"draws":94,"losses":302,"wins":1072},"GB2-02":{"draws":742,"losses":185,"wins":443},"GB2-03":{"draws":322,"losses":607,"wins":477},"GB2-04":{"draws":635,"losses":276,"wins":503},"GB2-05":{"draws":0,"losses":552,"wins":962},"GB2-06":{"draws":61,"losses":246,"wins":1127},"GB2-07":{"draws":0,"losses":499,"wins":981},"GB2-08":{"draws":214,"losses":252,"wins":1056}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":73,"wins":414},"GB2-02":{"draws":127,"losses":32,"wins":297},"GB2-03":{"draws":49,"losses":43,"wins":378},"GB2-04":{"draws":70,"losses":43,"wins":359},"GB2-05":{"draws":0,"losses":228,"wins":278},"GB2-06":{"draws":19,"losses":55,"wins":404},"GB2-07":{"draws":0,"losses":175,"wins":319},"GB2-08":{"draws":213,"losses":136,"wins":157}},"medium":{"GB2-01":{"draws":35,"losses":109,"wins":348},"GB2-02":{"draws":279,"losses":56,"wins":123},"GB2-03":{"draws":96,"losses":334,"wins":38},"GB2-04":{"draws":278,"losses":83,"wins":111},"GB2-05":{"draws":0,"losses":160,"wins":344},"GB2-06":{"draws":28,"losses":81,"wins":369},"GB2-07":{"draws":0,"losses":131,"wins":361},"GB2-08":{"draws":0,"losses":38,"wins":468}},"none":{"GB2-01":{"draws":58,"losses":120,"wins":310},"GB2-02":{"draws":336,"losses":97,"wins":23},"GB2-03":{"draws":177,"losses":230,"wins":61},"GB2-04":{"draws":287,"losses":150,"wins":33},"GB2-05":{"draws":0,"losses":164,"wins":340},"GB2-06":{"draws":14,"losses":110,"wins":354},"GB2-07":{"draws":0,"losses":193,"wins":301},"GB2-08":{"draws":1,"losses":78,"wins":431}}},"per_game_raw_elo_all":{"GB2-01":1781.7728616887252,"GB2-02":1574.3039099935338,"GB2-03":1456.7266379220698,"GB2-04":1573.466077225695,"GB2-05":1637.4985406640965,"GB2-06":1986.8311076284747,"GB2-07":1681.002172203199,"GB2-08":1899.5387705165106},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1906.57635410566,"GB2-02":1756.910694104284,"GB2-03":1914.5997410846758,"GB2-04":1818.9662883516662,"GB2-05":1519.9236489252671,"GB2-06":2093.6915295503354,"GB2-07":1657.8185838528877,"GB2-08":1460.0547091270714},"medium":{"GB2-01":1747.501546561665,"GB2-02":1542.0279372159418,"GB2-03":1155.4835912221567,"GB2-04":1510.8803569066804,"GB2-05":1702.780372342749,"GB2-06":1976.09786965802,"GB2-07":1780.6463674207796,"GB2-08":2226.3825921477383},"none":{"GB2-01":1691.240684398851,"GB2-02":1423.9730986603756,"GB2-03":1300.0965814593767,"GB2-04":1390.5515864187387,"GB2-05":1689.7916007242743,"GB2-06":1890.7039236770693,"GB2-07":1604.5415653359303,"GB2-08":2012.1790102747225}},"per_game_tracks":{"highest":{"GB2-01":86.34554581920891,"GB2-02":80.04156412405737,"GB2-03":86.8404674823811,"GB2-04":84.33285273025258,"GB2-05":56.36299662967902,"GB2-06":86.68146869508746,"GB2-07":65.86974846343398,"GB2-08":54.686756840627815},"medium":{"GB2-01":76.09912799769837,"GB2-02":58.52115572424561,"GB2-03":20.586202730012847,"GB2-04":54.222777685015586,"GB2-05":69.21392269433903,"GB2-06":81.25722032151543,"GB2-07":73.86164291358662,"GB2-08":92.50693690338561},"none":{"GB2-01":71.51350673467105,"GB2-02":43.42311742141556,"GB2-03":34.93141996979333,"GB2-04":38.756345899470986,"GB2-05":68.4108015326693,"GB2-06":76.92364098456672,"GB2-07":62.04231171164029,"GB2-08":85.65658256521364}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-20T11:22:52Z","reasoning":{"highest":75.14517509809103,"medium":65.78362337122489,"none":60.2072158524301},"reasoning_agg":{"highest":{"max":86.8404674823811,"mean":75.14517509809103,"min":54.686756840627815},"medium":{"max":92.50693690338561,"mean":65.78362337122489,"min":20.586202730012847},"none":{"max":85.65658256521364,"mean":60.2072158524301,"min":34.93141996979333}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.937959245660927}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-wonder:e14b4932486f1ae8","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":0.680268,"mean":0.4875944,"median":0.46494,"min":0.362124,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":3.9007552},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.4270272,"mean":0.2502732,"median":0.206604,"min":0.16216,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":2.0021856},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.187324,"mean":0.12070595,"median":0.10780200000000001,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.9656475999999999}},"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":0.4270272,"mean":0.2502732,"median":0.206604,"min":0.16216,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":2.0021856},"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":0.187324,"mean":0.12070595,"median":0.10780200000000001,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.9656475999999999},"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":0.680268,"mean":0.4875944,"median":0.46494,"min":0.362124,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":3.9007551999999994}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.2861911833333333,"median":0.206604,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":30},"recorded_attempt_count":30,"run_count":24,"total":6.8685884},"codegen_latency_ms":{"attempt_count":30,"max_ms":235793,"mean_ms":83718.41666666667,"min_ms":17910,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":235793,"mean_ms":170391.375,"min_ms":123596,"run_count":8},"medium":{"attempt_count":11,"max_ms":84789,"mean_ms":58477.125,"min_ms":40383,"run_count":8},"none":{"attempt_count":10,"max_ms":29743,"mean_ms":22286.75,"min_ms":17910,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":29674,"output_mean":12261.208333333334,"output_min":3304,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":29674,"output_mean":22547.25,"output_min":16651,"run_count":8},"medium":{"attempt_count":11,"output_max":17493,"output_mean":10166.125,"output_min":6634,"run_count":8},"none":{"attempt_count":10,"output_max":5361,"output_mean":4070.25,"output_min":3304,"run_count":8}},"display_name":"Muse Wonder","economics":{"all":66.21997836104379,"highest":78.46386243688323,"medium":63.531940099669626,"none":56.66413254657851},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[943718],"finish_reason_observations":30,"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,"requested_max_output_token_observations":30,"requested_max_output_tokens":[943718],"total_output_tokens":294269,"total_reasoning_output_tokens":154600,"total_visible_output_tokens":139669,"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":"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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-wonder","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":69.27253471666168,"score":69.27253471666168},"GB2-02":{"attempts":3,"playable":54.84093826131314,"score":54.84093826131314},"GB2-03":{"attempts":3,"playable":45.54089387733517,"score":45.54089387733517},"GB2-04":{"attempts":3,"playable":58.319853928760246,"score":58.319853928760246},"GB2-05":{"attempts":3,"playable":87.77687254214872,"score":87.77687254214872},"GB2-06":{"attempts":3,"playable":76.89192792863786,"score":76.89192792863786},"GB2-07":{"attempts":3,"playable":71.57660747059181,"score":71.57660747059181},"GB2-08":{"attempts":3,"playable":65.54019816290172,"score":65.54019816290172}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.94634613262849,"score":84.94634613262849},"GB2-02":{"attempts":1,"playable":66.2770544040747,"score":66.2770544040747},"GB2-03":{"attempts":1,"playable":83.07415327545652,"score":83.07415327545652},"GB2-04":{"attempts":1,"playable":81.58624247287743,"score":81.58624247287743},"GB2-05":{"attempts":1,"playable":92.90721860764161,"score":92.90721860764161},"GB2-06":{"attempts":1,"playable":84.4991378522912,"score":84.4991378522912},"GB2-07":{"attempts":1,"playable":73.18655166513491,"score":73.18655166513491},"GB2-08":{"attempts":1,"playable":61.234195084961065,"score":61.234195084961065}},"medium":{"GB2-01":{"attempts":1,"playable":53.96562258140409,"score":53.96562258140409},"GB2-02":{"attempts":1,"playable":55.747528227025946,"score":55.747528227025946},"GB2-03":{"attempts":1,"playable":36.60116167563097,"score":36.60116167563097},"GB2-04":{"attempts":1,"playable":39.2486551417713,"score":39.2486551417713},"GB2-05":{"attempts":1,"playable":85.58011769640265,"score":85.58011769640265},"GB2-06":{"attempts":1,"playable":77.2312575826341,"score":77.2312575826341},"GB2-07":{"attempts":1,"playable":87.57378756144327,"score":87.57378756144327},"GB2-08":{"attempts":1,"playable":72.30739033104466,"score":72.30739033104466}},"none":{"GB2-01":{"attempts":1,"playable":68.90563543595246,"score":68.90563543595246},"GB2-02":{"attempts":1,"playable":42.49823215283876,"score":42.49823215283876},"GB2-03":{"attempts":1,"playable":16.947366680918012,"score":16.947366680918012},"GB2-04":{"attempts":1,"playable":54.124664171632006,"score":54.124664171632006},"GB2-05":{"attempts":1,"playable":84.84328132240188,"score":84.84328132240188},"GB2-06":{"attempts":1,"playable":68.94538835098827,"score":68.94538835098827},"GB2-07":{"attempts":1,"playable":53.969483185197255,"score":53.969483185197255},"GB2-08":{"attempts":1,"playable":63.07900907269941,"score":63.07900907269941}}},"id":"meta/muse-wonder","is_recent_addition":false,"last_measured_at":"2026-10-22T10:42:48Z","match_totals_all":{"draws":2150,"losses":2958,"wins":6481},"match_totals_tracks":{"highest":{"draws":508,"losses":615,"wins":2741},"medium":{"draws":635,"losses":1123,"wins":2104},"none":{"draws":1007,"losses":1220,"wins":1636}},"model_slug":"meta-muse-wonder","overall":{"max":92.90721860764161,"mean":66.21997836104379,"min":16.947366680918012},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.94634613262849,"GB2-02":66.2770544040747,"GB2-03":83.07415327545652,"GB2-04":81.58624247287743,"GB2-05":92.90721860764161,"GB2-06":84.4991378522912,"GB2-07":73.18655166513491,"GB2-08":61.234195084961065},"per_game_all":{"GB2-01":69.27253471666168,"GB2-02":54.84093826131314,"GB2-03":45.54089387733517,"GB2-04":58.319853928760246,"GB2-05":87.77687254214872,"GB2-06":76.89192792863786,"GB2-07":71.57660747059181,"GB2-08":65.54019816290172},"per_game_match_totals_all":{"GB2-01":{"draws":169,"losses":385,"wins":910},"GB2-02":{"draws":894,"losses":190,"wins":284},"GB2-03":{"draws":259,"losses":668,"wins":477},"GB2-04":{"draws":553,"losses":325,"wins":532},"GB2-05":{"draws":0,"losses":188,"wins":1328},"GB2-06":{"draws":96,"losses":300,"wins":1035},"GB2-07":{"draws":0,"losses":437,"wins":1045},"GB2-08":{"draws":179,"losses":465,"wins":870}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":77,"wins":406},"GB2-02":{"draws":257,"losses":30,"wins":169},"GB2-03":{"draws":79,"losses":48,"wins":341},"GB2-04":{"draws":59,"losses":61,"wins":350},"GB2-05":{"draws":0,"losses":34,"wins":472},"GB2-06":{"draws":29,"losses":63,"wins":386},"GB2-07":{"draws":0,"losses":135,"wins":357},"GB2-08":{"draws":79,"losses":167,"wins":260}},"medium":{"GB2-01":{"draws":4,"losses":230,"wins":254},"GB2-02":{"draws":284,"losses":68,"wins":106},"GB2-03":{"draws":93,"losses":266,"wins":109},"GB2-04":{"draws":200,"losses":190,"wins":80},"GB2-05":{"draws":0,"losses":75,"wins":429},"GB2-06":{"draws":29,"losses":98,"wins":349},"GB2-07":{"draws":0,"losses":61,"wins":433},"GB2-08":{"draws":25,"losses":135,"wins":344}},"none":{"GB2-01":{"draws":160,"losses":78,"wins":250},"GB2-02":{"draws":353,"losses":92,"wins":9},"GB2-03":{"draws":87,"losses":354,"wins":27},"GB2-04":{"draws":294,"losses":74,"wins":102},"GB2-05":{"draws":0,"losses":79,"wins":427},"GB2-06":{"draws":38,"losses":139,"wins":300},"GB2-07":{"draws":0,"losses":241,"wins":255},"GB2-08":{"draws":75,"losses":163,"wins":266}}},"per_game_raw_elo_all":{"GB2-01":1683.6714907750193,"GB2-02":1514.9943737639103,"GB2-03":1418.073684430762,"GB2-04":1561.0464091527945,"GB2-05":2182.5969761472006,"GB2-06":1894.4916863291567,"GB2-07":1786.9039922255972,"GB2-08":1612.838252925316},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1880.548496460122,"GB2-02":1608.4932920666283,"GB2-03":1829.4376291426413,"GB2-04":1778.5807028362374,"GB2-05":2400.4044338397343,"GB2-06":2044.2756900867766,"GB2-07":1769.4239666016397,"GB2-08":1544.9768505856262},"medium":{"GB2-01":1508.943166182393,"GB2-02":1519.6800202723643,"GB2-03":1315.0734037160878,"GB2-04":1394.4516975231877,"GB2-05":2086.206360867255,"GB2-06":1896.6186326930801,"GB2-07":2092.5139754567263,"GB2-08":1722.2972660380328},"none":{"GB2-01":1661.522809682543,"GB2-02":1416.8098089527384,"GB2-03":1109.710020433557,"GB2-04":1510.1068270989585,"GB2-05":2061.1801337346124,"GB2-06":1742.5807362076132,"GB2-07":1498.7740346184255,"GB2-08":1571.2406421522892}},"per_game_tracks":{"highest":{"GB2-01":84.94634613262849,"GB2-02":66.2770544040747,"GB2-03":83.07415327545652,"GB2-04":81.58624247287743,"GB2-05":92.90721860764161,"GB2-06":84.4991378522912,"GB2-07":73.18655166513491,"GB2-08":61.234195084961065},"medium":{"GB2-01":53.96562258140409,"GB2-02":55.747528227025946,"GB2-03":36.60116167563097,"GB2-04":39.2486551417713,"GB2-05":85.58011769640265,"GB2-06":77.2312575826341,"GB2-07":87.57378756144327,"GB2-08":72.30739033104466},"none":{"GB2-01":68.90563543595246,"GB2-02":42.49823215283876,"GB2-03":16.947366680918012,"GB2-04":54.124664171632006,"GB2-05":84.84328132240188,"GB2-06":68.94538835098827,"GB2-07":53.969483185197255,"GB2-08":63.07900907269941}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-1,"rank_movement_baseline_at":"2026-10-14T17:59:31Z","reasoning":{"highest":78.46386243688323,"medium":63.531940099669626,"none":56.66413254657851},"reasoning_agg":{"highest":{"max":92.90721860764161,"mean":78.46386243688323,"min":61.234195084961065},"medium":{"max":87.57378756144327,"mean":63.531940099669626,"min":36.60116167563097},"none":{"max":84.84328132240188,"mean":56.66413254657851,"min":16.947366680918012}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":21.799729890304725}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:2116d045c3990380","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.549677025,"median":0.477676,"min":0.280382,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":4.3974162},"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":0.43181687999999996},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.549677025,"median":0.477676,"min":0.280382,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":4.397416199999999}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.2535328433333333,"median":0.1720692,"min":0.0217974,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":28,"run_count":24,"total":6.084788240000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":4051923,"mean_ms":1012660.4583333334,"min_ms":28293,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":4051923,"mean_ms":2278758.375,"min_ms":1011583,"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":28,"output_max":206676,"output_mean":54914.25,"output_min":2671,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":206676,"output_mean":121740.75,"output_min":61533,"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":69.12268132869728,"highest":83.86965224437066,"medium":71.8633255851169,"none":51.169924786353526},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[131072],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":29,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":84,"requested_max_output_token_observations":10,"requested_max_output_tokens":[131072],"total_output_tokens":1317942,"total_reasoning_output_tokens":1189870,"total_visible_output_tokens":128072,"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","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":59.88863038985748,"score":39.92575359323832},"GB2-02":{"attempts":3,"playable":57.330209142855416,"score":57.330209142855416},"GB2-03":{"attempts":3,"playable":69.00900233980416,"score":69.00900233980416},"GB2-04":{"attempts":3,"playable":69.30973390024417,"score":69.30973390024417},"GB2-05":{"attempts":3,"playable":72.57451667668123,"score":72.57451667668123},"GB2-06":{"attempts":3,"playable":77.80991105074656,"score":77.80991105074656},"GB2-07":{"attempts":3,"playable":75.66961974423884,"score":75.66961974423884},"GB2-08":{"attempts":3,"playable":62.1557764463106,"score":62.1557764463106}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":73.50887232542763,"score":73.50887232542763},"GB2-03":{"attempts":1,"playable":84.46337411286521,"score":84.46337411286521},"GB2-04":{"attempts":1,"playable":76.9440738975773,"score":76.9440738975773},"GB2-05":{"attempts":1,"playable":89.89302578782349,"score":89.89302578782349},"GB2-06":{"attempts":1,"playable":90.98043713863217,"score":90.98043713863217},"GB2-07":{"attempts":1,"playable":78.56877120556457,"score":78.56877120556457},"GB2-08":{"attempts":1,"playable":92.72901124270419,"score":92.72901124270419}},"medium":{"GB2-01":{"attempts":1,"playable":51.48692160733251,"score":51.48692160733251},"GB2-02":{"attempts":1,"playable":54.72436857284809,"score":54.72436857284809},"GB2-03":{"attempts":1,"playable":79.27778130205076,"score":79.27778130205076},"GB2-04":{"attempts":1,"playable":82.66563808830324,"score":82.66563808830324},"GB2-05":{"attempts":1,"playable":68.02976037475503,"score":68.02976037475503},"GB2-06":{"attempts":1,"playable":92.66879148686418,"score":92.66879148686418},"GB2-07":{"attempts":1,"playable":76.70261724002464,"score":76.70261724002464},"GB2-08":{"attempts":1,"playable":69.35072600875675,"score":69.35072600875675}},"none":{"GB2-01":{"attempts":1,"playable":68.29033917238245,"score":68.29033917238245},"GB2-02":{"attempts":1,"playable":43.757386530290546,"score":43.757386530290546},"GB2-03":{"attempts":1,"playable":43.285851604496514,"score":43.285851604496514},"GB2-04":{"attempts":1,"playable":48.31948971485196,"score":48.31948971485196},"GB2-05":{"attempts":1,"playable":59.80076386746518,"score":59.80076386746518},"GB2-06":{"attempts":1,"playable":49.78050452674334,"score":49.78050452674334},"GB2-07":{"attempts":1,"playable":71.73747078712732,"score":71.73747078712732},"GB2-08":{"attempts":1,"playable":24.387592087470868,"score":24.387592087470868}}},"id":"z-ai/glm-5.3","is_recent_addition":false,"last_measured_at":"2026-10-22T10:00:37Z","match_totals_all":{"draws":2073,"losses":2606,"wins":6422},"match_totals_tracks":{"highest":{"draws":355,"losses":381,"wins":2634},"medium":{"draws":619,"losses":821,"wins":2425},"none":{"draws":1099,"losses":1404,"wins":1363}},"model_slug":"z-ai-glm-5-3","overall":{"max":92.72901124270419,"mean":65.47306536176491,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-02":73.50887232542763,"GB2-03":84.46337411286521,"GB2-04":76.9440738975773,"GB2-05":89.89302578782349,"GB2-06":90.98043713863217,"GB2-07":78.56877120556457,"GB2-08":92.72901124270419},"per_game_all":{"GB2-02":57.330209142855416,"GB2-03":69.00900233980416,"GB2-04":69.30973390024417,"GB2-05":72.57451667668123,"GB2-06":77.80991105074656,"GB2-07":75.66961974423884,"GB2-08":62.1557764463106},"per_game_match_totals_all":{"GB2-01":{"draws":163,"losses":325,"wins":490},"GB2-02":{"draws":884,"losses":158,"wins":322},"GB2-03":{"draws":146,"losses":397,"wins":863},"GB2-04":{"draws":526,"losses":183,"wins":704},"GB2-05":{"draws":0,"losses":426,"wins":1086},"GB2-06":{"draws":55,"losses":307,"wins":1070},"GB2-07":{"draws":0,"losses":366,"wins":1112},"GB2-08":{"draws":299,"losses":444,"wins":775}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":204,"losses":23,"wins":227},"GB2-03":{"draws":4,"losses":79,"wins":385},"GB2-04":{"draws":126,"losses":49,"wins":297},"GB2-05":{"draws":0,"losses":52,"wins":452},"GB2-06":{"draws":21,"losses":34,"wins":421},"GB2-07":{"draws":0,"losses":107,"wins":385},"GB2-08":{"draws":0,"losses":37,"wins":467}},"medium":{"GB2-01":{"draws":87,"losses":202,"wins":201},"GB2-02":{"draws":315,"losses":56,"wins":85},"GB2-03":{"draws":22,"losses":96,"wins":350},"GB2-04":{"draws":89,"losses":40,"wins":342},"GB2-05":{"draws":0,"losses":166,"wins":338},"GB2-06":{"draws":22,"losses":23,"wins":433},"GB2-07":{"draws":0,"losses":115,"wins":377},"GB2-08":{"draws":84,"losses":123,"wins":299}},"none":{"GB2-01":{"draws":76,"losses":123,"wins":289},"GB2-02":{"draws":365,"losses":79,"wins":10},"GB2-03":{"draws":120,"losses":222,"wins":128},"GB2-04":{"draws":311,"losses":94,"wins":65},"GB2-05":{"draws":0,"losses":208,"wins":296},"GB2-06":{"draws":12,"losses":250,"wins":216},"GB2-07":{"draws":0,"losses":144,"wins":350},"GB2-08":{"draws":215,"losses":284,"wins":9}}},"per_game_raw_elo_all":{"GB2-02":1539.1680923737588,"GB2-03":1664.1796164846082,"GB2-04":1659.5478801469126,"GB2-05":1834.5721994724656,"GB2-06":1963.6516719763295,"GB2-07":1813.9813970771531,"GB2-08":1679.6209951140524},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1679.3852634433351,"GB2-03":1858.5059227213615,"GB2-04":1719.8778120437219,"GB2-05":2255.0236655503068,"GB2-06":2206.4636422667154,"GB2-07":1865.6421400308577,"GB2-08":2235.201786095949},"medium":{"GB2-01":1485.1628590898456,"GB2-02":1511.5618618576314,"GB2-03":1760.3409388063694,"GB2-04":1793.8435379926495,"GB2-05":1683.7316755170189,"GB2-06":2260.806132309179,"GB2-07":1830.3348024053041,"GB2-08":1670.046282256299},"none":{"GB2-01":1654.7029287275045,"GB2-02":1426.55715182031,"GB2-03":1373.691987926094,"GB2-04":1464.9222904043665,"GB2-05":1564.9612573500715,"GB2-06":1423.685241353094,"GB2-07":1745.9672487952978,"GB2-08":1133.6149169899088}},"per_game_tracks":{"highest":{"GB2-02":73.50887232542763,"GB2-03":84.46337411286521,"GB2-04":76.9440738975773,"GB2-05":89.89302578782349,"GB2-06":90.98043713863217,"GB2-07":78.56877120556457,"GB2-08":92.72901124270419},"medium":{"GB2-01":51.48692160733251,"GB2-02":54.72436857284809,"GB2-03":79.27778130205076,"GB2-04":82.66563808830324,"GB2-05":68.02976037475503,"GB2-06":92.66879148686418,"GB2-07":76.70261724002464,"GB2-08":69.35072600875675},"none":{"GB2-01":68.29033917238245,"GB2-02":43.757386530290546,"GB2-03":43.285851604496514,"GB2-04":48.31948971485196,"GB2-05":59.80076386746518,"GB2-06":49.78050452674334,"GB2-07":71.73747078712732,"GB2-08":24.387592087470868}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-1,"rank_movement_baseline_at":"2026-10-20T11:34:49Z","reasoning":{"highest":73.38594571382433,"medium":71.8633255851169,"none":51.169924786353526},"reasoning_agg":{"highest":{"max":92.72901124270419,"mean":73.38594571382433,"min":0.0},"medium":{"max":92.66879148686418,"mean":71.8633255851169,"min":51.48692160733251},"none":{"max":71.73747078712732,"mean":51.169924786353526,"min":24.387592087470868}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":22.2160209274708}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:687087bd572badd8","codegen_cost_by_reasoning":{"highest":{"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":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.2355599999999995},"medium":{"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":0.576454,"mean":0.39871924999999997,"median":0.380795,"min":0.216934,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":3.189754},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.6637360000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.576454,"mean":0.39871924999999997,"median":0.380795,"min":0.216934,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":3.1897539999999998},"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":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.2355599999999995}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":1.2177,"mean":0.4203770833333333,"median":0.380795,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":10.089050000000002},"codegen_latency_ms":{"attempt_count":29,"max_ms":2516111,"mean_ms":895095.7083333334,"min_ms":107275,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2516111,"mean_ms":1632486.25,"min_ms":1212881,"run_count":8},"medium":{"attempt_count":9,"max_ms":1551665,"mean_ms":884117.375,"min_ms":472109,"run_count":8},"none":{"attempt_count":10,"max_ms":283828,"mean_ms":168683.5,"min_ms":107275,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":195136,"output_mean":67634.29166666667,"output_min":8421,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":195136,"output_mean":126135.375,"output_min":92484,"run_count":8},"medium":{"attempt_count":9,"output_max":95241,"output_mean":63372.625,"output_min":32426,"run_count":8},"none":{"attempt_count":10,"output_max":23276,"output_mean":13394.875,"output_min":8421,"run_count":8}},"display_name":"Grok 4.7","economics":{"all":72.75396291091887,"highest":83.76943156075198,"medium":83.7081347500733,"none":55.29105213352323},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[450000],"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":[450000],"total_output_tokens":1623223,"total_reasoning_output_tokens":1401661,"total_visible_output_tokens":221562,"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":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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":55.78916663270181,"score":55.78916663270181},"GB2-02":{"attempts":3,"playable":74.10840611705535,"score":74.10840611705535},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":80.38114464943055,"score":53.58742976628704},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":67.45642928622911,"score":44.970952857486076},"GB2-05":{"attempts":3,"playable":76.57037607180634,"score":76.57037607180634},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":86.19786878766865,"score":57.46524585844577},"GB2-07":{"attempts":3,"playable":70.28223470491933,"score":70.28223470491933},"GB2-08":{"attempts":3,"playable":87.01963102811152,"score":87.01963102811152}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":59.47728112550161,"score":59.47728112550161},"GB2-02":{"attempts":1,"playable":88.63125660685279,"score":88.63125660685279},"GB2-03":{"attempts":1,"playable":88.27375290884362,"score":88.27375290884362},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":93.22545031325062,"score":93.22545031325062},"GB2-06":{"attempts":1,"playable":89.94294883555837,"score":89.94294883555837},"GB2-07":{"attempts":1,"playable":78.62199403121048,"score":78.62199403121048},"GB2-08":{"attempts":1,"playable":88.21333710404646,"score":88.21333710404646}},"medium":{"GB2-01":{"attempts":1,"playable":79.83949489896985,"score":79.83949489896985},"GB2-02":{"attempts":1,"playable":80.98454772532816,"score":80.98454772532816},"GB2-03":{"attempts":1,"playable":72.48853639001747,"score":72.48853639001747},"GB2-04":{"attempts":1,"playable":92.36946199217707,"score":92.36946199217707},"GB2-05":{"attempts":1,"playable":93.46644883288367,"score":93.46644883288367},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":76.18265175635969,"score":76.18265175635969},"GB2-08":{"attempts":1,"playable":90.62580165477713,"score":90.62580165477713}},"none":{"GB2-01":{"attempts":1,"playable":28.050723873633952,"score":28.050723873633952},"GB2-02":{"attempts":1,"playable":52.709414018985115,"score":52.709414018985115},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.54339658028114,"score":42.54339658028114},"GB2-05":{"attempts":1,"playable":43.0192290692847,"score":43.0192290692847},"GB2-06":{"attempts":1,"playable":82.45278873977892,"score":82.45278873977892},"GB2-07":{"attempts":1,"playable":56.0420583271878,"score":56.0420583271878},"GB2-08":{"attempts":1,"playable":82.21975432551098,"score":82.21975432551098}}},"id":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-10-22T10:58:58Z","match_totals_all":{"draws":991,"losses":2199,"wins":6976},"match_totals_tracks":{"highest":{"draws":146,"losses":490,"wins":2750},"medium":{"draws":204,"losses":474,"wins":2706},"none":{"draws":641,"losses":1235,"wins":1520}},"model_slug":"x-ai-grok-4-7","overall":{"max":93.46644883288367,"mean":64.97418037960165,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.47728112550161,"GB2-02":88.63125660685279,"GB2-03":88.27375290884362,"GB2-05":93.22545031325062,"GB2-06":89.94294883555837,"GB2-07":78.62199403121048,"GB2-08":88.21333710404646},"per_game_all":{"GB2-01":55.78916663270181,"GB2-02":74.10840611705535,"GB2-05":76.57037607180634,"GB2-07":70.28223470491933,"GB2-08":87.01963102811152},"per_game_match_totals_all":{"GB2-01":{"draws":194,"losses":572,"wins":698},"GB2-02":{"draws":466,"losses":129,"wins":767},"GB2-03":{"draws":99,"losses":152,"wins":687},"GB2-04":{"draws":168,"losses":229,"wins":545},"GB2-05":{"draws":0,"losses":356,"wins":1156},"GB2-06":{"draws":64,"losses":104,"wins":786},"GB2-07":{"draws":0,"losses":451,"wins":1031},"GB2-08":{"draws":0,"losses":206,"wins":1306}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":199,"wins":276},"GB2-02":{"draws":48,"losses":28,"wins":378},"GB2-03":{"draws":72,"losses":24,"wins":372},"GB2-05":{"draws":0,"losses":33,"wins":471},"GB2-06":{"draws":13,"losses":41,"wins":422},"GB2-07":{"draws":0,"losses":104,"wins":388},"GB2-08":{"draws":0,"losses":61,"wins":443}},"medium":{"GB2-01":{"draws":32,"losses":90,"wins":366},"GB2-02":{"draws":102,"losses":39,"wins":313},"GB2-03":{"draws":27,"losses":128,"wins":315},"GB2-04":{"draws":43,"losses":16,"wins":413},"GB2-05":{"draws":0,"losses":31,"wins":473},"GB2-07":{"draws":0,"losses":120,"wins":372},"GB2-08":{"draws":0,"losses":50,"wins":454}},"none":{"GB2-01":{"draws":149,"losses":283,"wins":56},"GB2-02":{"draws":316,"losses":62,"wins":76},"GB2-04":{"draws":125,"losses":213,"wins":132},"GB2-05":{"draws":0,"losses":292,"wins":212},"GB2-06":{"draws":51,"losses":63,"wins":364},"GB2-07":{"draws":0,"losses":227,"wins":271},"GB2-08":{"draws":0,"losses":95,"wins":409}}},"per_game_raw_elo_all":{"GB2-01":1537.8162099499132,"GB2-02":1721.913535854502,"GB2-05":2067.039198097892,"GB2-07":1737.6299951122426,"GB2-08":2056.065057031032},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1562.8310699035258,"GB2-02":1900.2877354109842,"GB2-03":1953.3011123269537,"GB2-05":2417.6411007885035,"GB2-06":2176.585042774117,"GB2-07":1866.68649992542,"GB2-08":2082.645589072369},"medium":{"GB2-01":1798.6545767329694,"GB2-02":1769.723584814976,"GB2-03":1661.9107599227264,"GB2-04":1985.03369878296,"GB2-05":2431.0153107345277,"GB2-07":1820.908234985609,"GB2-08":2158.1130407827745},"none":{"GB2-01":1251.9629832132443,"GB2-02":1495.7292873375468,"GB2-04":1420.2689108913064,"GB2-05":1352.4611827706449,"GB2-06":2000.6779361956283,"GB2-07":1525.2952504256984,"GB2-08":1927.4365412379543}},"per_game_tracks":{"highest":{"GB2-01":59.47728112550161,"GB2-02":88.63125660685279,"GB2-03":88.27375290884362,"GB2-05":93.22545031325062,"GB2-06":89.94294883555837,"GB2-07":78.62199403121048,"GB2-08":88.21333710404646},"medium":{"GB2-01":79.83949489896985,"GB2-02":80.98454772532816,"GB2-03":72.48853639001747,"GB2-04":92.36946199217707,"GB2-05":93.46644883288367,"GB2-07":76.18265175635969,"GB2-08":90.62580165477713},"none":{"GB2-01":28.050723873633952,"GB2-02":52.709414018985115,"GB2-04":42.54339658028114,"GB2-05":43.0192290692847,"GB2-06":82.45278873977892,"GB2-07":56.0420583271878,"GB2-08":82.21975432551098}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-1,"rank_movement_baseline_at":"2026-10-20T10:52:59Z","reasoning":{"highest":73.298252615658,"medium":73.24461790631413,"none":48.379670616832826},"reasoning_agg":{"highest":{"max":93.22545031325062,"mean":73.298252615658,"min":0.0},"medium":{"max":93.46644883288367,"mean":73.24461790631413,"min":0.0},"none":{"max":82.45278873977892,"mean":48.379670616832826,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.918581998825175}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash-1017:5f298d28ceb6d368","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":0.11170938600000001,"mean":0.07554854925,"median":0.075366243,"min":0.03476295,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.604388394},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.065551536,"mean":0.04201661175,"median":0.0380097,"min":0.02021175,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.336132894},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00749985,"mean":0.0058554465,"median":0.006206184,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.04684357200000001}},"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":0.065551536,"mean":0.04201661175,"median":0.0380097,"min":0.02021175,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.336132894},"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":0.00749985,"mean":0.0058554465,"median":0.006206184,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.04684357200000001},"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":0.11170938600000001,"mean":0.07554854925,"median":0.075366243,"min":0.03476295,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.604388394}},"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":0.11170938600000001,"mean":0.0411402025,"median":0.037120068,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":27,"run_count":24,"total":0.98736486},"codegen_latency_ms":{"attempt_count":27,"max_ms":473334,"mean_ms":151724.33333333334,"min_ms":8145,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":473334,"mean_ms":299503.0,"min_ms":228847,"run_count":8},"medium":{"attempt_count":8,"max_ms":206258,"mean_ms":144560.375,"min_ms":109598,"run_count":8},"none":{"attempt_count":9,"max_ms":15039,"mean_ms":11109.625,"min_ms":8145,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":101363,"output_mean":34770.375,"output_min":2168,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":101363,"output_mean":66009.25,"output_min":55824,"run_count":8},"medium":{"attempt_count":8,"output_max":52800,"output_mean":35105.0,"output_min":27852,"run_count":8},"none":{"attempt_count":9,"output_max":4467,"output_mean":3196.875,"output_min":2168,"run_count":8}},"display_name":"DeepSeek V4.1 Flash 1017","economics":{"all":63.318031439678975,"highest":72.0959056764509,"medium":66.32701080878051,"none":51.5311778338055},"first_seen_at":"2026-10-22T11:01:43Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[393216],"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,"requested_max_output_token_observations":27,"requested_max_output_tokens":[393216],"total_output_tokens":834489,"total_reasoning_output_tokens":719894,"total_visible_output_tokens":114595,"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":393216,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash-1017","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":74.91769010279482,"score":74.91769010279482},"GB2-02":{"attempts":3,"playable":56.32949084033137,"score":56.32949084033137},"GB2-03":{"attempts":3,"playable":46.91942139136387,"score":46.91942139136387},"GB2-04":{"attempts":3,"playable":59.89675407615541,"score":59.89675407615541},"GB2-05":{"attempts":3,"playable":63.79982990135134,"score":63.79982990135134},"GB2-06":{"attempts":3,"playable":67.75222778887887,"score":67.75222778887887},"GB2-07":{"attempts":3,"playable":59.59262553636961,"score":59.59262553636961},"GB2-08":{"attempts":3,"playable":77.3362118801865,"score":77.3362118801865}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.83791358547069,"score":68.83791358547069},"GB2-02":{"attempts":1,"playable":81.42424202418054,"score":81.42424202418054},"GB2-03":{"attempts":1,"playable":46.99810425510223,"score":46.99810425510223},"GB2-04":{"attempts":1,"playable":69.6314621432694,"score":69.6314621432694},"GB2-05":{"attempts":1,"playable":73.6158347183136,"score":73.6158347183136},"GB2-06":{"attempts":1,"playable":75.50742525274553,"score":75.50742525274553},"GB2-07":{"attempts":1,"playable":75.33688057821094,"score":75.33688057821094},"GB2-08":{"attempts":1,"playable":85.41538285431434,"score":85.41538285431434}},"medium":{"GB2-01":{"attempts":1,"playable":82.46274150897514,"score":82.46274150897514},"GB2-02":{"attempts":1,"playable":43.874595076065454,"score":43.874595076065454},"GB2-03":{"attempts":1,"playable":51.228963524558104,"score":51.228963524558104},"GB2-04":{"attempts":1,"playable":68.44271176359538,"score":68.44271176359538},"GB2-05":{"attempts":1,"playable":63.84636657954632,"score":63.84636657954632},"GB2-06":{"attempts":1,"playable":84.47759690974846,"score":84.47759690974846},"GB2-07":{"attempts":1,"playable":71.42716800267014,"score":71.42716800267014},"GB2-08":{"attempts":1,"playable":64.85594310508506,"score":64.85594310508506}},"none":{"GB2-01":{"attempts":1,"playable":73.45241521393862,"score":73.45241521393862},"GB2-02":{"attempts":1,"playable":43.689635420748104,"score":43.689635420748104},"GB2-03":{"attempts":1,"playable":42.53119639443129,"score":42.53119639443129},"GB2-04":{"attempts":1,"playable":41.61608832160143,"score":41.61608832160143},"GB2-05":{"attempts":1,"playable":53.93728840619413,"score":53.93728840619413},"GB2-06":{"attempts":1,"playable":43.27166120414261,"score":43.27166120414261},"GB2-07":{"attempts":1,"playable":32.01382802822775,"score":32.01382802822775},"GB2-08":{"attempts":1,"playable":81.73730968116008,"score":81.73730968116008}}},"id":"deepseek/deepseek-v4.1-flash-1017","is_recent_addition":true,"last_measured_at":"2026-10-22T11:01:43Z","match_totals_all":{"draws":1273,"losses":2021,"wins":3853},"match_totals_tracks":{"highest":{"draws":315,"losses":506,"wins":1463},"medium":{"draws":397,"losses":653,"wins":1260},"none":{"draws":561,"losses":862,"wins":1130}},"model_slug":"deepseek-deepseek-v4-1-flash-1017","overall":{"max":85.41538285431434,"mean":63.318031439678975,"min":32.01382802822775},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.83791358547069,"GB2-02":81.42424202418054,"GB2-03":46.99810425510223,"GB2-04":69.6314621432694,"GB2-05":73.6158347183136,"GB2-06":75.50742525274553,"GB2-07":75.33688057821094,"GB2-08":85.41538285431434},"per_game_all":{"GB2-01":74.91769010279482,"GB2-02":56.32949084033137,"GB2-03":46.91942139136387,"GB2-04":59.89675407615541,"GB2-05":63.79982990135134,"GB2-06":67.75222778887887,"GB2-07":59.59262553636961,"GB2-08":77.3362118801865},"per_game_match_totals_all":{"GB2-01":{"draws":110,"losses":218,"wins":674},"GB2-02":{"draws":520,"losses":127,"wins":213},"GB2-03":{"draws":205,"losses":416,"wins":315},"GB2-04":{"draws":413,"losses":131,"wins":256},"GB2-05":{"draws":0,"losses":367,"wins":701},"GB2-06":{"draws":25,"losses":278,"wins":534},"GB2-07":{"draws":0,"losses":262,"wins":404},"GB2-08":{"draws":0,"losses":222,"wins":756}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":53,"losses":59,"wins":140},"GB2-02":{"draws":60,"losses":22,"wins":188},"GB2-03":{"draws":51,"losses":122,"wins":85},"GB2-04":{"draws":141,"losses":14,"wins":107},"GB2-05":{"draws":0,"losses":137,"wins":367},"GB2-06":{"draws":10,"losses":68,"wins":202},"GB2-07":{"draws":0,"losses":56,"wins":176},"GB2-08":{"draws":0,"losses":28,"wins":198}},"medium":{"GB2-01":{"draws":0,"losses":50,"wins":212},"GB2-02":{"draws":237,"losses":62,"wins":17},"GB2-03":{"draws":48,"losses":203,"wins":187},"GB2-04":{"draws":100,"losses":38,"wins":124},"GB2-05":{"draws":0,"losses":102,"wins":182},"GB2-06":{"draws":12,"losses":45,"wins":225},"GB2-07":{"draws":0,"losses":58,"wins":168},"GB2-08":{"draws":0,"losses":95,"wins":145}},"none":{"GB2-01":{"draws":57,"losses":109,"wins":322},"GB2-02":{"draws":223,"losses":43,"wins":8},"GB2-03":{"draws":106,"losses":91,"wins":43},"GB2-04":{"draws":172,"losses":79,"wins":25},"GB2-05":{"draws":0,"losses":128,"wins":152},"GB2-06":{"draws":3,"losses":165,"wins":107},"GB2-07":{"draws":0,"losses":148,"wins":60},"GB2-08":{"draws":0,"losses":99,"wins":413}}},"per_game_raw_elo_all":{"GB2-01":1737.8803229116238,"GB2-02":1543.1248757246312,"GB2-03":1405.4236690224652,"GB2-04":1562.480004277262,"GB2-05":1630.0445482759685,"GB2-06":1743.6950449562219,"GB2-07":1589.5311912284687,"GB2-08":1839.9393396569637},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1660.7688661188704,"GB2-02":1775.8783409789933,"GB2-03":1405.9720145919996,"GB2-04":1642.8510286246158,"GB2-05":1780.2237007698882,"GB2-06":1863.6984861242388,"GB2-07":1805.9110523803354,"GB2-08":2005.9061968960887},"medium":{"GB2-01":1838.5500530445288,"GB2-02":1427.4626964925283,"GB2-03":1443.1663329376813,"GB2-04":1631.5440991856062,"GB2-05":1620.876155156687,"GB2-06":2043.804736990991,"GB2-07":1741.0473122599615,"GB2-08":1597.6772372139972},"none":{"GB2-01":1714.3220495714722,"GB2-02":1426.0335897023724,"GB2-03":1367.1326595377147,"GB2-04":1413.0448850215632,"GB2-05":1489.0337889013301,"GB2-06":1323.5819117534359,"GB2-07":1221.6352090451087,"GB2-08":1916.2345848608054}},"per_game_tracks":{"highest":{"GB2-01":68.83791358547069,"GB2-02":81.42424202418054,"GB2-03":46.99810425510223,"GB2-04":69.6314621432694,"GB2-05":73.6158347183136,"GB2-06":75.50742525274553,"GB2-07":75.33688057821094,"GB2-08":85.41538285431434},"medium":{"GB2-01":82.46274150897514,"GB2-02":43.874595076065454,"GB2-03":51.228963524558104,"GB2-04":68.44271176359538,"GB2-05":63.84636657954632,"GB2-06":84.47759690974846,"GB2-07":71.42716800267014,"GB2-08":64.85594310508506},"none":{"GB2-01":73.45241521393862,"GB2-02":43.689635420748104,"GB2-03":42.53119639443129,"GB2-04":41.61608832160143,"GB2-05":53.93728840619413,"GB2-06":43.27166120414261,"GB2-07":32.01382802822775,"GB2-08":81.73730968116008}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":72.0959056764509,"medium":66.32701080878051,"none":51.5311778338055},"reasoning_agg":{"highest":{"max":85.41538285431434,"mean":72.0959056764509,"min":46.99810425510223},"medium":{"max":84.47759690974846,"mean":66.32701080878051,"min":43.874595076065454},"none":{"max":81.73730968116008,"mean":51.5311778338055,"min":32.01382802822775}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":20.564727842645397}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:23389c580951846d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385362},"medium":{"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":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4863780000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.32749799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.48637800000000003},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.327498},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385362}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.21663491666666665,"median":0.058081,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":5.199238},"codegen_output_tokens":{"attempt_count":28,"output_max":70064,"output_mean":18803.166666666668,"output_min":1228,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":70064,"output_mean":51989.0,"output_min":25995,"run_count":8},"medium":{"attempt_count":11,"output_max":4348,"output_mean":2842.75,"output_min":1552,"run_count":8},"none":{"attempt_count":8,"output_max":2376,"output_mean":1577.75,"output_min":1228,"run_count":8}},"display_name":"Claude Sonnet 5.5","economics":{"all":61.65719473742604,"highest":91.73686778690728,"medium":52.046848019708754,"none":41.1878684056621},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn"],"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,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":451276,"total_reasoning_output_tokens":352227,"total_visible_output_tokens":99049,"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":"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-5-5","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.47181576777276,"score":59.47181576777276},"GB2-02":{"attempts":3,"playable":61.560979769213596,"score":61.560979769213596},"GB2-03":{"attempts":3,"playable":58.5612202616607,"score":58.5612202616607},"GB2-04":{"attempts":3,"playable":57.16276457193644,"score":57.16276457193644},"GB2-05":{"attempts":3,"playable":43.60250219175867,"score":43.60250219175867},"GB2-06":{"attempts":3,"playable":61.58743390986919,"score":61.58743390986919},"GB2-07":{"attempts":3,"playable":70.77810445454283,"score":70.77810445454283},"GB2-08":{"attempts":3,"playable":80.53273697265412,"score":80.53273697265412}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":79.57533966217044,"score":79.57533966217044},"GB2-02":{"attempts":1,"playable":95.83779536550492,"score":95.83779536550492},"GB2-03":{"attempts":1,"playable":95.54115824161748,"score":95.54115824161748},"GB2-04":{"attempts":1,"playable":84.16613454546233,"score":84.16613454546233},"GB2-05":{"attempts":1,"playable":97.27276340277697,"score":97.27276340277697},"GB2-06":{"attempts":1,"playable":89.15683710509073,"score":89.15683710509073},"GB2-07":{"attempts":1,"playable":93.48555527172981,"score":93.48555527172981},"GB2-08":{"attempts":1,"playable":98.85935870090556,"score":98.85935870090556}},"medium":{"GB2-01":{"attempts":1,"playable":46.939730165974964,"score":46.939730165974964},"GB2-02":{"attempts":1,"playable":42.78083264188377,"score":42.78083264188377},"GB2-03":{"attempts":1,"playable":31.639816509388925,"score":31.639816509388925},"GB2-04":{"attempts":1,"playable":41.84608795122939,"score":41.84608795122939},"GB2-05":{"attempts":1,"playable":19.433555287254414,"score":19.433555287254414},"GB2-06":{"attempts":1,"playable":77.39068920661367,"score":77.39068920661367},"GB2-07":{"attempts":1,"playable":72.3575908821202,"score":72.3575908821202},"GB2-08":{"attempts":1,"playable":83.98648151320465,"score":83.98648151320465}},"none":{"GB2-01":{"attempts":1,"playable":51.90037747517289,"score":51.90037747517289},"GB2-02":{"attempts":1,"playable":46.06431130025211,"score":46.06431130025211},"GB2-03":{"attempts":1,"playable":48.50268603397569,"score":48.50268603397569},"GB2-04":{"attempts":1,"playable":45.47607121911763,"score":45.47607121911763},"GB2-05":{"attempts":1,"playable":14.101187885244599,"score":14.101187885244599},"GB2-06":{"attempts":1,"playable":18.21477541790316,"score":18.21477541790316},"GB2-07":{"attempts":1,"playable":46.4911672097785,"score":46.4911672097785},"GB2-08":{"attempts":1,"playable":58.752370703852165,"score":58.752370703852165}}},"id":"claude-sonnet-5-5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:31:22Z","match_totals_all":{"draws":2027,"losses":3550,"wins":6013},"match_totals_tracks":{"highest":{"draws":301,"losses":172,"wins":3387},"medium":{"draws":891,"losses":1449,"wins":1524},"none":{"draws":835,"losses":1929,"wins":1102}},"model_slug":"claude-sonnet-5-5","overall":{"max":98.85935870090556,"mean":61.657194737426046,"min":14.101187885244599},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":79.57533966217044,"GB2-02":95.83779536550492,"GB2-03":95.54115824161748,"GB2-04":84.16613454546233,"GB2-05":97.27276340277697,"GB2-06":89.15683710509073,"GB2-07":93.48555527172981,"GB2-08":98.85935870090556},"per_game_all":{"GB2-01":59.47181576777276,"GB2-02":61.560979769213596,"GB2-03":58.5612202616607,"GB2-04":57.16276457193644,"GB2-05":43.60250219175867,"GB2-06":61.58743390986919,"GB2-07":70.77810445454283,"GB2-08":80.53273697265412},"per_game_match_totals_all":{"GB2-01":{"draws":206,"losses":511,"wins":747},"GB2-02":{"draws":724,"losses":176,"wins":462},"GB2-03":{"draws":317,"losses":453,"wins":634},"GB2-04":{"draws":655,"losses":290,"wins":465},"GB2-05":{"draws":0,"losses":859,"wins":655},"GB2-06":{"draws":52,"losses":541,"wins":835},"GB2-07":{"draws":0,"losses":446,"wins":1044},"GB2-08":{"draws":73,"losses":274,"wins":1171}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":149,"losses":31,"wins":308},"GB2-02":{"draws":21,"losses":8,"wins":425},"GB2-03":{"draws":1,"losses":20,"wins":447},"GB2-04":{"draws":81,"losses":37,"wins":352},"GB2-05":{"draws":0,"losses":12,"wins":492},"GB2-06":{"draws":42,"losses":34,"wins":400},"GB2-07":{"draws":0,"losses":30,"wins":466},"GB2-08":{"draws":7,"losses":0,"wins":497}},"medium":{"GB2-01":{"draws":12,"losses":260,"wins":216},"GB2-02":{"draws":356,"losses":89,"wins":9},"GB2-03":{"draws":207,"losses":230,"wins":31},"GB2-04":{"draws":305,"losses":126,"wins":39},"GB2-05":{"draws":0,"losses":411,"wins":95},"GB2-06":{"draws":4,"losses":110,"wins":362},"GB2-07":{"draws":0,"losses":142,"wins":356},"GB2-08":{"draws":7,"losses":81,"wins":416}},"none":{"GB2-01":{"draws":45,"losses":220,"wins":223},"GB2-02":{"draws":347,"losses":79,"wins":28},"GB2-03":{"draws":109,"losses":203,"wins":156},"GB2-04":{"draws":269,"losses":127,"wins":74},"GB2-05":{"draws":0,"losses":436,"wins":68},"GB2-06":{"draws":6,"losses":397,"wins":73},"GB2-07":{"draws":0,"losses":274,"wins":222},"GB2-08":{"draws":59,"losses":193,"wins":258}}},"per_game_raw_elo_all":{"GB2-01":1575.2607124437636,"GB2-02":1665.0887205606396,"GB2-03":1647.9867466845474,"GB2-04":1558.0597682116897,"GB2-05":1535.5097485093756,"GB2-06":1663.9029588351661,"GB2-07":1837.1322498576035,"GB2-08":2056.4171304145148},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1794.8431654234203,"GB2-02":2131.920846672061,"GB2-03":2254.966069054188,"GB2-04":1816.3606921365515,"GB2-05":2711.121724616978,"GB2-06":2155.275375770957,"GB2-07":2350.3983239383797,"GB2-08":2688.047220666137},"medium":{"GB2-01":1441.8216745227207,"GB2-02":1419.00087291022,"GB2-03":1269.8721955808594,"GB2-04":1414.8392448848335,"GB2-05":1001.1549487403443,"GB2-06":1899.6914645679403,"GB2-07":1755.905208555072,"GB2-08":1969.8249641662646},"none":{"GB2-01":1489.1172973851499,"GB2-02":1444.3444420996373,"GB2-03":1419.121975418595,"GB2-04":1442.979367613684,"GB2-05":894.2525721708048,"GB2-06":936.742036166601,"GB2-07":1405.093217079358,"GB2-08":1511.3792064111421}},"per_game_tracks":{"highest":{"GB2-01":79.57533966217044,"GB2-02":95.83779536550492,"GB2-03":95.54115824161748,"GB2-04":84.16613454546233,"GB2-05":97.27276340277697,"GB2-06":89.15683710509073,"GB2-07":93.48555527172981,"GB2-08":98.85935870090556},"medium":{"GB2-01":46.939730165974964,"GB2-02":42.78083264188377,"GB2-03":31.639816509388925,"GB2-04":41.84608795122939,"GB2-05":19.433555287254414,"GB2-06":77.39068920661367,"GB2-07":72.3575908821202,"GB2-08":83.98648151320465},"none":{"GB2-01":51.90037747517289,"GB2-02":46.06431130025211,"GB2-03":48.50268603397569,"GB2-04":45.47607121911763,"GB2-05":14.101187885244599,"GB2-06":18.21477541790316,"GB2-07":46.4911672097785,"GB2-08":58.752370703852165}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T10:52:46Z","reasoning":{"highest":91.73686778690728,"medium":52.046848019708754,"none":41.1878684056621},"reasoning_agg":{"highest":{"max":98.85935870090556,"mean":91.73686778690728,"min":79.57533966217044},"medium":{"max":83.98648151320465,"mean":52.046848019708754,"min":19.433555287254414},"none":{"max":58.752370703852165,"mean":41.1878684056621,"min":14.101187885244599}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":50.54899938124518}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:38cb1c3fa3c4d26e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.8727580000000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.872758}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.13107158333333335,"median":0.12371399999999999,"min":0.027072,"recorded_attempt_count":27,"run_count":24,"total":3.1457179999999996},"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":60.90833573696044,"highest":65.70838095285335,"medium":71.88197413283544,"none":45.13465212519257},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":60.316206100495585,"score":60.316206100495585},"GB2-02":{"attempts":3,"playable":60.498033496483345,"score":60.498033496483345},"GB2-03":{"attempts":3,"playable":54.632436475311515,"score":54.632436475311515},"GB2-04":{"attempts":3,"playable":56.55345710713798,"score":56.55345710713798},"GB2-05":{"attempts":3,"playable":72.97993711325074,"score":72.97993711325074},"GB2-06":{"attempts":3,"playable":53.04583861605699,"score":53.04583861605699},"GB2-07":{"attempts":3,"playable":70.03427053171619,"score":70.03427053171619},"GB2-08":{"attempts":3,"playable":59.206506455231214,"score":59.206506455231214}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":51.01459333098411,"score":51.01459333098411},"GB2-02":{"attempts":1,"playable":83.11775013728806,"score":83.11775013728806},"GB2-03":{"attempts":1,"playable":51.49473212699959,"score":51.49473212699959},"GB2-04":{"attempts":1,"playable":60.79695527679721,"score":60.79695527679721},"GB2-05":{"attempts":1,"playable":85.16167201153283,"score":85.16167201153283},"GB2-06":{"attempts":1,"playable":65.43382790497625,"score":65.43382790497625},"GB2-07":{"attempts":1,"playable":75.85228542141374,"score":75.85228542141374},"GB2-08":{"attempts":1,"playable":52.79523141283489,"score":52.79523141283489}},"medium":{"GB2-01":{"attempts":1,"playable":63.45488732296266,"score":63.45488732296266},"GB2-02":{"attempts":1,"playable":54.25285367919406,"score":54.25285367919406},"GB2-03":{"attempts":1,"playable":68.0157238257432,"score":68.0157238257432},"GB2-04":{"attempts":1,"playable":65.98542571742905,"score":65.98542571742905},"GB2-05":{"attempts":1,"playable":82.55536143633832,"score":82.55536143633832},"GB2-06":{"attempts":1,"playable":80.01934199358097,"score":80.01934199358097},"GB2-07":{"attempts":1,"playable":76.416727549484,"score":76.416727549484},"GB2-08":{"attempts":1,"playable":84.35547153795122,"score":84.35547153795122}},"none":{"GB2-01":{"attempts":1,"playable":66.47913764753999,"score":66.47913764753999},"GB2-02":{"attempts":1,"playable":44.12349667296793,"score":44.12349667296793},"GB2-03":{"attempts":1,"playable":44.38685347319177,"score":44.38685347319177},"GB2-04":{"attempts":1,"playable":42.8779903271877,"score":42.8779903271877},"GB2-05":{"attempts":1,"playable":51.2227778918811,"score":51.2227778918811},"GB2-06":{"attempts":1,"playable":13.684345949613755,"score":13.684345949613755},"GB2-07":{"attempts":1,"playable":57.83379862425081,"score":57.83379862425081},"GB2-08":{"attempts":1,"playable":40.46881641490753,"score":40.46881641490753}}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-10-22T10:30:31Z","match_totals_all":{"draws":2943,"losses":3234,"wins":5428},"match_totals_tracks":{"highest":{"draws":852,"losses":961,"wins":2054},"medium":{"draws":754,"losses":753,"wins":2357},"none":{"draws":1337,"losses":1520,"wins":1017}},"model_slug":"x-ai-grok-4-6","overall":{"max":85.16167201153283,"mean":60.908335736960446,"min":13.684345949613755},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":51.01459333098411,"GB2-02":83.11775013728806,"GB2-03":51.49473212699959,"GB2-04":60.79695527679721,"GB2-05":85.16167201153283,"GB2-06":65.43382790497625,"GB2-07":75.85228542141374,"GB2-08":52.79523141283489},"per_game_all":{"GB2-01":60.316206100495585,"GB2-02":60.498033496483345,"GB2-03":54.632436475311515,"GB2-04":56.55345710713798,"GB2-05":72.97993711325074,"GB2-06":53.04583861605699,"GB2-07":70.03427053171619,"GB2-08":59.206506455231214},"per_game_match_totals_all":{"GB2-01":{"draws":430,"losses":390,"wins":648},"GB2-02":{"draws":709,"losses":202,"wins":456},"GB2-03":{"draws":559,"losses":407,"wins":440},"GB2-04":{"draws":786,"losses":243,"wins":385},"GB2-05":{"draws":0,"losses":421,"wins":1091},"GB2-06":{"draws":59,"losses":668,"wins":707},"GB2-07":{"draws":0,"losses":454,"wins":1030},"GB2-08":{"draws":400,"losses":449,"wins":671}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":248,"losses":121,"wins":119},"GB2-02":{"draws":63,"losses":47,"wins":347},"GB2-03":{"draws":95,"losses":197,"wins":176},"GB2-04":{"draws":254,"losses":65,"wins":153},"GB2-05":{"draws":0,"losses":79,"wins":425},"GB2-06":{"draws":33,"losses":160,"wins":285},"GB2-07":{"draws":0,"losses":120,"wins":374},"GB2-08":{"draws":159,"losses":172,"wins":175}},"medium":{"GB2-01":{"draws":126,"losses":124,"wins":240},"GB2-02":{"draws":287,"losses":73,"wins":96},"GB2-03":{"draws":89,"losses":120,"wins":259},"GB2-04":{"draws":231,"losses":52,"wins":187},"GB2-05":{"draws":0,"losses":93,"wins":411},"GB2-06":{"draws":21,"losses":89,"wins":368},"GB2-07":{"draws":0,"losses":118,"wins":376},"GB2-08":{"draws":0,"losses":84,"wins":420}},"none":{"GB2-01":{"draws":56,"losses":145,"wins":289},"GB2-02":{"draws":359,"losses":82,"wins":13},"GB2-03":{"draws":375,"losses":90,"wins":5},"GB2-04":{"draws":301,"losses":126,"wins":45},"GB2-05":{"draws":0,"losses":249,"wins":255},"GB2-06":{"draws":5,"losses":419,"wins":54},"GB2-07":{"draws":0,"losses":216,"wins":280},"GB2-08":{"draws":241,"losses":193,"wins":76}}},"per_game_raw_elo_all":{"GB2-01":1572.9321113897674,"GB2-02":1579.3365235436222,"GB2-03":1478.9463536729363,"GB2-04":1531.9737818210822,"GB2-05":1838.8835669466973,"GB2-06":1495.145159844819,"GB2-07":1729.5541648990504,"GB2-08":1573.349389397659},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1480.6499682454164,"GB2-02":1800.7849393985764,"GB2-03":1445.5299704238205,"GB2-04":1564.086417677279,"GB2-05":2071.866660003493,"GB2-06":1680.3149737049687,"GB2-07":1815.0022929903025,"GB2-08":1437.5004252524388},"medium":{"GB2-01":1603.1496039544404,"GB2-02":1507.8397819078934,"GB2-03":1608.0525809486644,"GB2-04":1608.9657383910483,"GB2-05":1989.7928702625431,"GB2-06":1951.1868319425216,"GB2-07":1825.1315501933846,"GB2-08":1978.975156736049},"none":{"GB2-01":1634.996761969445,"GB2-02":1429.384849324397,"GB2-03":1383.2565096463243,"GB2-04":1422.869189394919,"GB2-05":1454.9911705740558,"GB2-06":853.9336738869667,"GB2-07":1548.5286515134642,"GB2-08":1303.5725862044894}},"per_game_tracks":{"highest":{"GB2-01":51.01459333098411,"GB2-02":83.11775013728806,"GB2-03":51.49473212699959,"GB2-04":60.79695527679721,"GB2-05":85.16167201153283,"GB2-06":65.43382790497625,"GB2-07":75.85228542141374,"GB2-08":52.79523141283489},"medium":{"GB2-01":63.45488732296266,"GB2-02":54.25285367919406,"GB2-03":68.0157238257432,"GB2-04":65.98542571742905,"GB2-05":82.55536143633832,"GB2-06":80.01934199358097,"GB2-07":76.416727549484,"GB2-08":84.35547153795122},"none":{"GB2-01":66.47913764753999,"GB2-02":44.12349667296793,"GB2-03":44.38685347319177,"GB2-04":42.8779903271877,"GB2-05":51.2227778918811,"GB2-06":13.684345949613755,"GB2-07":57.83379862425081,"GB2-08":40.46881641490753}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:35:03Z","reasoning":{"highest":65.70838095285335,"medium":71.88197413283544,"none":45.13465212519257},"reasoning_agg":{"highest":{"max":85.16167201153283,"mean":65.70838095285335,"min":51.01459333098411},"medium":{"max":84.35547153795122,"mean":71.88197413283544,"min":54.25285367919406},"none":{"max":66.47913764753999,"mean":45.13465212519257,"min":13.684345949613755}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":26.74732200764287}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:7c19b98b1f0b67a6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"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":true,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850015},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2555334390339119}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850015},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"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":true,"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":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.08231859375,"median":0.06440174762499168,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":1.97564625},"codegen_output_tokens":{"attempt_count":25,"output_max":73160,"output_mean":20095.833333333332,"output_min":1712,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":73160,"output_mean":40784.875,"output_min":28671,"run_count":8},"medium":{"attempt_count":8,"output_max":31721,"output_mean":16792.0,"output_min":5265,"run_count":8},"none":{"attempt_count":8,"output_max":3473,"output_mean":2710.625,"output_min":1712,"run_count":8}},"display_name":"Gemini 3.8 Flash","economics":{"all":60.60673502439463,"highest":65.76716810434628,"medium":60.49470626365813,"none":55.55833070517948},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":61.100078704747254,"score":61.100078704747254},"GB2-02":{"attempts":3,"playable":50.196062939371444,"score":50.196062939371444},"GB2-03":{"attempts":3,"playable":69.09825062325547,"score":69.09825062325547},"GB2-04":{"attempts":3,"playable":51.137925381173126,"score":51.137925381173126},"GB2-05":{"attempts":3,"playable":59.29104296650184,"score":59.29104296650184},"GB2-06":{"attempts":3,"playable":80.59356928321833,"score":80.59356928321833},"GB2-07":{"attempts":3,"playable":56.267740184256816,"score":56.267740184256816},"GB2-08":{"attempts":3,"playable":57.16921011263279,"score":57.16921011263279}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.66969806782727,"score":55.66969806782727},"GB2-02":{"attempts":1,"playable":69.61392765025036,"score":69.61392765025036},"GB2-03":{"attempts":1,"playable":71.04314377906931,"score":71.04314377906931},"GB2-04":{"attempts":1,"playable":47.241395731002974,"score":47.241395731002974},"GB2-05":{"attempts":1,"playable":66.7701532472458,"score":66.7701532472458},"GB2-06":{"attempts":1,"playable":87.81381385909661,"score":87.81381385909661},"GB2-07":{"attempts":1,"playable":69.10761259226376,"score":69.10761259226376},"GB2-08":{"attempts":1,"playable":58.87759990801419,"score":58.87759990801419}},"medium":{"GB2-01":{"attempts":1,"playable":71.14765855052795,"score":71.14765855052795},"GB2-02":{"attempts":1,"playable":40.198969945905944,"score":40.198969945905944},"GB2-03":{"attempts":1,"playable":84.72364586212821,"score":84.72364586212821},"GB2-04":{"attempts":1,"playable":59.99141626245316,"score":59.99141626245316},"GB2-05":{"attempts":1,"playable":55.432397469254454,"score":55.432397469254454},"GB2-06":{"attempts":1,"playable":79.54943977047272,"score":79.54943977047272},"GB2-07":{"attempts":1,"playable":57.40010741402786,"score":57.40010741402786},"GB2-08":{"attempts":1,"playable":35.514014834494795,"score":35.514014834494795}},"none":{"GB2-01":{"attempts":1,"playable":56.48287949588654,"score":56.48287949588654},"GB2-02":{"attempts":1,"playable":40.77529122195803,"score":40.77529122195803},"GB2-03":{"attempts":1,"playable":51.52796222856886,"score":51.52796222856886},"GB2-04":{"attempts":1,"playable":46.18096415006326,"score":46.18096415006326},"GB2-05":{"attempts":1,"playable":55.67057818300527,"score":55.67057818300527},"GB2-06":{"attempts":1,"playable":74.41745422008566,"score":74.41745422008566},"GB2-07":{"attempts":1,"playable":42.295500546478834,"score":42.295500546478834},"GB2-08":{"attempts":1,"playable":77.11601559538941,"score":77.11601559538941}}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:21:52Z","match_totals_all":{"draws":2458,"losses":3520,"wins":5636},"match_totals_tracks":{"highest":{"draws":444,"losses":1160,"wins":2266},"medium":{"draws":1055,"losses":1059,"wins":1758},"none":{"draws":959,"losses":1301,"wins":1612}},"model_slug":"google-gemini-3-8-flash","overall":{"max":87.81381385909661,"mean":60.60673502439463,"min":35.514014834494795},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.66969806782727,"GB2-02":69.61392765025036,"GB2-03":71.04314377906931,"GB2-04":47.241395731002974,"GB2-05":66.7701532472458,"GB2-06":87.81381385909661,"GB2-07":69.10761259226376,"GB2-08":58.87759990801419},"per_game_all":{"GB2-01":61.100078704747254,"GB2-02":50.196062939371444,"GB2-03":69.09825062325547,"GB2-04":51.137925381173126,"GB2-05":59.29104296650184,"GB2-06":80.59356928321833,"GB2-07":56.267740184256816,"GB2-08":57.16921011263279},"per_game_match_totals_all":{"GB2-01":{"draws":304,"losses":439,"wins":721},"GB2-02":{"draws":892,"losses":254,"wins":224},"GB2-03":{"draws":174,"losses":384,"wins":850},"GB2-04":{"draws":674,"losses":370,"wins":366},"GB2-05":{"draws":0,"losses":633,"wins":883},"GB2-06":{"draws":66,"losses":258,"wins":1110},"GB2-07":{"draws":0,"losses":679,"wins":809},"GB2-08":{"draws":348,"losses":503,"wins":673}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":44,"losses":202,"wins":242},"GB2-02":{"draws":184,"losses":51,"wins":221},"GB2-03":{"draws":7,"losses":148,"wins":315},"GB2-04":{"draws":85,"losses":212,"wins":173},"GB2-05":{"draws":0,"losses":173,"wins":333},"GB2-06":{"draws":34,"losses":44,"wins":400},"GB2-07":{"draws":0,"losses":158,"wins":338},"GB2-08":{"draws":90,"losses":172,"wins":244}},"medium":{"GB2-01":{"draws":75,"losses":108,"wins":305},"GB2-02":{"draws":351,"losses":105,"wins":2},"GB2-03":{"draws":84,"losses":35,"wins":351},"GB2-04":{"draws":293,"losses":48,"wins":129},"GB2-05":{"draws":0,"losses":232,"wins":272},"GB2-06":{"draws":16,"losses":93,"wins":369},"GB2-07":{"draws":0,"losses":222,"wins":276},"GB2-08":{"draws":236,"losses":216,"wins":54}},"none":{"GB2-01":{"draws":185,"losses":129,"wins":174},"GB2-02":{"draws":357,"losses":98,"wins":1},"GB2-03":{"draws":83,"losses":201,"wins":184},"GB2-04":{"draws":296,"losses":110,"wins":64},"GB2-05":{"draws":0,"losses":228,"wins":278},"GB2-06":{"draws":16,"losses":121,"wins":341},"GB2-07":{"draws":0,"losses":299,"wins":195},"GB2-08":{"draws":22,"losses":115,"wins":375}}},"per_game_raw_elo_all":{"GB2-01":1581.9156871493803,"GB2-02":1480.6900460297977,"GB2-03":1651.2745072567216,"GB2-04":1487.469717479614,"GB2-05":1561.0617021729843,"GB2-06":1968.6556402132128,"GB2-07":1533.7145577112235,"GB2-08":1527.131914508366},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1525.4236232108285,"GB2-02":1639.7879442256067,"GB2-03":1643.7683970979917,"GB2-04":1456.601789280027,"GB2-05":1664.1343799289111,"GB2-06":2120.96969354965,"GB2-07":1705.275995413632,"GB2-08":1513.0300567736433},"medium":{"GB2-01":1686.9858477094758,"GB2-02":1398.8852938065102,"GB2-03":1864.2293323808387,"GB2-04":1557.3871697672066,"GB2-05":1508.004527051816,"GB2-06":1941.8533140237796,"GB2-07":1542.8759343759423,"GB2-08":1252.668270178333},"none":{"GB2-01":1533.3375905278367,"GB2-02":1403.3969000572768,"GB2-03":1445.8257922913347,"GB2-04":1448.4201933916088,"GB2-05":1511.0461995382252,"GB2-06":1843.1439130662086,"GB2-07":1352.9917433440962,"GB2-08":1815.697416573122}},"per_game_tracks":{"highest":{"GB2-01":55.66969806782727,"GB2-02":69.61392765025036,"GB2-03":71.04314377906931,"GB2-04":47.241395731002974,"GB2-05":66.7701532472458,"GB2-06":87.81381385909661,"GB2-07":69.10761259226376,"GB2-08":58.87759990801419},"medium":{"GB2-01":71.14765855052795,"GB2-02":40.198969945905944,"GB2-03":84.72364586212821,"GB2-04":59.99141626245316,"GB2-05":55.432397469254454,"GB2-06":79.54943977047272,"GB2-07":57.40010741402786,"GB2-08":35.514014834494795},"none":{"GB2-01":56.48287949588654,"GB2-02":40.77529122195803,"GB2-03":51.52796222856886,"GB2-04":46.18096415006326,"GB2-05":55.67057818300527,"GB2-06":74.41745422008566,"GB2-07":42.295500546478834,"GB2-08":77.11601559538941}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:23:54Z","reasoning":{"highest":65.76716810434628,"medium":60.49470626365813,"none":55.55833070517948},"reasoning_agg":{"highest":{"max":87.81381385909661,"mean":65.76716810434628,"min":47.241395731002974},"medium":{"max":84.72364586212821,"mean":60.49470626365813,"min":35.514014834494795},"none":{"max":77.11601559538941,"mean":55.55833070517948,"min":40.77529122195803}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.208837399166804}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:752b6b5834374738","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":0.358603,"mean":0.24868390625000003,"median":0.2596235,"min":0.12429875,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.9894712499999998},"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":0.19110974999999997},"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":0.358603,"mean":0.24868390625000003,"median":0.2596235,"min":0.12429875,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.9894712499999998}},"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":0.358603,"mean":0.10824926041666667,"median":0.050446875,"min":0.017614,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":27,"run_count":24,"total":2.5979822500000003},"codegen_latency_ms":{"attempt_count":27,"max_ms":344702,"mean_ms":125679.0,"min_ms":18724,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":344702,"mean_ms":258574.75,"min_ms":141477,"run_count":8},"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":27,"output_max":82251,"output_mean":22811.583333333332,"output_min":2043,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":82251,"output_mean":55365.125,"output_min":27171,"run_count":8},"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":59.713902722536695,"highest":70.92888185439381,"medium":66.90747238617617,"none":41.30535392704014},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[943718],"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":79,"requested_max_output_token_observations":10,"requested_max_output_tokens":[943718],"total_output_tokens":547478,"total_reasoning_output_tokens":432530,"total_visible_output_tokens":114948,"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":"meta","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.993144531635075,"score":59.993144531635075},"GB2-02":{"attempts":3,"playable":55.75058615829209,"score":55.75058615829209},"GB2-03":{"attempts":3,"playable":67.86119700896981,"score":67.86119700896981},"GB2-04":{"attempts":3,"playable":52.89694436522464,"score":52.89694436522464},"GB2-05":{"attempts":3,"playable":59.594110727052076,"score":59.594110727052076},"GB2-06":{"attempts":3,"playable":69.52094797058216,"score":69.52094797058216},"GB2-07":{"attempts":3,"playable":50.07089991885337,"score":50.07089991885337},"GB2-08":{"attempts":3,"playable":62.023391099684396,"score":62.023391099684396}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":77.75263484210915,"score":77.75263484210915},"GB2-02":{"attempts":1,"playable":62.44700372947579,"score":62.44700372947579},"GB2-03":{"attempts":1,"playable":83.49631691573695,"score":83.49631691573695},"GB2-04":{"attempts":1,"playable":51.0330439953902,"score":51.0330439953902},"GB2-05":{"attempts":1,"playable":79.52716708298662,"score":79.52716708298662},"GB2-06":{"attempts":1,"playable":84.44208637897101,"score":84.44208637897101},"GB2-07":{"attempts":1,"playable":58.12360186503144,"score":58.12360186503144},"GB2-08":{"attempts":1,"playable":70.6092000254493,"score":70.6092000254493}},"medium":{"GB2-01":{"attempts":1,"playable":75.59942432876706,"score":75.59942432876706},"GB2-02":{"attempts":1,"playable":57.54876949818144,"score":57.54876949818144},"GB2-03":{"attempts":1,"playable":64.19008826477986,"score":64.19008826477986},"GB2-04":{"attempts":1,"playable":64.77306742104369,"score":64.77306742104369},"GB2-05":{"attempts":1,"playable":58.663608441361625,"score":58.663608441361625},"GB2-06":{"attempts":1,"playable":82.4660876226747,"score":82.4660876226747},"GB2-07":{"attempts":1,"playable":54.524589916004416,"score":54.524589916004416},"GB2-08":{"attempts":1,"playable":77.49414359659654,"score":77.49414359659654}},"none":{"GB2-01":{"attempts":1,"playable":26.62737442402904,"score":26.62737442402904},"GB2-02":{"attempts":1,"playable":47.25598524721902,"score":47.25598524721902},"GB2-03":{"attempts":1,"playable":55.8971858463926,"score":55.8971858463926},"GB2-04":{"attempts":1,"playable":42.88472167924003,"score":42.88472167924003},"GB2-05":{"attempts":1,"playable":40.59155665680798,"score":40.59155665680798},"GB2-06":{"attempts":1,"playable":41.654669910100786,"score":41.654669910100786},"GB2-07":{"attempts":1,"playable":37.56450797552427,"score":37.56450797552427},"GB2-08":{"attempts":1,"playable":37.96682967700734,"score":37.96682967700734}}},"id":"meta/muse-spark-1.3","is_recent_addition":false,"last_measured_at":"2026-10-22T10:00:07Z","match_totals_all":{"draws":2191,"losses":3769,"wins":5642},"match_totals_tracks":{"highest":{"draws":513,"losses":912,"wins":2433},"medium":{"draws":603,"losses":1040,"wins":2231},"none":{"draws":1075,"losses":1817,"wins":978}},"model_slug":"meta-muse-spark-1-3","overall":{"max":84.44208637897101,"mean":59.713902722536695,"min":26.62737442402904},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.75263484210915,"GB2-02":62.44700372947579,"GB2-03":83.49631691573695,"GB2-04":51.0330439953902,"GB2-05":79.52716708298662,"GB2-06":84.44208637897101,"GB2-07":58.12360186503144,"GB2-08":70.6092000254493},"per_game_all":{"GB2-01":59.993144531635075,"GB2-02":55.75058615829209,"GB2-03":67.86119700896981,"GB2-04":52.89694436522464,"GB2-05":59.594110727052076,"GB2-06":69.52094797058216,"GB2-07":50.07089991885337,"GB2-08":62.023391099684396},"per_game_match_totals_all":{"GB2-01":{"draws":103,"losses":557,"wins":810},"GB2-02":{"draws":900,"losses":176,"wins":294},"GB2-03":{"draws":176,"losses":400,"wins":830},"GB2-04":{"draws":622,"losses":371,"wins":417},"GB2-05":{"draws":0,"losses":625,"wins":887},"GB2-06":{"draws":62,"losses":427,"wins":943},"GB2-07":{"draws":0,"losses":774,"wins":710},"GB2-08":{"draws":328,"losses":439,"wins":751}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":110,"wins":374},"GB2-02":{"draws":262,"losses":46,"wins":146},"GB2-03":{"draws":37,"losses":68,"wins":363},"GB2-04":{"draws":124,"losses":175,"wins":171},"GB2-05":{"draws":0,"losses":107,"wins":397},"GB2-06":{"draws":35,"losses":59,"wins":382},"GB2-07":{"draws":0,"losses":216,"wins":278},"GB2-08":{"draws":51,"losses":131,"wins":322}},"medium":{"GB2-01":{"draws":0,"losses":127,"wins":363},"GB2-02":{"draws":290,"losses":57,"wins":113},"GB2-03":{"draws":58,"losses":153,"wins":259},"GB2-04":{"draws":238,"losses":52,"wins":180},"GB2-05":{"draws":0,"losses":214,"wins":290},"GB2-06":{"draws":12,"losses":81,"wins":385},"GB2-07":{"draws":0,"losses":237,"wins":259},"GB2-08":{"draws":5,"losses":119,"wins":382}},"none":{"GB2-01":{"draws":99,"losses":320,"wins":73},"GB2-02":{"draws":348,"losses":73,"wins":35},"GB2-03":{"draws":81,"losses":179,"wins":208},"GB2-04":{"draws":260,"losses":144,"wins":66},"GB2-05":{"draws":0,"losses":304,"wins":200},"GB2-06":{"draws":15,"losses":287,"wins":176},"GB2-07":{"draws":0,"losses":321,"wins":173},"GB2-08":{"draws":272,"losses":189,"wins":47}}},"per_game_raw_elo_all":{"GB2-01":1582.1208582047666,"GB2-02":1520.810565199011,"GB2-03":1629.96055301448,"GB2-04":1502.341257016049,"GB2-05":1593.1604015526984,"GB2-06":1780.9894560192936,"GB2-07":1450.5932050882013,"GB2-08":1597.721170770457},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1769.4121867548668,"GB2-02":1574.7829356458012,"GB2-03":1838.0202561833466,"GB2-04":1485.929339839367,"GB2-05":1908.207883470175,"GB2-06":2043.0289892205708,"GB2-07":1552.3169732650538,"GB2-08":1691.818940447793},"medium":{"GB2-01":1741.0706406778183,"GB2-02":1534.1301768302524,"GB2-03":1566.455902928939,"GB2-04":1598.1729604520099,"GB2-05":1549.8610448719794,"GB2-06":2000.954632504332,"GB2-07":1505.8442201895564,"GB2-08":1823.5041433720414},"none":{"GB2-01":1235.8797471816144,"GB2-02":1453.5185831209799,"GB2-03":1485.4054999311543,"GB2-04":1422.92147075677,"GB2-05":1321.412276315941,"GB2-06":1298.9847463329781,"GB2-07":1293.618421809994,"GB2-08":1277.8404284915368}},"per_game_tracks":{"highest":{"GB2-01":77.75263484210915,"GB2-02":62.44700372947579,"GB2-03":83.49631691573695,"GB2-04":51.0330439953902,"GB2-05":79.52716708298662,"GB2-06":84.44208637897101,"GB2-07":58.12360186503144,"GB2-08":70.6092000254493},"medium":{"GB2-01":75.59942432876706,"GB2-02":57.54876949818144,"GB2-03":64.19008826477986,"GB2-04":64.77306742104369,"GB2-05":58.663608441361625,"GB2-06":82.4660876226747,"GB2-07":54.524589916004416,"GB2-08":77.49414359659654},"none":{"GB2-01":26.62737442402904,"GB2-02":47.25598524721902,"GB2-03":55.8971858463926,"GB2-04":42.88472167924003,"GB2-05":40.59155665680798,"GB2-06":41.654669910100786,"GB2-07":37.56450797552427,"GB2-08":37.96682967700734}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:32:13Z","reasoning":{"highest":70.92888185439381,"medium":66.90747238617617,"none":41.30535392704014},"reasoning_agg":{"highest":{"max":84.44208637897101,"mean":70.92888185439381,"min":51.0330439953902},"medium":{"max":82.4660876226747,"mean":66.90747238617617,"min":54.524589916004416},"none":{"max":55.8971858463926,"mean":41.30535392704014,"min":26.62737442402904}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.62352792735367}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-open:bf4740edbe797f8b","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":0.15589245,"mean":0.10417243749999998,"median":0.11212245,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":8,"run_count":8,"total":0.8333794999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0828612,"mean":0.042346231250000005,"median":0.032108575,"min":0.0286407,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.33876985},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.053624950000000005,"mean":0.0276842,"median":0.025075325,"min":0.0206182,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.22147360000000002}},"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":0.0828612,"mean":0.042346231250000005,"median":0.032108575,"min":0.0286407,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.33876985000000004},"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":0.053624950000000005,"mean":0.0276842,"median":0.025075325,"min":0.0206182,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.22147360000000002},"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":0.15589245,"mean":0.10417243749999998,"median":0.11212245,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":8,"run_count":8,"total":0.8333794999999999}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.05806762291666667,"median":0.032108575,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":27,"run_count":24,"total":1.3936229500000001},"codegen_latency_ms":{"attempt_count":26,"max_ms":402561,"mean_ms":134621.65217391305,"min_ms":29772,"run_count":23},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":7,"max_ms":402561,"mean_ms":285010.28571428574,"min_ms":177131,"run_count":7},"medium":{"attempt_count":10,"max_ms":176476,"mean_ms":81184.125,"min_ms":41325,"run_count":8},"none":{"attempt_count":9,"max_ms":171955,"mean_ms":56469.125,"min_ms":29772,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":34389,"output_mean":11455.5,"output_min":2743,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":34389,"output_mean":23554.125,"output_min":8453,"run_count":8},"medium":{"attempt_count":10,"output_max":13963,"output_mean":6880.875,"output_min":3882,"run_count":8},"none":{"attempt_count":9,"output_max":7898,"output_mean":3931.5,"output_min":2743,"run_count":8}},"display_name":"Muse Spark Open","economics":{"all":59.27478220330371,"highest":63.66536948319274,"medium":54.714666668650906,"none":56.47428368587873},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[943718],"finish_reason_observations":26,"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,"requested_max_output_token_observations":27,"requested_max_output_tokens":[943718],"total_output_tokens":274932,"total_reasoning_output_tokens":170578,"total_visible_output_tokens":104354,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-open","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":7,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-02"],"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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":68.71659763238331,"score":68.71659763238331},"GB2-02":{"attempts":2,"playable":45.199381474604266,"score":45.199381474604266},"GB2-03":{"attempts":3,"playable":51.792390606848244,"score":51.792390606848244},"GB2-04":{"attempts":3,"playable":44.932478997967756,"score":44.932478997967756},"GB2-05":{"attempts":3,"playable":51.34368462830886,"score":51.34368462830886},"GB2-06":{"attempts":3,"playable":63.88740470144051,"score":63.88740470144051},"GB2-07":{"attempts":3,"playable":55.0410596067371,"score":55.0410596067371},"GB2-08":{"attempts":3,"playable":79.20985924944017,"score":79.20985924944017}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":90.46276540403163,"score":90.46276540403163},"GB2-03":{"attempts":1,"playable":66.97071653851859,"score":66.97071653851859},"GB2-04":{"attempts":1,"playable":39.09917306762819,"score":39.09917306762819},"GB2-05":{"attempts":1,"playable":42.29590634035252,"score":42.29590634035252},"GB2-06":{"attempts":1,"playable":51.163056905341705,"score":51.163056905341705},"GB2-07":{"attempts":1,"playable":74.01937251035218,"score":74.01937251035218},"GB2-08":{"attempts":1,"playable":81.64659561612439,"score":81.64659561612439}},"medium":{"GB2-01":{"attempts":1,"playable":51.93903790256137,"score":51.93903790256137},"GB2-02":{"attempts":1,"playable":44.557191155083636,"score":44.557191155083636},"GB2-03":{"attempts":1,"playable":32.73235054646836,"score":32.73235054646836},"GB2-04":{"attempts":1,"playable":48.09690080671397,"score":48.09690080671397},"GB2-05":{"attempts":1,"playable":54.97365098957368,"score":54.97365098957368},"GB2-06":{"attempts":1,"playable":77.79804496903472,"score":77.79804496903472},"GB2-07":{"attempts":1,"playable":56.61358827682659,"score":56.61358827682659},"GB2-08":{"attempts":1,"playable":71.00656870294493,"score":71.00656870294493}},"none":{"GB2-01":{"attempts":1,"playable":63.747989590556934,"score":63.747989590556934},"GB2-02":{"attempts":1,"playable":45.8415717941249,"score":45.8415717941249},"GB2-03":{"attempts":1,"playable":55.674104735557805,"score":55.674104735557805},"GB2-04":{"attempts":1,"playable":47.6013631195611,"score":47.6013631195611},"GB2-05":{"attempts":1,"playable":56.76149655500038,"score":56.76149655500038},"GB2-06":{"attempts":1,"playable":62.70111222994509,"score":62.70111222994509},"GB2-07":{"attempts":1,"playable":34.49021803303253,"score":34.49021803303253},"GB2-08":{"attempts":1,"playable":84.97641342925118,"score":84.97641342925118}}},"id":"meta/muse-spark-open","is_recent_addition":false,"last_measured_at":"2026-10-22T10:59:28Z","match_totals_all":{"draws":1160,"losses":2105,"wins":2867},"match_totals_tracks":{"highest":{"draws":200,"losses":670,"wins":1188},"medium":{"draws":520,"losses":733,"wins":816},"none":{"draws":440,"losses":702,"wins":863}},"model_slug":"meta-muse-spark-open","overall":{"max":90.46276540403163,"mean":58.284773279240795,"min":32.73235054646836},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":18,"overall_ranking_status":"partial","per_game":{"GB2-01":90.46276540403163,"GB2-03":66.97071653851859,"GB2-04":39.09917306762819,"GB2-05":42.29590634035252,"GB2-06":51.163056905341705,"GB2-07":74.01937251035218,"GB2-08":81.64659561612439},"per_game_all":{"GB2-01":68.71659763238331,"GB2-03":51.792390606848244,"GB2-04":44.932478997967756,"GB2-05":51.34368462830886,"GB2-06":63.88740470144051,"GB2-07":55.0410596067371,"GB2-08":79.20985924944017},"per_game_match_totals_all":{"GB2-01":{"draws":100,"losses":213,"wins":467},"GB2-02":{"draws":398,"losses":97,"wins":30},"GB2-03":{"draws":160,"losses":311,"wins":283},"GB2-04":{"draws":477,"losses":203,"wins":110},"GB2-05":{"draws":0,"losses":418,"wins":392},"GB2-06":{"draws":25,"losses":323,"wins":499},"GB2-07":{"draws":0,"losses":380,"wins":548},"GB2-08":{"draws":0,"losses":160,"wins":538}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":26,"wins":230},"GB2-03":{"draws":33,"losses":84,"wins":143},"GB2-04":{"draws":156,"losses":84,"wins":28},"GB2-05":{"draws":0,"losses":160,"wins":110},"GB2-06":{"draws":11,"losses":144,"wins":129},"GB2-07":{"draws":0,"losses":131,"wins":361},"GB2-08":{"draws":0,"losses":41,"wins":187}},"medium":{"GB2-01":{"draws":63,"losses":107,"wins":102},"GB2-02":{"draws":201,"losses":55,"wins":14},"GB2-03":{"draws":66,"losses":143,"wins":39},"GB2-04":{"draws":177,"losses":50,"wins":39},"GB2-05":{"draws":0,"losses":134,"wins":144},"GB2-06":{"draws":13,"losses":65,"wins":199},"GB2-07":{"draws":0,"losses":104,"wins":116},"GB2-08":{"draws":0,"losses":75,"wins":163}},"none":{"GB2-01":{"draws":37,"losses":80,"wins":135},"GB2-02":{"draws":197,"losses":42,"wins":16},"GB2-03":{"draws":61,"losses":84,"wins":101},"GB2-04":{"draws":144,"losses":69,"wins":43},"GB2-05":{"draws":0,"losses":124,"wins":138},"GB2-06":{"draws":1,"losses":114,"wins":171},"GB2-07":{"draws":0,"losses":145,"wins":71},"GB2-08":{"draws":0,"losses":44,"wins":188}}},"per_game_raw_elo_all":{"GB2-01":1697.8728629738032,"GB2-03":1453.2369791684043,"GB2-04":1438.617309723203,"GB2-05":1456.82977690609,"GB2-06":1661.9930508056343,"GB2-07":1523.3844165400312,"GB2-08":1869.2042063574245},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1997.9459780541463,"GB2-03":1596.3405106314158,"GB2-04":1393.2688777485862,"GB2-05":1343.2690508234189,"GB2-06":1445.2661110479244,"GB2-07":1783.2976070594639,"GB2-08":1914.144855611611},"medium":{"GB2-01":1489.4872701853576,"GB2-02":1432.7315994236355,"GB2-03":1280.0243942626194,"GB2-04":1463.2037934276082,"GB2-05":1502.1621832408184,"GB2-06":1907.566337963385,"GB2-07":1532.6726825609805,"GB2-08":1698.8367363315278},"none":{"GB2-01":1606.1853406819057,"GB2-02":1442.629321797202,"GB2-03":1483.3460326111783,"GB2-04":1459.3792579934154,"GB2-05":1525.0580966540324,"GB2-06":1633.1467034055936,"GB2-07":1254.182959999649,"GB2-08":1994.631027129134}},"per_game_tracks":{"highest":{"GB2-01":90.46276540403163,"GB2-03":66.97071653851859,"GB2-04":39.09917306762819,"GB2-05":42.29590634035252,"GB2-06":51.163056905341705,"GB2-07":74.01937251035218,"GB2-08":81.64659561612439},"medium":{"GB2-01":51.93903790256137,"GB2-02":44.557191155083636,"GB2-03":32.73235054646836,"GB2-04":48.09690080671397,"GB2-05":54.97365098957368,"GB2-06":77.79804496903472,"GB2-07":56.61358827682659,"GB2-08":71.00656870294493},"none":{"GB2-01":63.747989590556934,"GB2-02":45.8415717941249,"GB2-03":55.674104735557805,"GB2-04":47.6013631195611,"GB2-05":56.76149655500038,"GB2-06":62.70111222994509,"GB2-07":34.49021803303253,"GB2-08":84.97641342925118}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.66536948319274,"medium":54.714666668650906,"none":56.47428368587873},"reasoning_agg":{"highest":{"max":90.46276540403163,"mean":63.66536948319274,"min":39.09917306762819},"medium":{"max":77.79804496903472,"mean":54.714666668650906,"min":32.73235054646836},"none":{"max":84.97641342925118,"mean":56.47428368587873,"min":34.49021803303253}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.950702814541835}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:0f62cbefe9dc6770","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-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087456},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":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-2026-10-09":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-2026-10-09":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-2026-10-09":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-2026-10-09":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998544},"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":58.0746618992464,"highest":63.49456842548774,"medium":61.66835056152032,"none":49.061066710731154},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":73.5717324808075,"score":73.5717324808075},"GB2-02":{"attempts":3,"playable":51.86389266892035,"score":51.86389266892035},"GB2-03":{"attempts":3,"playable":39.40205937441047,"score":39.40205937441047},"GB2-04":{"attempts":3,"playable":43.219295373319376,"score":43.219295373319376},"GB2-05":{"attempts":3,"playable":61.23687750560756,"score":61.23687750560756},"GB2-06":{"attempts":3,"playable":47.61999237936589,"score":47.61999237936589},"GB2-07":{"attempts":3,"playable":61.08014441717088,"score":61.08014441717088},"GB2-08":{"attempts":3,"playable":86.60330099436919,"score":86.60330099436919}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.11445997747924,"score":84.11445997747924},"GB2-02":{"attempts":1,"playable":59.65764818226014,"score":59.65764818226014},"GB2-03":{"attempts":1,"playable":45.893061109741424,"score":45.893061109741424},"GB2-04":{"attempts":1,"playable":44.114044858873505,"score":44.114044858873505},"GB2-05":{"attempts":1,"playable":73.21568141352,"score":73.21568141352},"GB2-06":{"attempts":1,"playable":54.447755696869194,"score":54.447755696869194},"GB2-07":{"attempts":1,"playable":56.27538540166795,"score":56.27538540166795},"GB2-08":{"attempts":1,"playable":90.23851076349038,"score":90.23851076349038}},"medium":{"GB2-01":{"attempts":1,"playable":84.10834529070434,"score":84.10834529070434},"GB2-02":{"attempts":1,"playable":52.330939920512535,"score":52.330939920512535},"GB2-03":{"attempts":1,"playable":56.19213165092924,"score":56.19213165092924},"GB2-04":{"attempts":1,"playable":42.77159117882744,"score":42.77159117882744},"GB2-05":{"attempts":1,"playable":67.40808086925315,"score":67.40808086925315},"GB2-06":{"attempts":1,"playable":45.09302369059133,"score":45.09302369059133},"GB2-07":{"attempts":1,"playable":58.468328390803,"score":58.468328390803},"GB2-08":{"attempts":1,"playable":86.97436350054153,"score":86.97436350054153}},"none":{"GB2-01":{"attempts":1,"playable":52.49239217423892,"score":52.49239217423892},"GB2-02":{"attempts":1,"playable":43.603089903988376,"score":43.603089903988376},"GB2-03":{"attempts":1,"playable":16.120985362560745,"score":16.120985362560745},"GB2-04":{"attempts":1,"playable":42.772250082257194,"score":42.772250082257194},"GB2-05":{"attempts":1,"playable":43.086870234049506,"score":43.086870234049506},"GB2-06":{"attempts":1,"playable":43.31919775063714,"score":43.31919775063714},"GB2-07":{"attempts":1,"playable":68.4967194590417,"score":68.4967194590417},"GB2-08":{"attempts":1,"playable":82.59702871907564,"score":82.59702871907564}}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:44:15Z","match_totals_all":{"draws":2450,"losses":3775,"wins":5376},"match_totals_tracks":{"highest":{"draws":654,"losses":1131,"wins":2081},"medium":{"draws":799,"losses":1128,"wins":1939},"none":{"draws":997,"losses":1516,"wins":1356}},"model_slug":"x-ai-grok-4-5","overall":{"max":90.23851076349038,"mean":58.0746618992464,"min":16.120985362560745},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.11445997747924,"GB2-02":59.65764818226014,"GB2-03":45.893061109741424,"GB2-04":44.114044858873505,"GB2-05":73.21568141352,"GB2-06":54.447755696869194,"GB2-07":56.27538540166795,"GB2-08":90.23851076349038},"per_game_all":{"GB2-01":73.5717324808075,"GB2-02":51.86389266892035,"GB2-03":39.40205937441047,"GB2-04":43.219295373319376,"GB2-05":61.23687750560756,"GB2-06":47.61999237936589,"GB2-07":61.08014441717088,"GB2-08":86.60330099436919},"per_game_match_totals_all":{"GB2-01":{"draws":372,"losses":220,"wins":873},"GB2-02":{"draws":869,"losses":242,"wins":257},"GB2-03":{"draws":300,"losses":740,"wins":368},"GB2-04":{"draws":861,"losses":391,"wins":160},"GB2-05":{"draws":0,"losses":601,"wins":917},"GB2-06":{"draws":42,"losses":775,"wins":617},"GB2-07":{"draws":0,"losses":600,"wins":880},"GB2-08":{"draws":6,"losses":206,"wins":1304}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":98,"losses":33,"wins":357},"GB2-02":{"draws":229,"losses":76,"wins":151},"GB2-03":{"draws":110,"losses":214,"wins":146},"GB2-04":{"draws":197,"losses":171,"wins":102},"GB2-05":{"draws":0,"losses":141,"wins":365},"GB2-06":{"draws":18,"losses":222,"wins":238},"GB2-07":{"draws":0,"losses":225,"wins":267},"GB2-08":{"draws":2,"losses":49,"wins":455}},"medium":{"GB2-01":{"draws":41,"losses":63,"wins":384},"GB2-02":{"draws":290,"losses":78,"wins":88},"GB2-03":{"draws":121,"losses":157,"wins":190},"GB2-04":{"draws":327,"losses":112,"wins":31},"GB2-05":{"draws":0,"losses":168,"wins":338},"GB2-06":{"draws":16,"losses":270,"wins":192},"GB2-07":{"draws":0,"losses":214,"wins":280},"GB2-08":{"draws":4,"losses":66,"wins":436}},"none":{"GB2-01":{"draws":233,"losses":124,"wins":132},"GB2-02":{"draws":350,"losses":88,"wins":18},"GB2-03":{"draws":69,"losses":369,"wins":32},"GB2-04":{"draws":337,"losses":108,"wins":27},"GB2-05":{"draws":0,"losses":292,"wins":214},"GB2-06":{"draws":8,"losses":283,"wins":187},"GB2-07":{"draws":0,"losses":161,"wins":333},"GB2-08":{"draws":0,"losses":91,"wins":413}}},"per_game_raw_elo_all":{"GB2-01":1742.187344683205,"GB2-02":1489.832212662512,"GB2-03":1327.6166686065362,"GB2-04":1425.514011385994,"GB2-05":1599.9910243963204,"GB2-06":1390.9604024013152,"GB2-07":1593.7532440226641,"GB2-08":2043.016483311679},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1865.940088827249,"GB2-02":1551.3572371242985,"GB2-03":1396.3481995788898,"GB2-04":1432.4516256240286,"GB2-05":1772.6759586119083,"GB2-06":1497.18003837485,"GB2-07":1528.303476923122,"GB2-08":2145.228754453993},"medium":{"GB2-01":1865.8348710622554,"GB2-02":1492.7747454115188,"GB2-03":1488.1359064545704,"GB2-04":1422.0426445081857,"GB2-05":1673.9785874775043,"GB2-06":1351.3948842195146,"GB2-07":1556.835147283468,"GB2-08":2047.5177416114107},"none":{"GB2-01":1494.7870741601107,"GB2-02":1425.3646554517188,"GB2-03":1098.3658997861482,"GB2-04":1422.047764025768,"GB2-05":1353.3185270995486,"GB2-06":1324.3062846095804,"GB2-07":1696.1211078614028,"GB2-08":1936.3029538696337}},"per_game_tracks":{"highest":{"GB2-01":84.11445997747924,"GB2-02":59.65764818226014,"GB2-03":45.893061109741424,"GB2-04":44.114044858873505,"GB2-05":73.21568141352,"GB2-06":54.447755696869194,"GB2-07":56.27538540166795,"GB2-08":90.23851076349038},"medium":{"GB2-01":84.10834529070434,"GB2-02":52.330939920512535,"GB2-03":56.19213165092924,"GB2-04":42.77159117882744,"GB2-05":67.40808086925315,"GB2-06":45.09302369059133,"GB2-07":58.468328390803,"GB2-08":86.97436350054153},"none":{"GB2-01":52.49239217423892,"GB2-02":43.603089903988376,"GB2-03":16.120985362560745,"GB2-04":42.772250082257194,"GB2-05":43.086870234049506,"GB2-06":43.31919775063714,"GB2-07":68.4967194590417,"GB2-08":82.59702871907564}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:37:50Z","reasoning":{"highest":63.49456842548774,"medium":61.66835056152032,"none":49.061066710731154},"reasoning_agg":{"highest":{"max":90.23851076349038,"mean":63.49456842548774,"min":44.114044858873505},"medium":{"max":86.97436350054153,"mean":61.66835056152032,"min":42.77159117882744},"none":{"max":82.59702871907564,"mean":49.061066710731154,"min":16.120985362560745}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":14.433501714756588}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:cbff4a5de71ce87c","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":0.48296144},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558000000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.0681627}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558000000003},"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":0.48296144}},"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":57.490853269447555,"highest":68.42167277093799,"medium":52.10170830269207,"none":51.94917873471262},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":61.98733308768022,"score":61.98733308768022},"GB2-02":{"attempts":3,"playable":54.40958426172468,"score":54.40958426172468},"GB2-03":{"attempts":3,"playable":63.504701573793255,"score":63.504701573793255},"GB2-04":{"attempts":3,"playable":62.39595742410436,"score":62.39595742410436},"GB2-05":{"attempts":3,"playable":56.28255073240749,"score":56.28255073240749},"GB2-06":{"attempts":3,"playable":67.3646890725987,"score":67.3646890725987},"GB2-07":{"attempts":3,"playable":65.8516290314971,"score":65.8516290314971},"GB2-08":{"attempts":3,"playable":28.130380971774656,"score":28.130380971774656}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.91317461108321,"score":41.91317461108321},"GB2-02":{"attempts":1,"playable":69.36515869151873,"score":69.36515869151873},"GB2-03":{"attempts":1,"playable":84.99804643586837,"score":84.99804643586837},"GB2-04":{"attempts":1,"playable":78.65053228769119,"score":78.65053228769119},"GB2-05":{"attempts":1,"playable":78.82765608007782,"score":78.82765608007782},"GB2-06":{"attempts":1,"playable":82.32401670554906,"score":82.32401670554906},"GB2-07":{"attempts":1,"playable":73.82781907037081,"score":73.82781907037081},"GB2-08":{"attempts":1,"playable":37.46697828534474,"score":37.46697828534474}},"medium":{"GB2-01":{"attempts":1,"playable":77.89450722012026,"score":77.89450722012026},"GB2-02":{"attempts":1,"playable":51.98935472492092,"score":51.98935472492092},"GB2-03":{"attempts":1,"playable":57.43081529166134,"score":57.43081529166134},"GB2-04":{"attempts":1,"playable":55.94676910470221,"score":55.94676910470221},"GB2-05":{"attempts":1,"playable":40.237293513176795,"score":40.237293513176795},"GB2-06":{"attempts":1,"playable":55.56604691445873,"score":55.56604691445873},"GB2-07":{"attempts":1,"playable":58.902342041552615,"score":58.902342041552615},"GB2-08":{"attempts":1,"playable":18.846537610943624,"score":18.846537610943624}},"none":{"GB2-01":{"attempts":1,"playable":66.1543174318372,"score":66.1543174318372},"GB2-02":{"attempts":1,"playable":41.87423936873439,"score":41.87423936873439},"GB2-03":{"attempts":1,"playable":48.08524299385004,"score":48.08524299385004},"GB2-04":{"attempts":1,"playable":52.590570879919696,"score":52.590570879919696},"GB2-05":{"attempts":1,"playable":49.78270260396789,"score":49.78270260396789},"GB2-06":{"attempts":1,"playable":64.20400359778829,"score":64.20400359778829},"GB2-07":{"attempts":1,"playable":64.82472598256784,"score":64.82472598256784},"GB2-08":{"attempts":1,"playable":28.07762701903561,"score":28.07762701903561}}},"id":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-10-22T10:55:49Z","match_totals_all":{"draws":2619,"losses":3806,"wins":5163},"match_totals_tracks":{"highest":{"draws":655,"losses":946,"wins":2263},"medium":{"draws":840,"losses":1499,"wins":1521},"none":{"draws":1124,"losses":1361,"wins":1379}},"model_slug":"z-ai-glm-5-3-flashx","overall":{"max":84.99804643586837,"mean":57.49085326944756,"min":18.846537610943624},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":41.91317461108321,"GB2-02":69.36515869151873,"GB2-03":84.99804643586837,"GB2-04":78.65053228769119,"GB2-05":78.82765608007782,"GB2-06":82.32401670554906,"GB2-07":73.82781907037081,"GB2-08":37.46697828534474},"per_game_all":{"GB2-01":61.98733308768022,"GB2-02":54.40958426172468,"GB2-03":63.504701573793255,"GB2-04":62.39595742410436,"GB2-05":56.28255073240749,"GB2-06":67.3646890725987,"GB2-07":65.8516290314971,"GB2-08":28.130380971774656},"per_game_match_totals_all":{"GB2-01":{"draws":108,"losses":519,"wins":839},"GB2-02":{"draws":901,"losses":191,"wins":272},"GB2-03":{"draws":158,"losses":473,"wins":773},"GB2-04":{"draws":756,"losses":167,"wins":487},"GB2-05":{"draws":0,"losses":676,"wins":836},"GB2-06":{"draws":70,"losses":462,"wins":908},"GB2-07":{"draws":0,"losses":521,"wins":957},"GB2-08":{"draws":626,"losses":797,"wins":91}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":289,"wins":199},"GB2-02":{"draws":216,"losses":36,"wins":202},"GB2-03":{"draws":6,"losses":76,"wins":386},"GB2-04":{"draws":152,"losses":28,"wins":290},"GB2-05":{"draws":0,"losses":111,"wins":393},"GB2-06":{"draws":31,"losses":74,"wins":377},"GB2-07":{"draws":0,"losses":132,"wins":360},"GB2-08":{"draws":248,"losses":200,"wins":56}},"medium":{"GB2-01":{"draws":6,"losses":109,"wins":373},"GB2-02":{"draws":334,"losses":58,"wins":62},"GB2-03":{"draws":52,"losses":187,"wins":229},"GB2-04":{"draws":273,"losses":76,"wins":121},"GB2-05":{"draws":0,"losses":306,"wins":198},"GB2-06":{"draws":26,"losses":212,"wins":240},"GB2-07":{"draws":0,"losses":209,"wins":283},"GB2-08":{"draws":149,"losses":342,"wins":15}},"none":{"GB2-01":{"draws":100,"losses":121,"wins":267},"GB2-02":{"draws":351,"losses":97,"wins":8},"GB2-03":{"draws":100,"losses":210,"wins":158},"GB2-04":{"draws":331,"losses":63,"wins":76},"GB2-05":{"draws":0,"losses":259,"wins":245},"GB2-06":{"draws":13,"losses":176,"wins":291},"GB2-07":{"draws":0,"losses":180,"wins":314},"GB2-08":{"draws":229,"losses":255,"wins":20}}},"per_game_raw_elo_all":{"GB2-01":1598.8540911064272,"GB2-02":1513.1523025517902,"GB2-03":1595.1781316029503,"GB2-04":1587.6452254453498,"GB2-05":1548.3428146049093,"GB2-06":1724.0155364988505,"GB2-07":1661.8757080390653,"GB2-08":1171.0351721020659},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1393.7049624397391,"GB2-02":1637.3805918429834,"GB2-03":1870.366062927206,"GB2-04":1740.3169604226014,"GB2-05":1891.1459799177812,"GB2-06":1998.0026644166392,"GB2-07":1780.079304823688,"GB2-08":1272.7122563129951},"medium":{"GB2-01":1771.3406876209974,"GB2-02":1490.112662405864,"GB2-03":1499.7014499505458,"GB2-04":1524.552423068308,"GB2-05":1316.8297742848986,"GB2-06":1515.09740720941,"GB2-07":1562.5425408737474,"GB2-08":1065.6965344214736},"none":{"GB2-01":1631.5166232585452,"GB2-02":1411.963653406523,"GB2-03":1415.466881931099,"GB2-04":1498.0662928451404,"GB2-05":1437.052689612048,"GB2-06":1658.9465378705024,"GB2-07":1643.0052784197605,"GB2-08":1174.6967255717286}},"per_game_tracks":{"highest":{"GB2-01":41.91317461108321,"GB2-02":69.36515869151873,"GB2-03":84.99804643586837,"GB2-04":78.65053228769119,"GB2-05":78.82765608007782,"GB2-06":82.32401670554906,"GB2-07":73.82781907037081,"GB2-08":37.46697828534474},"medium":{"GB2-01":77.89450722012026,"GB2-02":51.98935472492092,"GB2-03":57.43081529166134,"GB2-04":55.94676910470221,"GB2-05":40.237293513176795,"GB2-06":55.56604691445873,"GB2-07":58.902342041552615,"GB2-08":18.846537610943624},"none":{"GB2-01":66.1543174318372,"GB2-02":41.87423936873439,"GB2-03":48.08524299385004,"GB2-04":52.590570879919696,"GB2-05":49.78270260396789,"GB2-06":64.20400359778829,"GB2-07":64.82472598256784,"GB2-08":28.07762701903561}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:20:22Z","reasoning":{"highest":68.42167277093799,"medium":52.10170830269207,"none":51.94917873471262},"reasoning_agg":{"highest":{"max":84.99804643586837,"mean":68.42167277093799,"min":37.46697828534474},"medium":{"max":77.89450722012026,"mean":52.10170830269207,"min":18.846537610943624},"none":{"max":66.1543174318372,"mean":51.94917873471262,"min":28.07762701903561}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":16.47249403622537}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:f405e8f22efe7e39","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":0.029847899999999997}},"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":0.0298479},"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":0.119209325}},"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":0.195345875},"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":57.19617954192179,"highest":59.33670118513738,"medium":63.76835178455808,"none":48.48348565606992},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":58.08458251815576,"score":58.08458251815576},"GB2-02":{"attempts":3,"playable":52.53012717029833,"score":52.53012717029833},"GB2-03":{"attempts":3,"playable":72.77021905742893,"score":72.77021905742893},"GB2-04":{"attempts":3,"playable":72.34028826494166,"score":72.34028826494166},"GB2-05":{"attempts":3,"playable":53.3495346058801,"score":53.3495346058801},"GB2-06":{"attempts":3,"playable":47.92078013464894,"score":47.92078013464894},"GB2-07":{"attempts":3,"playable":72.4936153658734,"score":72.4936153658734},"GB2-08":{"attempts":3,"playable":28.080289218147215,"score":28.080289218147215}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":66.7292730216545,"score":66.7292730216545},"GB2-02":{"attempts":1,"playable":66.23430450617803,"score":66.23430450617803},"GB2-03":{"attempts":1,"playable":79.05784308889132,"score":79.05784308889132},"GB2-04":{"attempts":1,"playable":78.5143031366937,"score":78.5143031366937},"GB2-05":{"attempts":1,"playable":74.35106748710521,"score":74.35106748710521},"GB2-06":{"attempts":1,"playable":18.205818506192156,"score":18.205818506192156},"GB2-07":{"attempts":1,"playable":69.53556686394579,"score":69.53556686394579},"GB2-08":{"attempts":1,"playable":22.065432870438386,"score":22.065432870438386}},"medium":{"GB2-01":{"attempts":1,"playable":70.96810851553548,"score":70.96810851553548},"GB2-02":{"attempts":1,"playable":46.38149299444741,"score":46.38149299444741},"GB2-03":{"attempts":1,"playable":80.92621173534958,"score":80.92621173534958},"GB2-04":{"attempts":1,"playable":74.08689977296869,"score":74.08689977296869},"GB2-05":{"attempts":1,"playable":48.23645162559752,"score":48.23645162559752},"GB2-06":{"attempts":1,"playable":81.22988835631688,"score":81.22988835631688},"GB2-07":{"attempts":1,"playable":75.77930099562408,"score":75.77930099562408},"GB2-08":{"attempts":1,"playable":32.53846028062489,"score":32.53846028062489}},"none":{"GB2-01":{"attempts":1,"playable":36.55636601727729,"score":36.55636601727729},"GB2-02":{"attempts":1,"playable":44.97458401026954,"score":44.97458401026954},"GB2-03":{"attempts":1,"playable":58.32660234804589,"score":58.32660234804589},"GB2-04":{"attempts":1,"playable":64.41966188516258,"score":64.41966188516258},"GB2-05":{"attempts":1,"playable":37.461084704937576,"score":37.461084704937576},"GB2-06":{"attempts":1,"playable":44.326633541437786,"score":44.326633541437786},"GB2-07":{"attempts":1,"playable":72.16597823805031,"score":72.16597823805031},"GB2-08":{"attempts":1,"playable":29.636974503378365,"score":29.636974503378365}}},"id":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:30:37Z","match_totals_all":{"draws":2229,"losses":4048,"wins":5338},"match_totals_tracks":{"highest":{"draws":441,"losses":1419,"wins":2018},"medium":{"draws":799,"losses":1059,"wins":2010},"none":{"draws":989,"losses":1570,"wins":1310}},"model_slug":"z-ai-glm-5-3-flash","overall":{"max":81.22988835631688,"mean":57.19617954192179,"min":18.205818506192156},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":66.7292730216545,"GB2-02":66.23430450617803,"GB2-03":79.05784308889132,"GB2-04":78.5143031366937,"GB2-05":74.35106748710521,"GB2-06":18.205818506192156,"GB2-07":69.53556686394579,"GB2-08":22.065432870438386},"per_game_all":{"GB2-01":58.08458251815576,"GB2-02":52.53012717029833,"GB2-03":72.77021905742893,"GB2-04":72.34028826494166,"GB2-05":53.3495346058801,"GB2-06":47.92078013464894,"GB2-07":72.4936153658734,"GB2-08":28.080289218147215},"per_game_match_totals_all":{"GB2-01":{"draws":238,"losses":515,"wins":715},"GB2-02":{"draws":921,"losses":208,"wins":239},"GB2-03":{"draws":136,"losses":353,"wins":917},"GB2-04":{"draws":472,"losses":169,"wins":773},"GB2-05":{"draws":0,"losses":722,"wins":798},"GB2-06":{"draws":82,"losses":737,"wins":616},"GB2-07":{"draws":0,"losses":413,"wins":1065},"GB2-08":{"draws":380,"losses":931,"wins":215}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":168,"wins":317},"GB2-02":{"draws":238,"losses":42,"wins":176},"GB2-03":{"draws":8,"losses":104,"wins":356},"GB2-04":{"draws":130,"losses":40,"wins":302},"GB2-05":{"draws":0,"losses":134,"wins":374},"GB2-06":{"draws":16,"losses":394,"wins":68},"GB2-07":{"draws":0,"losses":153,"wins":341},"GB2-08":{"draws":44,"losses":384,"wins":84}},"medium":{"GB2-01":{"draws":20,"losses":138,"wins":330},"GB2-02":{"draws":335,"losses":83,"wins":38},"GB2-03":{"draws":22,"losses":90,"wins":358},"GB2-04":{"draws":149,"losses":53,"wins":270},"GB2-05":{"draws":0,"losses":268,"wins":238},"GB2-06":{"draws":31,"losses":78,"wins":369},"GB2-07":{"draws":0,"losses":120,"wins":372},"GB2-08":{"draws":242,"losses":229,"wins":35}},"none":{"GB2-01":{"draws":213,"losses":209,"wins":68},"GB2-02":{"draws":348,"losses":83,"wins":25},"GB2-03":{"draws":106,"losses":159,"wins":203},"GB2-04":{"draws":193,"losses":76,"wins":201},"GB2-05":{"draws":0,"losses":320,"wins":186},"GB2-06":{"draws":35,"losses":265,"wins":179},"GB2-07":{"draws":0,"losses":140,"wins":352},"GB2-08":{"draws":94,"losses":318,"wins":96}}},"per_game_raw_elo_all":{"GB2-01":1554.602877250161,"GB2-02":1496.9472139002446,"GB2-03":1684.5375312991566,"GB2-04":1673.90369495748,"GB2-05":1497.52559994537,"GB2-06":1417.2691781651602,"GB2-07":1759.4254956651573,"GB2-08":1173.2226523329023},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1637.6874246058887,"GB2-02":1608.1051986982347,"GB2-03":1756.716279415776,"GB2-04":1738.6413450781197,"GB2-05":1794.4019840443502,"GB2-06":936.5886673634113,"GB2-07":1711.7514933907928,"GB2-08":1106.2942482209166},"medium":{"GB2-01":1684.9085164279331,"GB2-02":1446.7864246444713,"GB2-03":1788.7236791862233,"GB2-04":1688.0042300728035,"GB2-05":1417.8200278416134,"GB2-06":1975.5423139146503,"GB2-07":1813.7059767820188,"GB2-08":1221.9360473536756},"none":{"GB2-01":1341.2126907166612,"GB2-02":1435.9500183580271,"GB2-03":1508.172635295471,"GB2-04":1595.0655097215167,"GB2-05":1280.354787950146,"GB2-06":1339.6765532174186,"GB2-07":1752.8190168226597,"GB2-08":1191.4376614241146}},"per_game_tracks":{"highest":{"GB2-01":66.7292730216545,"GB2-02":66.23430450617803,"GB2-03":79.05784308889132,"GB2-04":78.5143031366937,"GB2-05":74.35106748710521,"GB2-06":18.205818506192156,"GB2-07":69.53556686394579,"GB2-08":22.065432870438386},"medium":{"GB2-01":70.96810851553548,"GB2-02":46.38149299444741,"GB2-03":80.92621173534958,"GB2-04":74.08689977296869,"GB2-05":48.23645162559752,"GB2-06":81.22988835631688,"GB2-07":75.77930099562408,"GB2-08":32.53846028062489},"none":{"GB2-01":36.55636601727729,"GB2-02":44.97458401026954,"GB2-03":58.32660234804589,"GB2-04":64.41966188516258,"GB2-05":37.461084704937576,"GB2-06":44.326633541437786,"GB2-07":72.16597823805031,"GB2-08":29.636974503378365}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:35:12Z","reasoning":{"highest":59.33670118513738,"medium":63.76835178455808,"none":48.48348565606992},"reasoning_agg":{"highest":{"max":79.05784308889132,"mean":59.33670118513738,"min":18.205818506192156},"medium":{"max":81.22988835631688,"mean":63.76835178455808,"min":32.53846028062489},"none":{"max":72.16597823805031,"mean":48.48348565606992,"min":29.636974503378365}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":15.284866128488162}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-haiku-5-5:2089f7b89ac77937","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.04782545,"median":0.046146,"min":0.0294405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.38260360000000004},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.0955808},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.0249632}},"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":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.09558079999999998},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.024963200000000005},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.04782545,"median":0.046146,"min":0.0294405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.3826036}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.020964483333333336,"median":0.012623549999999999,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":0.5031475999999999},"codegen_output_tokens":{"attempt_count":28,"output_max":128000,"output_mean":38910.541666666664,"output_min":1643,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":128000,"output_mean":92691.0,"output_min":56566,"run_count":8},"medium":{"attempt_count":9,"output_max":32619,"output_mean":20970.375,"output_min":8448,"run_count":8},"none":{"attempt_count":10,"output_max":6434,"output_mean":3070.25,"output_min":1643,"run_count":8}},"display_name":"Claude Haiku 5.5","economics":{"all":56.47029395276496,"highest":74.66563005731503,"medium":57.354246374036414,"none":39.35385222413454},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn","max_tokens"],"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,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":933853,"total_reasoning_output_tokens":827092,"total_visible_output_tokens":106761,"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":"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":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":7,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03"],"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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":40.91743327014804,"score":40.91743327014804},"GB2-02":{"attempts":3,"playable":58.13070871224162,"score":58.13070871224162},"GB2-03":{"attempts":2,"playable":55.224013089254285,"score":55.224013089254285},"GB2-04":{"attempts":3,"playable":63.07128804619544,"score":63.07128804619544},"GB2-05":{"attempts":3,"playable":53.66239808960675,"score":53.66239808960675},"GB2-06":{"attempts":3,"playable":69.7792093097869,"score":69.7792093097869},"GB2-07":{"attempts":3,"playable":58.53922227169718,"score":58.53922227169718},"GB2-08":{"attempts":3,"playable":51.191797969678795,"score":51.191797969678795}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.691412820710674,"score":41.691412820710674},"GB2-02":{"attempts":1,"playable":69.86016874894194,"score":69.86016874894194},"GB2-04":{"attempts":1,"playable":80.47357126905736,"score":80.47357126905736},"GB2-05":{"attempts":1,"playable":86.48403510872485,"score":86.48403510872485},"GB2-06":{"attempts":1,"playable":91.28160827480967,"score":91.28160827480967},"GB2-07":{"attempts":1,"playable":66.79348379872599,"score":66.79348379872599},"GB2-08":{"attempts":1,"playable":86.07513038023471,"score":86.07513038023471}},"medium":{"GB2-01":{"attempts":1,"playable":45.84042252444561,"score":45.84042252444561},"GB2-02":{"attempts":1,"playable":62.15816373622399,"score":62.15816373622399},"GB2-03":{"attempts":1,"playable":67.84541433024006,"score":67.84541433024006},"GB2-04":{"attempts":1,"playable":67.56079959291797,"score":67.56079959291797},"GB2-05":{"attempts":1,"playable":57.85322868739028,"score":57.85322868739028},"GB2-06":{"attempts":1,"playable":68.62681295742449,"score":68.62681295742449},"GB2-07":{"attempts":1,"playable":56.56825206086745,"score":56.56825206086745},"GB2-08":{"attempts":1,"playable":32.38087710278143,"score":32.38087710278143}},"none":{"GB2-01":{"attempts":1,"playable":35.22046446528783,"score":35.22046446528783},"GB2-02":{"attempts":1,"playable":42.37379365155894,"score":42.37379365155894},"GB2-03":{"attempts":1,"playable":42.602611848268516,"score":42.602611848268516},"GB2-04":{"attempts":1,"playable":41.179493276611,"score":41.179493276611},"GB2-05":{"attempts":1,"playable":16.649930472705122,"score":16.649930472705122},"GB2-06":{"attempts":1,"playable":49.42920669712659,"score":49.42920669712659},"GB2-07":{"attempts":1,"playable":52.2559309554981,"score":52.2559309554981},"GB2-08":{"attempts":1,"playable":35.11938642602025,"score":35.11938642602025}}},"id":"claude-haiku-5-5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:43:06Z","match_totals_all":{"draws":2533,"losses":3759,"wins":4822},"match_totals_tracks":{"highest":{"draws":384,"losses":701,"wins":2313},"medium":{"draws":926,"losses":1254,"wins":1678},"none":{"draws":1223,"losses":1804,"wins":831}},"model_slug":"claude-haiku-5-5","overall":{"max":91.28160827480967,"mean":57.12457621849533,"min":16.649930472705122},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":22,"overall_ranking_status":"partial","per_game":{"GB2-01":41.691412820710674,"GB2-02":69.86016874894194,"GB2-04":80.47357126905736,"GB2-05":86.48403510872485,"GB2-06":91.28160827480967,"GB2-07":66.79348379872599,"GB2-08":86.07513038023471},"per_game_all":{"GB2-01":40.91743327014804,"GB2-02":58.13070871224162,"GB2-04":63.07128804619544,"GB2-05":53.66239808960675,"GB2-06":69.7792093097869,"GB2-07":58.53922227169718,"GB2-08":51.191797969678795},"per_game_match_totals_all":{"GB2-01":{"draws":246,"losses":765,"wins":457},"GB2-02":{"draws":816,"losses":179,"wins":369},"GB2-03":{"draws":266,"losses":314,"wins":356},"GB2-04":{"draws":620,"losses":227,"wins":567},"GB2-05":{"draws":0,"losses":710,"wins":802},"GB2-06":{"draws":58,"losses":428,"wins":942},"GB2-07":{"draws":0,"losses":644,"wins":836},"GB2-08":{"draws":527,"losses":492,"wins":493}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":32,"losses":279,"wins":181},"GB2-02":{"draws":204,"losses":40,"wins":210},"GB2-04":{"draws":112,"losses":40,"wins":320},"GB2-05":{"draws":0,"losses":70,"wins":434},"GB2-06":{"draws":35,"losses":25,"wins":416},"GB2-07":{"draws":0,"losses":174,"wins":322},"GB2-08":{"draws":1,"losses":73,"wins":430}},"medium":{"GB2-01":{"draws":129,"losses":205,"wins":154},"GB2-02":{"draws":246,"losses":54,"wins":154},"GB2-03":{"draws":92,"losses":118,"wins":258},"GB2-04":{"draws":202,"losses":58,"wins":212},"GB2-05":{"draws":0,"losses":217,"wins":287},"GB2-06":{"draws":6,"losses":155,"wins":315},"GB2-07":{"draws":0,"losses":225,"wins":267},"GB2-08":{"draws":251,"losses":222,"wins":31}},"none":{"GB2-01":{"draws":85,"losses":281,"wins":122},"GB2-02":{"draws":366,"losses":85,"wins":5},"GB2-03":{"draws":174,"losses":196,"wins":98},"GB2-04":{"draws":306,"losses":129,"wins":35},"GB2-05":{"draws":0,"losses":423,"wins":81},"GB2-06":{"draws":17,"losses":248,"wins":211},"GB2-07":{"draws":0,"losses":245,"wins":247},"GB2-08":{"draws":275,"losses":197,"wins":32}}},"per_game_raw_elo_all":{"GB2-01":1383.5647563223386,"GB2-02":1543.448807328569,"GB2-04":1598.8397461332627,"GB2-05":1535.066051588504,"GB2-06":1790.2196472467356,"GB2-07":1560.0902930925702,"GB2-08":1497.3695760125302},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1391.5642407820305,"GB2-02":1642.1838063115058,"GB2-04":1763.5613524026144,"GB2-05":2118.3547953268994,"GB2-06":2215.5785483906707,"GB2-07":1671.1033371725075,"GB2-08":2023.2012755302644},"medium":{"GB2-01":1431.344142522965,"GB2-02":1572.3183108085125,"GB2-03":1606.1240800366863,"GB2-04":1623.3242961423205,"GB2-05":1539.2300456018659,"GB2-06":1736.8570265920512,"GB2-07":1532.086371053172,"GB2-08":1220.2964002454478},"none":{"GB2-01":1327.78588566202,"GB2-02":1415.8443048656884,"GB2-03":1367.7536275048908,"GB2-04":1409.6335898548534,"GB2-05":947.6133138367469,"GB2-06":1418.223366757485,"GB2-07":1477.0811710520309,"GB2-08":1248.6110522618787}},"per_game_tracks":{"highest":{"GB2-01":41.691412820710674,"GB2-02":69.86016874894194,"GB2-04":80.47357126905736,"GB2-05":86.48403510872485,"GB2-06":91.28160827480967,"GB2-07":66.79348379872599,"GB2-08":86.07513038023471},"medium":{"GB2-01":45.84042252444561,"GB2-02":62.15816373622399,"GB2-03":67.84541433024006,"GB2-04":67.56079959291797,"GB2-05":57.85322868739028,"GB2-06":68.62681295742449,"GB2-07":56.56825206086745,"GB2-08":32.38087710278143},"none":{"GB2-01":35.22046446528783,"GB2-02":42.37379365155894,"GB2-03":42.602611848268516,"GB2-04":41.179493276611,"GB2-05":16.649930472705122,"GB2-06":49.42920669712659,"GB2-07":52.2559309554981,"GB2-08":35.11938642602025}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":74.66563005731503,"medium":57.354246374036414,"none":39.35385222413454},"reasoning_agg":{"highest":{"max":91.28160827480967,"mean":74.66563005731503,"min":41.691412820710674},"medium":{"max":68.62681295742449,"mean":57.354246374036414,"min":32.38087710278143},"none":{"max":52.2559309554981,"mean":39.35385222413454,"min":16.649930472705122}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":35.311777833180486}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:f7e4cdb6be62da53","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"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":12.152240000000003},"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":0.4120425,"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":true,"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":true,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.2669949999999996},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"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":0.7687025000000002},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"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":true,"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":15.1879375},"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":59.131981128774065,"highest":72.36511928793769,"medium":55.912824456917264,"none":46.83186904752059},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":91.25561481237473,"score":91.25561481237473},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.370889673405536,"score":28.913926448937023},"GB2-03":{"attempts":3,"playable":39.95083711793172,"score":39.95083711793172},"GB2-04":{"attempts":3,"playable":43.12270802170519,"score":43.12270802170519},"GB2-05":{"attempts":3,"playable":73.04046581680237,"score":73.04046581680237},"GB2-06":{"attempts":3,"playable":74.38307041146776,"score":74.38307041146776},"GB2-07":{"attempts":3,"playable":47.18820045361448,"score":47.18820045361448},"GB2-08":{"attempts":3,"playable":44.98297126752229,"score":44.98297126752229}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":94.94848956543726,"score":94.94848956543726},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":43.86894425892641,"score":43.86894425892641},"GB2-04":{"attempts":1,"playable":57.14105750799816,"score":57.14105750799816},"GB2-05":{"attempts":1,"playable":86.23655592789169,"score":86.23655592789169},"GB2-06":{"attempts":1,"playable":80.93249672432434,"score":80.93249672432434},"GB2-07":{"attempts":1,"playable":77.31709500293043,"score":77.31709500293043},"GB2-08":{"attempts":1,"playable":66.11119602805552,"score":66.11119602805552}},"medium":{"GB2-01":{"attempts":1,"playable":97.80035057276528,"score":97.80035057276528},"GB2-02":{"attempts":1,"playable":47.038939368077656,"score":47.038939368077656},"GB2-03":{"attempts":1,"playable":43.585025320444764,"score":43.585025320444764},"GB2-04":{"attempts":1,"playable":33.1355721569011,"score":33.1355721569011},"GB2-05":{"attempts":1,"playable":71.67187371828939,"score":71.67187371828939},"GB2-06":{"attempts":1,"playable":78.34421905130597,"score":78.34421905130597},"GB2-07":{"attempts":1,"playable":35.39304916550397,"score":35.39304916550397},"GB2-08":{"attempts":1,"playable":40.333566302049995,"score":40.333566302049995}},"none":{"GB2-01":{"attempts":1,"playable":81.01800429892162,"score":81.01800429892162},"GB2-02":{"attempts":1,"playable":39.702839978733415,"score":39.702839978733415},"GB2-03":{"attempts":1,"playable":32.398541774423975,"score":32.398541774423975},"GB2-04":{"attempts":1,"playable":39.09149440021632,"score":39.09149440021632},"GB2-05":{"attempts":1,"playable":61.21296780422602,"score":61.21296780422602},"GB2-06":{"attempts":1,"playable":63.87249545877298,"score":63.87249545877298},"GB2-07":{"attempts":1,"playable":28.85445719240903,"score":28.85445719240903},"GB2-08":{"attempts":1,"playable":28.50415147246137,"score":28.50415147246137}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-10-22T10:20:30Z","match_totals_all":{"draws":2540,"losses":3580,"wins":5016},"match_totals_tracks":{"highest":{"draws":480,"losses":735,"wins":2195},"medium":{"draws":1101,"losses":1204,"wins":1559},"none":{"draws":959,"losses":1641,"wins":1262}},"model_slug":"gpt-5-4","overall":{"max":97.80035057276528,"mean":55.35472429379445,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":23,"overall_ranking_status":"ranked","per_game":{"GB2-01":94.94848956543726,"GB2-03":43.86894425892641,"GB2-04":57.14105750799816,"GB2-05":86.23655592789169,"GB2-06":80.93249672432434,"GB2-07":77.31709500293043,"GB2-08":66.11119602805552},"per_game_all":{"GB2-01":91.25561481237473,"GB2-03":39.95083711793172,"GB2-04":43.12270802170519,"GB2-05":73.04046581680237,"GB2-06":74.38307041146776,"GB2-07":47.18820045361448,"GB2-08":44.98297126752229},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":104,"wins":1295},"GB2-02":{"draws":690,"losses":181,"wins":39},"GB2-03":{"draws":509,"losses":636,"wins":261},"GB2-04":{"draws":782,"losses":426,"wins":202},"GB2-05":{"draws":0,"losses":419,"wins":1097},"GB2-06":{"draws":74,"losses":351,"wins":1009},"GB2-07":{"draws":0,"losses":810,"wins":668},"GB2-08":{"draws":420,"losses":653,"wins":445}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":20,"wins":455},"GB2-03":{"draws":137,"losses":211,"wins":122},"GB2-04":{"draws":250,"losses":82,"wins":138},"GB2-05":{"draws":0,"losses":71,"wins":433},"GB2-06":{"draws":33,"losses":78,"wins":367},"GB2-07":{"draws":0,"losses":114,"wins":380},"GB2-08":{"draws":47,"losses":159,"wins":300}},"medium":{"GB2-01":{"draws":6,"losses":7,"wins":475},"GB2-02":{"draws":352,"losses":71,"wins":33},"GB2-03":{"draws":211,"losses":174,"wins":83},"GB2-04":{"draws":248,"losses":195,"wins":27},"GB2-05":{"draws":0,"losses":147,"wins":359},"GB2-06":{"draws":29,"losses":95,"wins":354},"GB2-07":{"draws":0,"losses":332,"wins":160},"GB2-08":{"draws":255,"losses":183,"wins":68}},"none":{"GB2-01":{"draws":46,"losses":77,"wins":365},"GB2-02":{"draws":338,"losses":110,"wins":6},"GB2-03":{"draws":161,"losses":251,"wins":56},"GB2-04":{"draws":284,"losses":149,"wins":37},"GB2-05":{"draws":0,"losses":201,"wins":305},"GB2-06":{"draws":12,"losses":178,"wins":288},"GB2-07":{"draws":0,"losses":364,"wins":128},"GB2-08":{"draws":118,"losses":311,"wins":77}}},"per_game_raw_elo_all":{"GB2-01":2095.9854439172236,"GB2-03":1343.9951062785094,"GB2-04":1424.0455390306026,"GB2-05":1812.6753574034346,"GB2-06":1846.9737079352572,"GB2-07":1428.75244038783,"GB2-08":1366.184172258434},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2147.1105181962453,"GB2-03":1378.7576185624591,"GB2-04":1534.1248225880515,"GB2-05":2109.3912630643003,"GB2-06":1969.5143880481346,"GB2-07":1841.6940012179425,"GB2-08":1617.069717609239},"medium":{"GB2-01":2324.7522532635717,"GB2-02":1451.8476118762812,"GB2-03":1376.2912226763003,"GB2-04":1344.8037085834465,"GB2-05":1744.5814655703516,"GB2-06":1918.1807223945689,"GB2-07":1265.8604358113262,"GB2-08":1302.1770552420287},"none":{"GB2-01":1816.0935602918548,"GB2-02":1394.9895853567268,"GB2-03":1276.9364775967688,"GB2-04":1393.2080859203104,"GB2-05":1584.0533435756522,"GB2-06":1653.226013363068,"GB2-07":1178.7028841342208,"GB2-08":1179.3057439240345}},"per_game_tracks":{"highest":{"GB2-01":94.94848956543726,"GB2-03":43.86894425892641,"GB2-04":57.14105750799816,"GB2-05":86.23655592789169,"GB2-06":80.93249672432434,"GB2-07":77.31709500293043,"GB2-08":66.11119602805552},"medium":{"GB2-01":97.80035057276528,"GB2-02":47.038939368077656,"GB2-03":43.585025320444764,"GB2-04":33.1355721569011,"GB2-05":71.67187371828939,"GB2-06":78.34421905130597,"GB2-07":35.39304916550397,"GB2-08":40.333566302049995},"none":{"GB2-01":81.01800429892162,"GB2-02":39.702839978733415,"GB2-03":32.398541774423975,"GB2-04":39.09149440021632,"GB2-05":61.21296780422602,"GB2-06":63.87249545877298,"GB2-07":28.85445719240903,"GB2-08":28.50415147246137}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:35:00Z","reasoning":{"highest":63.31947937694548,"medium":55.912824456917264,"none":46.83186904752059},"reasoning_agg":{"highest":{"max":94.94848956543726,"mean":63.31947937694548,"min":0.0},"medium":{"max":97.80035057276528,"mean":55.912824456917264,"min":33.1355721569011},"none":{"max":81.01800429892162,"mean":46.83186904752059,"min":28.50415147246137}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.48761032942489}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:3fd780758dcde54e","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":0.518502,"mean":0.398628,"median":0.380653,"min":0.332482,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.189024},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.30508599999999997,"mean":0.10921525,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":10,"run_count":8,"total":0.8737219999999999},"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":0.30508599999999997,"mean":0.10921525,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":10,"run_count":8,"total":0.873722},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.212408,"mean":0.12122175,"median":0.11379500000000001,"min":0.08249,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.9697739999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.398628,"median":0.380653,"min":0.332482,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.1890240000000003}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.20968833333333334,"median":0.124697,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":19,"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":30,"run_count":24,"total":5.03252},"codegen_latency_ms":{"attempt_count":30,"max_ms":1906796,"mean_ms":726982.5833333334,"min_ms":135091,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1906796,"mean_ms":1528927.125,"min_ms":1229561,"run_count":8},"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":30,"output_max":78760,"output_mean":31343.75,"output_min":6298,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":78760,"output_mean":62794.5,"output_min":52930,"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":55.146410956084075,"highest":70.34534534852304,"medium":45.09904212901522,"none":49.99484539071397},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[131072],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":31,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[131072],"total_output_tokens":752250,"total_reasoning_output_tokens":630868,"total_visible_output_tokens":121382,"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":"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":"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":48.38473029653963,"score":48.38473029653963},"GB2-02":{"attempts":3,"playable":46.70463743324492,"score":46.70463743324492},"GB2-03":{"attempts":3,"playable":61.121801873171854,"score":61.121801873171854},"GB2-04":{"attempts":3,"playable":56.54321352920386,"score":56.54321352920386},"GB2-05":{"attempts":3,"playable":65.23392051808041,"score":65.23392051808041},"GB2-06":{"attempts":3,"playable":68.75293676569692,"score":68.75293676569692},"GB2-07":{"attempts":3,"playable":51.30685529818887,"score":51.30685529818887},"GB2-08":{"attempts":3,"playable":43.12319193454618,"score":43.12319193454618}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":77.1629715072712,"score":77.1629715072712},"GB2-02":{"attempts":1,"playable":49.46759260094671,"score":49.46759260094671},"GB2-03":{"attempts":1,"playable":70.87076231238827,"score":70.87076231238827},"GB2-04":{"attempts":1,"playable":85.58440716524503,"score":85.58440716524503},"GB2-05":{"attempts":1,"playable":92.36380495923693,"score":92.36380495923693},"GB2-06":{"attempts":1,"playable":64.63105937212245,"score":64.63105937212245},"GB2-07":{"attempts":1,"playable":76.82203505652194,"score":76.82203505652194},"GB2-08":{"attempts":1,"playable":45.86012981445182,"score":45.86012981445182}},"medium":{"GB2-01":{"attempts":1,"playable":26.375940375157036,"score":26.375940375157036},"GB2-02":{"attempts":1,"playable":48.52562181430719,"score":48.52562181430719},"GB2-03":{"attempts":1,"playable":56.66148123082295,"score":56.66148123082295},"GB2-04":{"attempts":1,"playable":46.04477789175597,"score":46.04477789175597},"GB2-05":{"attempts":1,"playable":43.17138835224428,"score":43.17138835224428},"GB2-06":{"attempts":1,"playable":60.59210817918699,"score":60.59210817918699},"GB2-07":{"attempts":1,"playable":36.898353945249326,"score":36.898353945249326},"GB2-08":{"attempts":1,"playable":42.52266524339802,"score":42.52266524339802}},"none":{"GB2-01":{"attempts":1,"playable":41.615279007190644,"score":41.615279007190644},"GB2-02":{"attempts":1,"playable":42.12069788448083,"score":42.12069788448083},"GB2-03":{"attempts":1,"playable":55.83316207630434,"score":55.83316207630434},"GB2-04":{"attempts":1,"playable":38.00045553061059,"score":38.00045553061059},"GB2-05":{"attempts":1,"playable":60.166568242760036,"score":60.166568242760036},"GB2-06":{"attempts":1,"playable":81.0356427457813,"score":81.0356427457813},"GB2-07":{"attempts":1,"playable":40.200176892795355,"score":40.200176892795355},"GB2-08":{"attempts":1,"playable":40.98678074578867,"score":40.98678074578867}}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-10-22T10:32:29Z","match_totals_all":{"draws":3037,"losses":3872,"wins":4679},"match_totals_tracks":{"highest":{"draws":781,"losses":801,"wins":2276},"medium":{"draws":1029,"losses":1698,"wins":1145},"none":{"draws":1227,"losses":1373,"wins":1258}},"model_slug":"qwen-qwen3-8-max-0902","overall":{"max":92.36380495923693,"mean":55.146410956084075,"min":26.375940375157036},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.1629715072712,"GB2-02":49.46759260094671,"GB2-03":70.87076231238827,"GB2-04":85.58440716524503,"GB2-05":92.36380495923693,"GB2-06":64.63105937212245,"GB2-07":76.82203505652194,"GB2-08":45.86012981445182},"per_game_all":{"GB2-01":48.38473029653963,"GB2-02":46.70463743324492,"GB2-03":61.121801873171854,"GB2-04":56.54321352920386,"GB2-05":65.23392051808041,"GB2-06":68.75293676569692,"GB2-07":51.30685529818887,"GB2-08":43.12319193454618},"per_game_match_totals_all":{"GB2-01":{"draws":292,"losses":632,"wins":542},"GB2-02":{"draws":996,"losses":243,"wins":123},"GB2-03":{"draws":262,"losses":458,"wins":684},"GB2-04":{"draws":669,"losses":291,"wins":452},"GB2-05":{"draws":0,"losses":534,"wins":978},"GB2-06":{"draws":97,"losses":426,"wins":909},"GB2-07":{"draws":0,"losses":758,"wins":728},"GB2-08":{"draws":721,"losses":530,"wins":263}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":116,"wins":370},"GB2-02":{"draws":315,"losses":77,"wins":62},"GB2-03":{"draws":85,"losses":108,"wins":275},"GB2-04":{"draws":82,"losses":30,"wins":360},"GB2-05":{"draws":0,"losses":39,"wins":465},"GB2-06":{"draws":48,"losses":155,"wins":273},"GB2-07":{"draws":0,"losses":118,"wins":374},"GB2-08":{"draws":249,"losses":158,"wins":97}},"medium":{"GB2-01":{"draws":89,"losses":325,"wins":76},"GB2-02":{"draws":338,"losses":70,"wins":46},"GB2-03":{"draws":89,"losses":173,"wins":206},"GB2-04":{"draws":299,"losses":110,"wins":61},"GB2-05":{"draws":0,"losses":290,"wins":214},"GB2-06":{"draws":16,"losses":194,"wins":268},"GB2-07":{"draws":0,"losses":334,"wins":168},"GB2-08":{"draws":198,"losses":202,"wins":106}},"none":{"GB2-01":{"draws":201,"losses":191,"wins":96},"GB2-02":{"draws":343,"losses":96,"wins":15},"GB2-03":{"draws":88,"losses":177,"wins":203},"GB2-04":{"draws":288,"losses":151,"wins":31},"GB2-05":{"draws":0,"losses":205,"wins":299},"GB2-06":{"draws":33,"losses":77,"wins":368},"GB2-07":{"draws":0,"losses":306,"wins":186},"GB2-08":{"draws":274,"losses":170,"wins":60}}},"per_game_raw_elo_all":{"GB2-01":1461.7677706704583,"GB2-02":1449.2477550387687,"GB2-03":1539.656143070889,"GB2-04":1557.059614792135,"GB2-05":1765.4097273605057,"GB2-06":1745.152540790892,"GB2-07":1481.5013797351155,"GB2-08":1331.29303844661},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1761.4817952844433,"GB2-02":1470.5656502506258,"GB2-03":1641.655494273779,"GB2-04":1839.2731498614648,"GB2-05":2371.9714335995486,"GB2-06":1666.3405705043876,"GB2-07":1832.5232872275797,"GB2-08":1360.0867871228565},"medium":{"GB2-01":1232.9927081160622,"GB2-02":1463.2984541479857,"GB2-03":1492.4989906931835,"GB2-04":1447.369262653338,"GB2-05":1354.3892687668745,"GB2-06":1597.5154337186923,"GB2-07":1285.14710940723,"GB2-08":1324.8685051074824},"none":{"GB2-01":1390.8288086108696,"GB2-02":1413.8791607176945,"GB2-03":1484.8139442457043,"GB2-04":1384.536431861603,"GB2-05":1569.8684797150943,"GB2-06":1971.6016181495959,"GB2-07":1326.8337425705367,"GB2-08":1308.9238231094903}},"per_game_tracks":{"highest":{"GB2-01":77.1629715072712,"GB2-02":49.46759260094671,"GB2-03":70.87076231238827,"GB2-04":85.58440716524503,"GB2-05":92.36380495923693,"GB2-06":64.63105937212245,"GB2-07":76.82203505652194,"GB2-08":45.86012981445182},"medium":{"GB2-01":26.375940375157036,"GB2-02":48.52562181430719,"GB2-03":56.66148123082295,"GB2-04":46.04477789175597,"GB2-05":43.17138835224428,"GB2-06":60.59210817918699,"GB2-07":36.898353945249326,"GB2-08":42.52266524339802},"none":{"GB2-01":41.615279007190644,"GB2-02":42.12069788448083,"GB2-03":55.83316207630434,"GB2-04":38.00045553061059,"GB2-05":60.166568242760036,"GB2-06":81.0356427457813,"GB2-07":40.200176892795355,"GB2-08":40.98678074578867}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:22:34Z","reasoning":{"highest":70.34534534852304,"medium":45.09904212901522,"none":49.99484539071397},"reasoning_agg":{"highest":{"max":92.36380495923693,"mean":70.34534534852304,"min":45.86012981445182},"medium":{"max":60.59210817918699,"mean":45.09904212901522,"min":26.375940375157036},"none":{"max":81.0356427457813,"mean":49.99484539071397,"min":38.00045553061059}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.246303219507823}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:2290a484b4fb6583","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"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":true,"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":true,"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":true,"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":0.818811367247394},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"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":1.1978497759330728},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819533}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"cost_is_complete":true,"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":5.4708879999999995},"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":54.46989900518675,"highest":68.97443467885563,"medium":43.269191163074694,"none":51.16607117362992},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":49.54400123721408,"score":49.54400123721408},"GB2-02":{"attempts":3,"playable":48.78426970863842,"score":48.78426970863842},"GB2-03":{"attempts":3,"playable":58.78046601490456,"score":58.78046601490456},"GB2-04":{"attempts":3,"playable":44.163554754006725,"score":44.163554754006725},"GB2-05":{"attempts":3,"playable":51.71323521747811,"score":51.71323521747811},"GB2-06":{"attempts":3,"playable":63.26635371627896,"score":63.26635371627896},"GB2-07":{"attempts":3,"playable":48.51452643818741,"score":48.51452643818741},"GB2-08":{"attempts":3,"playable":70.9927849547857,"score":70.9927849547857}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":58.76446451614738,"score":58.76446451614738},"GB2-02":{"attempts":1,"playable":53.751310280249875,"score":53.751310280249875},"GB2-03":{"attempts":1,"playable":82.39268647125628,"score":82.39268647125628},"GB2-04":{"attempts":1,"playable":46.87481251791618,"score":46.87481251791618},"GB2-05":{"attempts":1,"playable":69.04696021082755,"score":69.04696021082755},"GB2-06":{"attempts":1,"playable":80.45329818413593,"score":80.45329818413593},"GB2-07":{"attempts":1,"playable":69.57416332370565,"score":69.57416332370565},"GB2-08":{"attempts":1,"playable":90.93778192660614,"score":90.93778192660614}},"medium":{"GB2-01":{"attempts":1,"playable":53.02134449829303,"score":53.02134449829303},"GB2-02":{"attempts":1,"playable":43.078840568268646,"score":43.078840568268646},"GB2-03":{"attempts":1,"playable":43.49573513680418,"score":43.49573513680418},"GB2-04":{"attempts":1,"playable":39.67156397374453,"score":39.67156397374453},"GB2-05":{"attempts":1,"playable":50.746453687481264,"score":50.746453687481264},"GB2-06":{"attempts":1,"playable":45.75696058015957,"score":45.75696058015957},"GB2-07":{"attempts":1,"playable":31.910779413092534,"score":31.910779413092534},"GB2-08":{"attempts":1,"playable":38.47185144675381,"score":38.47185144675381}},"none":{"GB2-01":{"attempts":1,"playable":36.84619469720185,"score":36.84619469720185},"GB2-02":{"attempts":1,"playable":49.522658277396744,"score":49.522658277396744},"GB2-03":{"attempts":1,"playable":50.45297643665323,"score":50.45297643665323},"GB2-04":{"attempts":1,"playable":45.94428777035945,"score":45.94428777035945},"GB2-05":{"attempts":1,"playable":35.3462917541255,"score":35.3462917541255},"GB2-06":{"attempts":1,"playable":63.588802384541374,"score":63.588802384541374},"GB2-07":{"attempts":1,"playable":44.05863657776404,"score":44.05863657776404},"GB2-08":{"attempts":1,"playable":83.56872149099716,"score":83.56872149099716}}},"id":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-10-22T10:11:51Z","match_totals_all":{"draws":3058,"losses":3931,"wins":4607},"match_totals_tracks":{"highest":{"draws":812,"losses":833,"wins":2223},"medium":{"draws":1302,"losses":1621,"wins":941},"none":{"draws":944,"losses":1477,"wins":1443}},"model_slug":"qwen-qwen3-8-2-4t-a95b","overall":{"max":90.93778192660614,"mean":54.469899005186754,"min":31.910779413092534},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.76446451614738,"GB2-02":53.751310280249875,"GB2-03":82.39268647125628,"GB2-04":46.87481251791618,"GB2-05":69.04696021082755,"GB2-06":80.45329818413593,"GB2-07":69.57416332370565,"GB2-08":90.93778192660614},"per_game_all":{"GB2-01":49.54400123721408,"GB2-02":48.78426970863842,"GB2-03":58.78046601490456,"GB2-04":44.163554754006725,"GB2-05":51.71323521747811,"GB2-06":63.26635371627896,"GB2-07":48.51452643818741,"GB2-08":70.9927849547857},"per_game_match_totals_all":{"GB2-01":{"draws":578,"losses":473,"wins":415},"GB2-02":{"draws":1009,"losses":215,"wins":142},"GB2-03":{"draws":221,"losses":506,"wins":677},"GB2-04":{"draws":894,"losses":358,"wins":158},"GB2-05":{"draws":0,"losses":749,"wins":767},"GB2-06":{"draws":112,"losses":504,"wins":820},"GB2-07":{"draws":0,"losses":788,"wins":690},"GB2-08":{"draws":244,"losses":338,"wins":938}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":148,"losses":136,"wins":206},"GB2-02":{"draws":322,"losses":56,"wins":78},"GB2-03":{"draws":13,"losses":84,"wins":371},"GB2-04":{"draws":284,"losses":114,"wins":72},"GB2-05":{"draws":0,"losses":164,"wins":342},"GB2-06":{"draws":44,"losses":78,"wins":358},"GB2-07":{"draws":0,"losses":154,"wins":338},"GB2-08":{"draws":1,"losses":47,"wins":458}},"medium":{"GB2-01":{"draws":247,"losses":114,"wins":127},"GB2-02":{"draws":344,"losses":94,"wins":18},"GB2-03":{"draws":155,"losses":202,"wins":111},"GB2-04":{"draws":279,"losses":150,"wins":41},"GB2-05":{"draws":0,"losses":254,"wins":250},"GB2-06":{"draws":36,"losses":258,"wins":184},"GB2-07":{"draws":0,"losses":346,"wins":146},"GB2-08":{"draws":241,"losses":203,"wins":64}},"none":{"GB2-01":{"draws":183,"losses":223,"wins":82},"GB2-02":{"draws":343,"losses":65,"wins":46},"GB2-03":{"draws":53,"losses":220,"wins":195},"GB2-04":{"draws":331,"losses":94,"wins":45},"GB2-05":{"draws":0,"losses":331,"wins":175},"GB2-06":{"draws":32,"losses":168,"wins":278},"GB2-07":{"draws":0,"losses":288,"wins":206},"GB2-08":{"draws":2,"losses":88,"wins":416}}},"per_game_raw_elo_all":{"GB2-01":1466.5731510092885,"GB2-02":1465.3975913720378,"GB2-03":1542.6037269200922,"GB2-04":1432.7197052291401,"GB2-05":1466.961462439652,"GB2-06":1656.5913463820068,"GB2-07":1435.8353940493132,"GB2-08":1803.7892807886813},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1555.753669744783,"GB2-02":1503.892740349281,"GB2-03":1816.0085012375143,"GB2-04":1453.7735714525668,"GB2-05":1700.0551712860058,"GB2-06":1959.8638417116795,"GB2-07":1712.3381100902002,"GB2-08":2168.7483923193695},"medium":{"GB2-01":1499.8614045644294,"GB2-02":1421.3091268215558,"GB2-03":1375.5155091038237,"GB2-04":1397.7918131446345,"GB2-05":1449.05214823763,"GB2-06":1361.5662900696855,"GB2-07":1220.2620738625205,"GB2-08":1283.0238924259772},"none":{"GB2-01":1344.104378718653,"GB2-02":1470.9909069452767,"GB2-03":1436.2871704189383,"GB2-04":1446.593731090219,"GB2-05":1251.77706779532,"GB2-06":1648.343907364655,"GB2-07":1374.9059981952187,"GB2-08":1959.5955576206968}},"per_game_tracks":{"highest":{"GB2-01":58.76446451614738,"GB2-02":53.751310280249875,"GB2-03":82.39268647125628,"GB2-04":46.87481251791618,"GB2-05":69.04696021082755,"GB2-06":80.45329818413593,"GB2-07":69.57416332370565,"GB2-08":90.93778192660614},"medium":{"GB2-01":53.02134449829303,"GB2-02":43.078840568268646,"GB2-03":43.49573513680418,"GB2-04":39.67156397374453,"GB2-05":50.746453687481264,"GB2-06":45.75696058015957,"GB2-07":31.910779413092534,"GB2-08":38.47185144675381},"none":{"GB2-01":36.84619469720185,"GB2-02":49.522658277396744,"GB2-03":50.45297643665323,"GB2-04":45.94428777035945,"GB2-05":35.3462917541255,"GB2-06":63.588802384541374,"GB2-07":44.05863657776404,"GB2-08":83.56872149099716}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:38:38Z","reasoning":{"highest":68.97443467885563,"medium":43.269191163074694,"none":51.16607117362992},"reasoning_agg":{"highest":{"max":90.93778192660614,"mean":68.97443467885563,"min":46.87481251791618},"medium":{"max":53.02134449829303,"mean":43.269191163074694,"min":31.910779413092534},"none":{"max":83.56872149099716,"mean":51.16607117362992,"min":35.3462917541255}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.705243515780936}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:06f1e8f7846998cc","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.0866157440000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.12751812499999998},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.09097980808333334,"median":0.1119999555,"min":0.009391185,"recorded_attempt_count":28,"run_count":24,"total":2.1835153940000005},"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":55.442065534874075,"highest":64.8515535362196,"medium":58.42512164081063,"none":44.81431521830357},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":51.511941621895545,"score":51.511941621895545},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":61.00971264475204,"score":40.673141763168026},"GB2-03":{"attempts":3,"playable":59.054008249839,"score":59.054008249839},"GB2-04":{"attempts":3,"playable":44.34189873206285,"score":44.34189873206285},"GB2-05":{"attempts":3,"playable":57.86932377621708,"score":57.86932377621708},"GB2-06":{"attempts":3,"playable":60.55897656603256,"score":60.55897656603256},"GB2-07":{"attempts":3,"playable":60.97946101436412,"score":60.97946101436412},"GB2-08":{"attempts":3,"playable":53.77884878370737,"score":53.77884878370737}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":54.99835897054302,"score":54.99835897054302},"GB2-02":{"attempts":1,"playable":78.81667076181145,"score":78.81667076181145},"GB2-03":{"attempts":1,"playable":72.22154454525618,"score":72.22154454525618},"GB2-04":{"attempts":1,"playable":56.39137544207722,"score":56.39137544207722},"GB2-05":{"attempts":1,"playable":70.54337743428914,"score":70.54337743428914},"GB2-06":{"attempts":1,"playable":81.35255441338644,"score":81.35255441338644},"GB2-07":{"attempts":1,"playable":67.88299829024487,"score":67.88299829024487},"GB2-08":{"attempts":1,"playable":36.60554843214846,"score":36.60554843214846}},"medium":{"GB2-01":{"attempts":1,"playable":53.13197885396289,"score":53.13197885396289},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":41.03661932716358,"score":41.03661932716358},"GB2-04":{"attempts":1,"playable":35.369660144689014,"score":35.369660144689014},"GB2-05":{"attempts":1,"playable":52.06533833220113,"score":52.06533833220113},"GB2-06":{"attempts":1,"playable":60.51971945527889,"score":60.51971945527889},"GB2-07":{"attempts":1,"playable":76.94678630003375,"score":76.94678630003375},"GB2-08":{"attempts":1,"playable":89.90574907234515,"score":89.90574907234515}},"none":{"GB2-01":{"attempts":1,"playable":46.40548704118071,"score":46.40548704118071},"GB2-02":{"attempts":1,"playable":43.20275452769263,"score":43.20275452769263},"GB2-03":{"attempts":1,"playable":63.90386087709725,"score":63.90386087709725},"GB2-04":{"attempts":1,"playable":41.26466060942233,"score":41.26466060942233},"GB2-05":{"attempts":1,"playable":50.999255562160975,"score":50.999255562160975},"GB2-06":{"attempts":1,"playable":39.80465582943237,"score":39.80465582943237},"GB2-07":{"attempts":1,"playable":38.10859845281373,"score":38.10859845281373},"GB2-08":{"attempts":1,"playable":34.82524884662852,"score":34.82524884662852}}},"id":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-10-22T10:49:56Z","match_totals_all":{"draws":2640,"losses":3783,"wins":4739},"match_totals_tracks":{"highest":{"draws":986,"losses":933,"wins":1953},"medium":{"draws":543,"losses":1190,"wins":1689},"none":{"draws":1111,"losses":1660,"wins":1097}},"model_slug":"tencent-hy4-preview","overall":{"max":89.90574907234515,"mean":53.59595006341082,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":54.99835897054302,"GB2-02":78.81667076181145,"GB2-03":72.22154454525618,"GB2-04":56.39137544207722,"GB2-05":70.54337743428914,"GB2-06":81.35255441338644,"GB2-07":67.88299829024487,"GB2-08":36.60554843214846},"per_game_all":{"GB2-01":51.511941621895545,"GB2-03":59.054008249839,"GB2-04":44.34189873206285,"GB2-05":57.86932377621708,"GB2-06":60.55897656603256,"GB2-07":60.97946101436412,"GB2-08":53.77884878370737},"per_game_match_totals_all":{"GB2-01":{"draws":347,"losses":560,"wins":561},"GB2-02":{"draws":499,"losses":118,"wins":301},"GB2-03":{"draws":389,"losses":428,"wins":587},"GB2-04":{"draws":806,"losses":403,"wins":205},"GB2-05":{"draws":0,"losses":653,"wins":863},"GB2-06":{"draws":50,"losses":572,"wins":812},"GB2-07":{"draws":0,"losses":601,"wins":881},"GB2-08":{"draws":549,"losses":448,"wins":529}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":237,"losses":109,"wins":142},"GB2-02":{"draws":125,"losses":38,"wins":295},"GB2-03":{"draws":44,"losses":122,"wins":302},"GB2-04":{"draws":249,"losses":88,"wins":135},"GB2-05":{"draws":0,"losses":153,"wins":353},"GB2-06":{"draws":19,"losses":82,"wins":377},"GB2-07":{"draws":0,"losses":165,"wins":329},"GB2-08":{"draws":312,"losses":176,"wins":20}},"medium":{"GB2-01":{"draws":32,"losses":219,"wins":239},"GB2-03":{"draws":247,"losses":169,"wins":52},"GB2-04":{"draws":250,"losses":186,"wins":36},"GB2-05":{"draws":0,"losses":250,"wins":256},"GB2-06":{"draws":14,"losses":194,"wins":270},"GB2-07":{"draws":0,"losses":120,"wins":376},"GB2-08":{"draws":0,"losses":52,"wins":460}},"none":{"GB2-01":{"draws":78,"losses":232,"wins":180},"GB2-02":{"draws":374,"losses":80,"wins":6},"GB2-03":{"draws":98,"losses":137,"wins":233},"GB2-04":{"draws":307,"losses":129,"wins":34},"GB2-05":{"draws":0,"losses":250,"wins":254},"GB2-06":{"draws":17,"losses":296,"wins":165},"GB2-07":{"draws":0,"losses":316,"wins":176},"GB2-08":{"draws":237,"losses":220,"wins":49}}},"per_game_raw_elo_all":{"GB2-01":1485.5235617414103,"GB2-03":1525.3643055081072,"GB2-04":1433.9014095747245,"GB2-05":1547.5665898748086,"GB2-06":1615.0913892541364,"GB2-07":1607.4516431513,"GB2-08":1547.9599509461486},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1518.9153922488065,"GB2-02":1740.986454733014,"GB2-03":1658.49997025799,"GB2-04":1528.1054774837507,"GB2-05":1724.9799112904457,"GB2-06":1978.0377484947658,"GB2-07":1687.0236903029936,"GB2-08":1263.8752507358117},"medium":{"GB2-01":1500.9238503355878,"GB2-03":1354.1187293513374,"GB2-04":1363.29916243846,"GB2-05":1465.5165265383228,"GB2-06":1596.304071701099,"GB2-07":1834.8191911020276,"GB2-08":2134.420281080986},"none":{"GB2-01":1436.7314426398373,"GB2-02":1422.268273496438,"GB2-03":1563.4742169149936,"GB2-04":1410.299588801963,"GB2-05":1452.2033317956573,"GB2-06":1270.9323475665444,"GB2-07":1300.5120480488788,"GB2-08":1245.5843210216478}},"per_game_tracks":{"highest":{"GB2-01":54.99835897054302,"GB2-02":78.81667076181145,"GB2-03":72.22154454525618,"GB2-04":56.39137544207722,"GB2-05":70.54337743428914,"GB2-06":81.35255441338644,"GB2-07":67.88299829024487,"GB2-08":36.60554843214846},"medium":{"GB2-01":53.13197885396289,"GB2-03":41.03661932716358,"GB2-04":35.369660144689014,"GB2-05":52.06533833220113,"GB2-06":60.51971945527889,"GB2-07":76.94678630003375,"GB2-08":89.90574907234515},"none":{"GB2-01":46.40548704118071,"GB2-02":43.20275452769263,"GB2-03":63.90386087709725,"GB2-04":41.26466060942233,"GB2-05":50.999255562160975,"GB2-06":39.80465582943237,"GB2-07":38.10859845281373,"GB2-08":34.82524884662852}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:22:44Z","reasoning":{"highest":64.8515535362196,"medium":51.1219814357093,"none":44.81431521830357},"reasoning_agg":{"highest":{"max":81.35255441338644,"mean":64.8515535362196,"min":36.60554843214846},"medium":{"max":89.90574907234515,"mean":51.1219814357093,"min":0.0},"none":{"max":63.90386087709725,"mean":44.81431521830357,"min":34.82524884662852}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":20.037238317916028}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:45240e13b47e4a60","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":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405000000001},"medium":{"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":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.37616799999999995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"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":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.37616800000000006},"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":0.03564825,"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":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2224195,"mean":0.071446625,"median":0.04824225,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":27,"run_count":24,"total":1.7147189999999999},"codegen_latency_ms":{"attempt_count":27,"max_ms":194716,"mean_ms":65710.04166666667,"min_ms":14709,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":194716,"mean_ms":132597.5,"min_ms":94687,"run_count":8},"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":27,"output_max":46299,"output_mean":14240.0,"output_min":2554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":46299,"output_mean":31097.375,"output_min":22420,"run_count":8},"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":56.13170011936928,"highest":59.76949112134257,"medium":58.97100412098075,"none":41.84535806271407},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[943718],"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":87,"requested_max_output_token_observations":9,"requested_max_output_tokens":[943718],"total_output_tokens":341760,"total_reasoning_output_tokens":238816,"total_visible_output_tokens":102944,"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":"meta","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":68.06398946566644,"score":68.06398946566644},"GB2-02":{"attempts":3,"playable":45.64320973489709,"score":45.64320973489709},"GB2-03":{"attempts":3,"playable":52.65035120622857,"score":52.65035120622857},"GB2-04":{"attempts":3,"playable":47.46007076523926,"score":47.46007076523926},"GB2-05":{"attempts":3,"playable":54.43397651659314,"score":54.43397651659314},"GB2-06":{"attempts":2,"playable":23.475059906281807,"score":23.475059906281807},"GB2-07":{"attempts":3,"playable":57.70985474648969,"score":57.70985474648969},"GB2-08":{"attempts":3,"playable":66.96044840047074,"score":66.96044840047074}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":81.49517110318034,"score":81.49517110318034},"GB2-02":{"attempts":1,"playable":48.392368747111256,"score":48.392368747111256},"GB2-03":{"attempts":1,"playable":60.38077082126584,"score":60.38077082126584},"GB2-04":{"attempts":1,"playable":49.87785617773407,"score":49.87785617773407},"GB2-05":{"attempts":1,"playable":61.745261275561845,"score":61.745261275561845},"GB2-06":{"attempts":1,"playable":27.107666010580832,"score":27.107666010580832},"GB2-07":{"attempts":1,"playable":74.87737192698349,"score":74.87737192698349},"GB2-08":{"attempts":1,"playable":74.27946290832293,"score":74.27946290832293}},"medium":{"GB2-01":{"attempts":1,"playable":85.60977720253862,"score":85.60977720253862},"GB2-02":{"attempts":1,"playable":46.7754467039408,"score":46.7754467039408},"GB2-03":{"attempts":1,"playable":51.19461110028997,"score":51.19461110028997},"GB2-04":{"attempts":1,"playable":44.90042208548701,"score":44.90042208548701},"GB2-05":{"attempts":1,"playable":49.78111049209816,"score":49.78111049209816},"GB2-07":{"attempts":1,"playable":64.09807448100673,"score":64.09807448100673},"GB2-08":{"attempts":1,"playable":70.437586781504,"score":70.437586781504}},"none":{"GB2-01":{"attempts":1,"playable":37.08702009128038,"score":37.08702009128038},"GB2-02":{"attempts":1,"playable":41.761813753639224,"score":41.761813753639224},"GB2-03":{"attempts":1,"playable":46.37567169712988,"score":46.37567169712988},"GB2-04":{"attempts":1,"playable":47.60193403249669,"score":47.60193403249669},"GB2-05":{"attempts":1,"playable":51.77555778211943,"score":51.77555778211943},"GB2-06":{"attempts":1,"playable":19.842453801982785,"score":19.842453801982785},"GB2-07":{"attempts":1,"playable":34.15411783147886,"score":34.15411783147886},"GB2-08":{"attempts":1,"playable":56.16429551158528,"score":56.16429551158528}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-10-22T09:52:25Z","match_totals_all":{"draws":2300,"losses":4206,"wins":4612},"match_totals_tracks":{"highest":{"draws":658,"losses":1278,"wins":1924},"medium":{"draws":745,"losses":1057,"wins":1588},"none":{"draws":897,"losses":1871,"wins":1100}},"model_slug":"meta-muse-spark-1-2","overall":{"max":85.60977720253862,"mean":53.5286177683458,"min":19.842453801982785},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.49517110318034,"GB2-02":48.392368747111256,"GB2-03":60.38077082126584,"GB2-04":49.87785617773407,"GB2-05":61.745261275561845,"GB2-06":27.107666010580832,"GB2-07":74.87737192698349,"GB2-08":74.27946290832293},"per_game_all":{"GB2-01":68.06398946566644,"GB2-02":45.64320973489709,"GB2-03":52.65035120622857,"GB2-04":47.46007076523926,"GB2-05":54.43397651659314,"GB2-07":57.70985474648969,"GB2-08":66.96044840047074},"per_game_match_totals_all":{"GB2-01":{"draws":185,"losses":395,"wins":884},"GB2-02":{"draws":1025,"losses":249,"wins":92},"GB2-03":{"draws":186,"losses":618,"wins":600},"GB2-04":{"draws":847,"losses":337,"wins":230},"GB2-05":{"draws":0,"losses":703,"wins":809},"GB2-06":{"draws":22,"losses":745,"wins":187},"GB2-07":{"draws":0,"losses":648,"wins":840},"GB2-08":{"draws":35,"losses":511,"wins":970}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":97,"wins":389},"GB2-02":{"draws":346,"losses":69,"wins":39},"GB2-03":{"draws":18,"losses":193,"wins":257},"GB2-04":{"draws":262,"losses":111,"wins":99},"GB2-05":{"draws":0,"losses":198,"wins":306},"GB2-06":{"draws":20,"losses":351,"wins":105},"GB2-07":{"draws":0,"losses":127,"wins":367},"GB2-08":{"draws":10,"losses":132,"wins":362}},"medium":{"GB2-01":{"draws":22,"losses":64,"wins":402},"GB2-02":{"draws":345,"losses":76,"wins":35},"GB2-03":{"draws":104,"losses":191,"wins":173},"GB2-04":{"draws":253,"losses":140,"wins":79},"GB2-05":{"draws":0,"losses":258,"wins":246},"GB2-07":{"draws":0,"losses":181,"wins":313},"GB2-08":{"draws":21,"losses":147,"wins":340}},"none":{"GB2-01":{"draws":161,"losses":234,"wins":93},"GB2-02":{"draws":334,"losses":104,"wins":18},"GB2-03":{"draws":64,"losses":234,"wins":170},"GB2-04":{"draws":332,"losses":86,"wins":52},"GB2-05":{"draws":0,"losses":247,"wins":257},"GB2-06":{"draws":2,"losses":394,"wins":82},"GB2-07":{"draws":0,"losses":340,"wins":160},"GB2-08":{"draws":4,"losses":232,"wins":268}}},"per_game_raw_elo_all":{"GB2-01":1687.5062012072767,"GB2-02":1441.059923171358,"GB2-03":1457.131316230849,"GB2-04":1458.2955710005233,"GB2-05":1496.7618050069975,"GB2-07":1560.18922105211,"GB2-08":1642.11493336418},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1823.3709557697935,"GB2-02":1462.2713738060907,"GB2-03":1527.9843277650962,"GB2-04":1476.9701487756406,"GB2-05":1591.3592676510577,"GB2-06":1078.9153032987606,"GB2-07":1797.9256440923316,"GB2-08":1759.3105878771466},"medium":{"GB2-01":1892.6458942532877,"GB2-02":1449.8191795441987,"GB2-03":1442.861109463886,"GB2-04":1438.5329007428459,"GB2-05":1437.0328799771858,"GB2-07":1632.829880478691,"GB2-08":1688.8094774003148},"none":{"GB2-01":1346.5017535987488,"GB2-02":1411.0892161637848,"GB2-03":1400.5485114635653,"GB2-04":1459.3836634830827,"GB2-05":1461.8932673927486,"GB2-06":964.1314797599653,"GB2-07":1249.8121385853076,"GB2-08":1478.2247348150784}},"per_game_tracks":{"highest":{"GB2-01":81.49517110318034,"GB2-02":48.392368747111256,"GB2-03":60.38077082126584,"GB2-04":49.87785617773407,"GB2-05":61.745261275561845,"GB2-06":27.107666010580832,"GB2-07":74.87737192698349,"GB2-08":74.27946290832293},"medium":{"GB2-01":85.60977720253862,"GB2-02":46.7754467039408,"GB2-03":51.19461110028997,"GB2-04":44.90042208548701,"GB2-05":49.78111049209816,"GB2-07":64.09807448100673,"GB2-08":70.437586781504},"none":{"GB2-01":37.08702009128038,"GB2-02":41.761813753639224,"GB2-03":46.37567169712988,"GB2-04":47.60193403249669,"GB2-05":51.77555778211943,"GB2-06":19.842453801982785,"GB2-07":34.15411783147886,"GB2-08":56.16429551158528}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-1,"rank_movement_baseline_at":"2026-10-20T11:44:02Z","reasoning":{"highest":59.76949112134257,"medium":58.97100412098075,"none":41.84535806271407},"reasoning_agg":{"highest":{"max":81.49517110318034,"mean":59.76949112134257,"min":27.107666010580832},"medium":{"max":85.60977720253862,"mean":58.97100412098075,"min":44.90042208548701},"none":{"max":56.16429551158528,"mean":41.84535806271407,"min":19.842453801982785}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.9241330586285}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:f114411661c1bcbe","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":0.028788054}},"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":0.15272934},"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":0.028788054},"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":0.39273128400000007},"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":53.5044950415776,"highest":68.63308382701196,"medium":55.42918610905846,"none":36.45121518866237},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":58.80358129382349,"score":58.80358129382349},"GB2-02":{"attempts":3,"playable":52.813861423493705,"score":52.813861423493705},"GB2-03":{"attempts":3,"playable":54.69403369496687,"score":54.69403369496687},"GB2-04":{"attempts":3,"playable":50.79394605423281,"score":50.79394605423281},"GB2-05":{"attempts":3,"playable":55.070119629450694,"score":55.070119629450694},"GB2-06":{"attempts":3,"playable":62.51424323920571,"score":62.51424323920571},"GB2-07":{"attempts":3,"playable":56.391055135905134,"score":56.391055135905134},"GB2-08":{"attempts":3,"playable":36.955119861542336,"score":36.955119861542336}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.65705165941744,"score":63.65705165941744},"GB2-02":{"attempts":1,"playable":57.41310949558838,"score":57.41310949558838},"GB2-03":{"attempts":1,"playable":60.480687419181,"score":60.480687419181},"GB2-04":{"attempts":1,"playable":75.00384968794027,"score":75.00384968794027},"GB2-05":{"attempts":1,"playable":82.51961357655476,"score":82.51961357655476},"GB2-06":{"attempts":1,"playable":82.4402497309643,"score":82.4402497309643},"GB2-07":{"attempts":1,"playable":75.33540734245307,"score":75.33540734245307},"GB2-08":{"attempts":1,"playable":52.21470170399643,"score":52.21470170399643}},"medium":{"GB2-01":{"attempts":1,"playable":67.1005295695362,"score":67.1005295695362},"GB2-02":{"attempts":1,"playable":58.70412189179318,"score":58.70412189179318},"GB2-03":{"attempts":1,"playable":55.2442784435878,"score":55.2442784435878},"GB2-04":{"attempts":1,"playable":38.79437387975818,"score":38.79437387975818},"GB2-05":{"attempts":1,"playable":53.15660879939605,"score":53.15660879939605},"GB2-06":{"attempts":1,"playable":77.55598529272868,"score":77.55598529272868},"GB2-07":{"attempts":1,"playable":68.90220783167136,"score":68.90220783167136},"GB2-08":{"attempts":1,"playable":23.97538316399625,"score":23.97538316399625}},"none":{"GB2-01":{"attempts":1,"playable":45.65316265251682,"score":45.65316265251682},"GB2-02":{"attempts":1,"playable":42.32435288309956,"score":42.32435288309956},"GB2-03":{"attempts":1,"playable":48.35713522213182,"score":48.35713522213182},"GB2-04":{"attempts":1,"playable":38.58361459499997,"score":38.58361459499997},"GB2-05":{"attempts":1,"playable":29.5341365124013,"score":29.5341365124013},"GB2-06":{"attempts":1,"playable":27.546494693924174,"score":27.546494693924174},"GB2-07":{"attempts":1,"playable":24.93555023359099,"score":24.93555023359099},"GB2-08":{"attempts":1,"playable":34.67527471663433,"score":34.67527471663433}}},"id":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:32:10Z","match_totals_all":{"draws":3156,"losses":4002,"wins":4435},"match_totals_tracks":{"highest":{"draws":763,"losses":885,"wins":2214},"medium":{"draws":1176,"losses":1190,"wins":1500},"none":{"draws":1217,"losses":1927,"wins":721}},"model_slug":"deepseek-deepseek-v4-1-flash","overall":{"max":82.51961357655476,"mean":53.5044950415776,"min":23.97538316399625},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.65705165941744,"GB2-02":57.41310949558838,"GB2-03":60.480687419181,"GB2-04":75.00384968794027,"GB2-05":82.51961357655476,"GB2-06":82.4402497309643,"GB2-07":75.33540734245307,"GB2-08":52.21470170399643},"per_game_all":{"GB2-01":58.80358129382349,"GB2-02":52.813861423493705,"GB2-03":54.69403369496687,"GB2-04":50.79394605423281,"GB2-05":55.070119629450694,"GB2-06":62.51424323920571,"GB2-07":56.391055135905134,"GB2-08":36.955119861542336},"per_game_match_totals_all":{"GB2-01":{"draws":456,"losses":399,"wins":613},"GB2-02":{"draws":948,"losses":186,"wins":228},"GB2-03":{"draws":296,"losses":538,"wins":575},"GB2-04":{"draws":691,"losses":367,"wins":352},"GB2-05":{"draws":0,"losses":688,"wins":824},"GB2-06":{"draws":91,"losses":515,"wins":828},"GB2-07":{"draws":0,"losses":665,"wins":817},"GB2-08":{"draws":674,"losses":644,"wins":198}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":176,"wins":291},"GB2-02":{"draws":278,"losses":60,"wins":116},"GB2-03":{"draws":54,"losses":177,"wins":241},"GB2-04":{"draws":149,"losses":48,"wins":273},"GB2-05":{"draws":0,"losses":90,"wins":414},"GB2-06":{"draws":31,"losses":73,"wins":374},"GB2-07":{"draws":0,"losses":123,"wins":369},"GB2-08":{"draws":230,"losses":138,"wins":136}},"medium":{"GB2-01":{"draws":283,"losses":26,"wins":183},"GB2-02":{"draws":301,"losses":43,"wins":110},"GB2-03":{"draws":132,"losses":157,"wins":179},"GB2-04":{"draws":246,"losses":172,"wins":52},"GB2-05":{"draws":0,"losses":239,"wins":265},"GB2-06":{"draws":30,"losses":96,"wins":352},"GB2-07":{"draws":0,"losses":160,"wins":336},"GB2-08":{"draws":184,"losses":297,"wins":23}},"none":{"GB2-01":{"draws":152,"losses":197,"wins":139},"GB2-02":{"draws":369,"losses":83,"wins":2},"GB2-03":{"draws":110,"losses":204,"wins":155},"GB2-04":{"draws":296,"losses":147,"wins":27},"GB2-05":{"draws":0,"losses":359,"wins":145},"GB2-06":{"draws":30,"losses":346,"wins":102},"GB2-07":{"draws":0,"losses":382,"wins":112},"GB2-08":{"draws":260,"losses":209,"wins":39}}},"per_game_raw_elo_all":{"GB2-01":1558.8329439315269,"GB2-02":1497.3390219567189,"GB2-03":1475.4003655795686,"GB2-04":1492.6598863413583,"GB2-05":1545.519368153083,"GB2-06":1662.9748186596541,"GB2-07":1543.4906442456734,"GB2-08":1267.875235821682},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1605.2423987922184,"GB2-02":1533.034070443376,"GB2-03":1528.9629645614934,"GB2-04":1697.9463313761348,"GB2-05":1988.7488371916652,"GB2-06":2000.4171203396422,"GB2-07":1805.8852732510784,"GB2-08":1430.7233486511013},"medium":{"GB2-01":1641.698591015923,"GB2-02":1543.5224200165906,"GB2-03":1479.391237359025,"GB2-04":1390.8533219322383,"GB2-05":1479.1995966681743,"GB2-06":1902.8827650895153,"GB2-07":1702.1863705864628,"GB2-08":1128.8622994574787},"none":{"GB2-01":1429.5578419864396,"GB2-02":1415.4605754101897,"GB2-03":1417.8468948181874,"GB2-04":1389.1800057157016,"GB2-05":1168.60967059941,"GB2-06":1085.6245705498045,"GB2-07":1122.4002888994796,"GB2-08":1244.040059356466}},"per_game_tracks":{"highest":{"GB2-01":63.65705165941744,"GB2-02":57.41310949558838,"GB2-03":60.480687419181,"GB2-04":75.00384968794027,"GB2-05":82.51961357655476,"GB2-06":82.4402497309643,"GB2-07":75.33540734245307,"GB2-08":52.21470170399643},"medium":{"GB2-01":67.1005295695362,"GB2-02":58.70412189179318,"GB2-03":55.2442784435878,"GB2-04":38.79437387975818,"GB2-05":53.15660879939605,"GB2-06":77.55598529272868,"GB2-07":68.90220783167136,"GB2-08":23.97538316399625},"none":{"GB2-01":45.65316265251682,"GB2-02":42.32435288309956,"GB2-03":48.35713522213182,"GB2-04":38.58361459499997,"GB2-05":29.5341365124013,"GB2-06":27.546494693924174,"GB2-07":24.93555023359099,"GB2-08":34.67527471663433}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:45:46Z","reasoning":{"highest":68.63308382701196,"medium":55.42918610905846,"none":36.45121518866237},"reasoning_agg":{"highest":{"max":82.51961357655476,"mean":68.63308382701196,"min":52.21470170399643},"medium":{"max":77.55598529272868,"mean":55.42918610905846,"min":23.97538316399625},"none":{"max":48.35713522213182,"mean":36.45121518866237,"min":24.93555023359099}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":32.18186863834959}},{"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:95fdfef11dba5733","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":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399970000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5826720000000001}},"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":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399970000000001},"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":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5826720000000001},"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":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147}},"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":0.508434,"mean":0.171409,"median":0.146631,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":28,"run_count":24,"total":4.113816},"codegen_latency_ms":{"attempt_count":28,"max_ms":413691,"mean_ms":128683.25,"min_ms":28133,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":413691,"mean_ms":243828.625,"min_ms":115297,"run_count":8},"medium":{"attempt_count":10,"max_ms":159798,"mean_ms":101243.125,"min_ms":39983,"run_count":8},"none":{"attempt_count":9,"max_ms":84315,"mean_ms":40978.0,"min_ms":28133,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":30544,"output_mean":9612.333333333334,"output_min":2170,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":30544,"output_mean":18138.375,"output_min":8542,"run_count":8},"medium":{"attempt_count":10,"output_max":11696,"output_mean":7576.625,"output_min":3317,"run_count":8},"none":{"attempt_count":9,"output_max":6625,"output_mean":3122.0,"output_min":2170,"run_count":8}},"display_name":"Ember-1","economics":{"all":52.90313931883219,"highest":65.1285220855591,"medium":54.51864630273677,"none":39.06224956820069},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[262144],"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,"requested_max_output_token_observations":28,"requested_max_output_tokens":[262144],"total_output_tokens":230696,"total_reasoning_output_tokens":146257,"total_visible_output_tokens":84439,"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":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"fireworks","provider_model":"fireworks/ember-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.91316406684527,"score":59.91316406684527},"GB2-02":{"attempts":3,"playable":44.410309789645744,"score":44.410309789645744},"GB2-03":{"attempts":3,"playable":59.93222301402968,"score":59.93222301402968},"GB2-04":{"attempts":3,"playable":44.94734231264578,"score":44.94734231264578},"GB2-05":{"attempts":3,"playable":44.379154895420676,"score":44.379154895420676},"GB2-06":{"attempts":3,"playable":52.655204506818734,"score":52.655204506818734},"GB2-07":{"attempts":3,"playable":59.20325725911952,"score":59.20325725911952},"GB2-08":{"attempts":3,"playable":57.78445870613208,"score":57.78445870613208}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":77.45441547399477,"score":77.45441547399477},"GB2-02":{"attempts":1,"playable":43.14430663663124,"score":43.14430663663124},"GB2-03":{"attempts":1,"playable":81.17186461065758,"score":81.17186461065758},"GB2-04":{"attempts":1,"playable":40.65199091832585,"score":40.65199091832585},"GB2-05":{"attempts":1,"playable":63.48530869851422,"score":63.48530869851422},"GB2-06":{"attempts":1,"playable":52.89001517986076,"score":52.89001517986076},"GB2-07":{"attempts":1,"playable":76.27926528669202,"score":76.27926528669202},"GB2-08":{"attempts":1,"playable":85.95100987979632,"score":85.95100987979632}},"medium":{"GB2-01":{"attempts":1,"playable":51.14643329451718,"score":51.14643329451718},"GB2-02":{"attempts":1,"playable":45.17984723102839,"score":45.17984723102839},"GB2-03":{"attempts":1,"playable":62.37258593920386,"score":62.37258593920386},"GB2-04":{"attempts":1,"playable":52.62930984904531,"score":52.62930984904531},"GB2-05":{"attempts":1,"playable":47.622413762547616,"score":47.622413762547616},"GB2-06":{"attempts":1,"playable":57.50627061754995,"score":57.50627061754995},"GB2-07":{"attempts":1,"playable":64.4722975325315,"score":64.4722975325315},"GB2-08":{"attempts":1,"playable":55.22001219547038,"score":55.22001219547038}},"none":{"GB2-01":{"attempts":1,"playable":51.138643432023855,"score":51.138643432023855},"GB2-02":{"attempts":1,"playable":44.90677550127761,"score":44.90677550127761},"GB2-03":{"attempts":1,"playable":36.25221849222761,"score":36.25221849222761},"GB2-04":{"attempts":1,"playable":41.56072617056618,"score":41.56072617056618},"GB2-05":{"attempts":1,"playable":22.029742225200216,"score":22.029742225200216},"GB2-06":{"attempts":1,"playable":47.569327723045504,"score":47.569327723045504},"GB2-07":{"attempts":1,"playable":36.85820895813505,"score":36.85820895813505},"GB2-08":{"attempts":1,"playable":32.18235404312953,"score":32.18235404312953}}},"id":"fireworks/ember-1","is_recent_addition":false,"last_measured_at":"2026-10-22T10:28:10Z","match_totals_all":{"draws":3141,"losses":4069,"wins":4366},"match_totals_tracks":{"highest":{"draws":692,"losses":1037,"wins":2127},"medium":{"draws":1108,"losses":1268,"wins":1484},"none":{"draws":1341,"losses":1764,"wins":755}},"model_slug":"fireworks-ember-1","overall":{"max":85.95100987979632,"mean":52.90313931883219,"min":22.029742225200216},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.45441547399477,"GB2-02":43.14430663663124,"GB2-03":81.17186461065758,"GB2-04":40.65199091832585,"GB2-05":63.48530869851422,"GB2-06":52.89001517986076,"GB2-07":76.27926528669202,"GB2-08":85.95100987979632},"per_game_all":{"GB2-01":59.91316406684527,"GB2-02":44.410309789645744,"GB2-03":59.93222301402968,"GB2-04":44.94734231264578,"GB2-05":44.379154895420676,"GB2-06":52.655204506818734,"GB2-07":59.20325725911952,"GB2-08":57.78445870613208},"per_game_match_totals_all":{"GB2-01":{"draws":448,"losses":385,"wins":635},"GB2-02":{"draws":1031,"losses":260,"wins":71},"GB2-03":{"draws":282,"losses":463,"wins":659},"GB2-04":{"draws":860,"losses":364,"wins":186},"GB2-05":{"draws":0,"losses":854,"wins":658},"GB2-06":{"draws":70,"losses":681,"wins":677},"GB2-07":{"draws":0,"losses":626,"wins":854},"GB2-08":{"draws":450,"losses":436,"wins":626}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":111,"wins":369},"GB2-02":{"draws":347,"losses":91,"wins":16},"GB2-03":{"draws":14,"losses":90,"wins":364},"GB2-04":{"draws":298,"losses":136,"wins":36},"GB2-05":{"draws":0,"losses":189,"wins":315},"GB2-06":{"draws":20,"losses":229,"wins":227},"GB2-07":{"draws":0,"losses":119,"wins":373},"GB2-08":{"draws":5,"losses":72,"wins":427}},"medium":{"GB2-01":{"draws":245,"losses":123,"wins":120},"GB2-02":{"draws":343,"losses":83,"wins":28},"GB2-03":{"draws":36,"losses":175,"wins":257},"GB2-04":{"draws":288,"losses":85,"wins":97},"GB2-05":{"draws":0,"losses":268,"wins":236},"GB2-06":{"draws":18,"losses":204,"wins":254},"GB2-07":{"draws":0,"losses":183,"wins":313},"GB2-08":{"draws":178,"losses":147,"wins":179}},"none":{"GB2-01":{"draws":195,"losses":151,"wins":146},"GB2-02":{"draws":341,"losses":86,"wins":27},"GB2-03":{"draws":232,"losses":198,"wins":38},"GB2-04":{"draws":274,"losses":143,"wins":53},"GB2-05":{"draws":0,"losses":397,"wins":107},"GB2-06":{"draws":32,"losses":248,"wins":196},"GB2-07":{"draws":0,"losses":324,"wins":168},"GB2-08":{"draws":267,"losses":217,"wins":20}}},"per_game_raw_elo_all":{"GB2-01":1576.3761653117942,"GB2-02":1431.5917370893173,"GB2-03":1550.9660250657573,"GB2-04":1438.8280451587036,"GB2-05":1357.866720898683,"GB2-06":1469.4662277649388,"GB2-07":1581.7802439419086,"GB2-08":1568.231991351032},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1765.3845424158735,"GB2-02":1421.8159074533726,"GB2-03":1793.1513234659851,"GB2-04":1405.5022487981432,"GB2-05":1615.7206084953432,"GB2-06":1472.436977446708,"GB2-07":1822.6474248356258,"GB2-08":2019.913994697382},"medium":{"GB2-01":1481.9091823218862,"GB2-02":1437.531992469069,"GB2-03":1547.7871916304857,"GB2-04":1498.3691870124958,"GB2-05":1410.1791792696154,"GB2-06":1546.5256030673752,"GB2-07":1638.057876263994,"GB2-08":1466.5534887099773},"none":{"GB2-01":1481.8347711976232,"GB2-02":1435.4273113455104,"GB2-03":1311.9595601008014,"GB2-04":1412.612699665472,"GB2-05":1047.7003749310907,"GB2-06":1389.4361027807336,"GB2-07":1284.6354307261063,"GB2-08":1218.2284906457369}},"per_game_tracks":{"highest":{"GB2-01":77.45441547399477,"GB2-02":43.14430663663124,"GB2-03":81.17186461065758,"GB2-04":40.65199091832585,"GB2-05":63.48530869851422,"GB2-06":52.89001517986076,"GB2-07":76.27926528669202,"GB2-08":85.95100987979632},"medium":{"GB2-01":51.14643329451718,"GB2-02":45.17984723102839,"GB2-03":62.37258593920386,"GB2-04":52.62930984904531,"GB2-05":47.622413762547616,"GB2-06":57.50627061754995,"GB2-07":64.4722975325315,"GB2-08":55.22001219547038},"none":{"GB2-01":51.138643432023855,"GB2-02":44.90677550127761,"GB2-03":36.25221849222761,"GB2-04":41.56072617056618,"GB2-05":22.029742225200216,"GB2-06":47.569327723045504,"GB2-07":36.85820895813505,"GB2-08":32.18235404312953}},"provider_color":"#6720FF","provider_company":"Fireworks AI","provider_key":"fireworks","provider_text_color":"#f8fafc","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:41:58Z","reasoning":{"highest":65.1285220855591,"medium":54.51864630273677,"none":39.06224956820069},"reasoning_agg":{"highest":{"max":85.95100987979632,"mean":65.1285220855591,"min":40.65199091832585},"medium":{"max":64.4722975325315,"mean":54.51864630273677,"min":45.17984723102839},"none":{"max":51.138643432023855,"mean":39.06224956820069,"min":22.029742225200216}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.066272517358406}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:0872dfe408a47318","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.531673125,"mean":0.4248703476562501,"median":0.446083425,"min":0.28979720625,"recorded_attempt_count":57,"run_count":20,"total":8.014536975},"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":0.8934513}},"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":16,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.531673125,"mean":0.4248703476562501,"median":0.446083425,"min":0.28979720625,"recorded_attempt_count":57,"run_count":20,"total":8.014536974999999}},"codegen_cost_usd":{"admitted_cell_count":46,"cell_count":24,"cost_basis_counts":{"provider_reported":130},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.531673125,"mean":0.24710551171874998,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":130,"run_count":52,"total":13.077675975},"codegen_latency_ms":{"attempt_count":126,"max_ms":348942,"mean_ms":134334.75,"min_ms":17298,"run_count":52},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":53,"max_ms":348942,"mean_ms":213753.4,"min_ms":85578,"run_count":20},"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":130,"output_max":100087,"output_mean":31640.134615384617,"output_min":2060,"run_count":52},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":57,"output_max":100087,"output_mean":54101.95,"output_min":17027,"run_count":20},"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":54.678434422970696,"highest":64.47737209849694,"medium":59.040456837956214,"none":40.51747433245891},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[65536],"finish_reason_observations":126,"finish_reasons":["length","stop"],"indexed_attempts":131,"output_token_observations":130,"provider_post_attempt_observations":4,"provider_post_attempts":4,"reasoning_token_observations":86,"reconciliation_get_attempt_observations":4,"reconciliation_get_attempts":19,"requested_max_output_token_observations":5,"requested_max_output_tokens":[65536],"total_output_tokens":1645287,"total_reasoning_output_tokens":844369,"total_visible_output_tokens":229233,"visible_token_observations":86},"generation_policy":{"generation_policy":"quality_generation_policy","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":1,"model_code_failures":1}},"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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2,"infra_failures_excluded":2},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2,"infra_failures_excluded":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-02","GB2-03","GB2-07"],"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":4,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":53.17280317725115,"score":53.17280317725115},"GB2-02":{"attempts":6,"failed_attempts":1,"playable":44.34230212615521,"score":38.065727306858165},"GB2-03":{"attempts":6,"playable":57.77255420683061,"score":57.77255420683061},"GB2-04":{"attempts":6,"playable":48.946792455727795,"score":48.946792455727795},"GB2-05":{"attempts":6,"playable":67.067265125134,"score":67.067265125134},"GB2-06":{"attempts":6,"playable":63.685534805581085,"score":63.685534805581085},"GB2-07":{"attempts":6,"playable":48.99062093421052,"score":48.99062093421052},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":53.44960255287515,"score":41.72722664425494}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":55.70612374936137,"score":55.70612374936137},"GB2-02":{"attempts":2,"playable":54.97086227960831,"score":54.97086227960831},"GB2-03":{"attempts":2,"playable":69.0742877400339,"score":69.0742877400339},"GB2-04":{"attempts":2,"playable":62.800026522246725,"score":62.800026522246725},"GB2-05":{"attempts":2,"playable":83.72619493916893,"score":83.72619493916893},"GB2-06":{"attempts":2,"playable":83.51379043707001,"score":83.51379043707001},"GB2-07":{"attempts":2,"playable":51.220979799341094,"score":51.220979799341094},"GB2-08":{"attempts":2,"playable":54.806711321145244,"score":54.806711321145244}},"medium":{"GB2-01":{"attempts":2,"playable":72.53099422722113,"score":72.53099422722113},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":37.65944891578224,"score":18.82972445789112},"GB2-03":{"attempts":2,"playable":48.52646279453595,"score":48.52646279453595},"GB2-04":{"attempts":2,"playable":41.3239836253731,"score":41.3239836253731},"GB2-05":{"attempts":2,"playable":70.12114709127681,"score":70.12114709127681},"GB2-06":{"attempts":2,"playable":83.79811939167506,"score":83.79811939167506},"GB2-07":{"attempts":2,"playable":48.029243206064166,"score":48.029243206064166},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":70.33425545172125,"score":35.167127725860624}},"none":{"GB2-01":{"attempts":2,"playable":31.281291555170927,"score":31.281291555170927},"GB2-02":{"attempts":2,"playable":40.396595183075064,"score":40.396595183075064},"GB2-03":{"attempts":2,"playable":55.71691208592199,"score":55.71691208592199},"GB2-04":{"attempts":2,"playable":42.71636721956355,"score":42.71636721956355},"GB2-05":{"attempts":2,"playable":47.354453344956255,"score":47.354453344956255},"GB2-06":{"attempts":2,"playable":23.744694587998183,"score":23.744694587998183},"GB2-07":{"attempts":2,"playable":47.721639797226295,"score":47.721639797226295},"GB2-08":{"attempts":2,"playable":35.207840885758955,"score":35.207840885758955}}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:53:58Z","match_totals_all":{"draws":5095,"losses":7860,"wins":9277},"match_totals_tracks":{"highest":{"draws":1468,"losses":2125,"wins":4135},"medium":{"draws":1350,"losses":2127,"wins":3295},"none":{"draws":2277,"losses":3608,"wins":1847}},"model_slug":"google-gemini-3-6-flash","overall":{"max":83.79811939167506,"mean":52.428565581981026,"min":18.82972445789112},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.70612374936137,"GB2-02":54.97086227960831,"GB2-03":69.0742877400339,"GB2-04":62.800026522246725,"GB2-05":83.72619493916893,"GB2-06":83.51379043707001,"GB2-07":51.220979799341094,"GB2-08":54.806711321145244},"per_game_all":{"GB2-01":53.17280317725115,"GB2-02":44.34230212615521,"GB2-03":57.77255420683061,"GB2-04":48.946792455727795,"GB2-05":67.067265125134,"GB2-06":63.685534805581085,"GB2-07":48.99062093421052,"GB2-08":53.44960255287515},"per_game_match_totals_all":{"GB2-01":{"draws":662,"losses":1082,"wins":1188},"GB2-02":{"draws":1572,"losses":483,"wins":223},"GB2-03":{"draws":302,"losses":1122,"wins":1386},"GB2-04":{"draws":1685,"losses":633,"wins":504},"GB2-05":{"draws":0,"losses":1022,"wins":2014},"GB2-06":{"draws":153,"losses":1006,"wins":1709},"GB2-07":{"draws":0,"losses":1564,"wins":1394},"GB2-08":{"draws":721,"losses":948,"wins":859}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":235,"losses":330,"wins":413},"GB2-02":{"draws":552,"losses":144,"wins":212},"GB2-03":{"draws":52,"losses":292,"wins":594},"GB2-04":{"draws":447,"losses":137,"wins":356},"GB2-05":{"draws":0,"losses":170,"wins":840},"GB2-06":{"draws":22,"losses":157,"wins":777},"GB2-07":{"draws":0,"losses":499,"wins":487},"GB2-08":{"draws":160,"losses":396,"wins":456}},"medium":{"GB2-01":{"draws":256,"losses":150,"wins":570},"GB2-02":{"draws":323,"losses":128,"wins":5},"GB2-03":{"draws":88,"losses":466,"wins":382},"GB2-04":{"draws":580,"losses":275,"wins":87},"GB2-05":{"draws":0,"losses":309,"wins":703},"GB2-06":{"draws":52,"losses":134,"wins":770},"GB2-07":{"draws":0,"losses":531,"wins":457},"GB2-08":{"draws":51,"losses":134,"wins":321}},"none":{"GB2-01":{"draws":171,"losses":602,"wins":205},"GB2-02":{"draws":697,"losses":211,"wins":6},"GB2-03":{"draws":162,"losses":364,"wins":410},"GB2-04":{"draws":658,"losses":221,"wins":61},"GB2-05":{"draws":0,"losses":543,"wins":471},"GB2-06":{"draws":79,"losses":715,"wins":162},"GB2-07":{"draws":0,"losses":534,"wins":450},"GB2-08":{"draws":510,"losses":418,"wins":82}}},"per_game_raw_elo_all":{"GB2-01":1537.142867894155,"GB2-02":1431.6425833606554,"GB2-03":1509.791147627818,"GB2-04":1472.419014998087,"GB2-05":1772.4470892159395,"GB2-06":1701.1908903270335,"GB2-07":1437.0219089817176,"GB2-08":1477.928964882433},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1531.848002863078,"GB2-02":1515.6866554604194,"GB2-03":1620.2718898231942,"GB2-04":1585.114704094814,"GB2-05":2069.7065004934293,"GB2-06":2051.2899970332546,"GB2-07":1464.0969744871163,"GB2-08":1497.2674118940115},"medium":{"GB2-01":1792.8874747229493,"GB2-02":1378.8080398857464,"GB2-03":1424.220030496025,"GB2-04":1410.61160857711,"GB2-05":1840.8781587645603,"GB2-06":2029.8589564821618,"GB2-07":1425.2203737895034,"GB2-08":1687.0036152742357},"none":{"GB2-01":1286.6931260964384,"GB2-02":1400.4330547358009,"GB2-03":1484.8815225642343,"GB2-04":1421.5307323223371,"GB2-05":1406.7566083898291,"GB2-06":1022.4237174656843,"GB2-07":1421.7483786685339,"GB2-08":1249.5158674790514}},"per_game_tracks":{"highest":{"GB2-01":55.70612374936137,"GB2-02":54.97086227960831,"GB2-03":69.0742877400339,"GB2-04":62.800026522246725,"GB2-05":83.72619493916893,"GB2-06":83.51379043707001,"GB2-07":51.220979799341094,"GB2-08":54.806711321145244},"medium":{"GB2-01":72.53099422722113,"GB2-02":37.65944891578224,"GB2-03":48.52646279453595,"GB2-04":41.3239836253731,"GB2-05":70.12114709127681,"GB2-06":83.79811939167506,"GB2-07":48.029243206064166,"GB2-08":70.33425545172125},"none":{"GB2-01":31.281291555170927,"GB2-02":40.396595183075064,"GB2-03":55.71691208592199,"GB2-04":42.71636721956355,"GB2-05":47.354453344956255,"GB2-06":23.744694587998183,"GB2-07":47.721639797226295,"GB2-08":35.207840885758955}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-20T11:41:58Z","reasoning":{"highest":64.47737209849694,"medium":52.290850314987246,"none":40.51747433245891},"reasoning_agg":{"highest":{"max":83.72619493916893,"mean":64.47737209849694,"min":51.220979799341094},"medium":{"max":83.79811939167506,"mean":52.290850314987246,"min":18.82972445789112},"none":{"max":55.71691208592199,"mean":40.51747433245891,"min":23.744694587998183}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":23.959897766038033}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:983461ec7081f23f","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":true,"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":true,"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":true,"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":true,"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":54.35562330289534,"highest":68.31441774985693,"medium":51.2863634154232,"none":43.4660887434059},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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"],"first_pass_admitted":21,"first_pass_rate":0.7241379310344828,"game_attempts":{"GB2-01":{"admitted":2,"model_code_failures":1},"GB2-02":{"admitted":3},"GB2-03":{"admitted":7,"model_code_failures":2},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":2,"performance_rejections":1},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.10344827586206896,"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},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":5,"repaired_rate":0.1724137931034483},"baseline":{"admitted_plugins":28,"evaluated_cells":30,"failed_game_aliases":["GB2-03","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6333333333333333,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":8,"model_code_failures":1},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":2,"model_code_failures":1}},"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,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":2,"infra_failures_excluded":1},"GB2-03":{"admitted":5,"infra_failures_excluded":4},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"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}},"headline_games_all":{"GB2-01":{"attempts":9,"failed_attempts":1,"playable":54.54448380594672,"score":47.58357852836685},"GB2-02":{"attempts":8,"playable":55.87313541048473,"score":55.87313541048473},"GB2-03":{"attempts":23,"failed_attempts":3,"playable":58.08277137404196,"score":52.13518836781929},"GB2-04":{"attempts":9,"playable":59.60154300555147,"score":59.60154300555147},"GB2-05":{"attempts":9,"playable":54.68603445090551,"score":54.68603445090551},"GB2-06":{"attempts":8,"playable":46.817401821569575,"score":46.817401821569575},"GB2-07":{"attempts":9,"playable":50.70989877919485,"score":50.70989877919485},"GB2-08":{"attempts":9,"failed_attempts":1,"playable":54.52971777546793,"score":50.928652806714915}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":3,"playable":58.6019384322153,"score":58.6019384322153},"GB2-02":{"attempts":2,"playable":73.91105484821749,"score":73.91105484821749},"GB2-03":{"attempts":5,"playable":71.42141763532382,"score":71.42141763532382},"GB2-04":{"attempts":3,"playable":71.88138334902587,"score":71.88138334902587},"GB2-05":{"attempts":3,"playable":62.78008659282265,"score":62.78008659282265},"GB2-06":{"attempts":3,"playable":69.37527854165438,"score":69.37527854165438},"GB2-07":{"attempts":3,"playable":66.57390714240803,"score":66.57390714240803},"GB2-08":{"attempts":3,"playable":71.97027545718792,"score":71.97027545718792}},"medium":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":62.648147498218734,"score":41.765431665479156},"GB2-02":{"attempts":3,"playable":50.2804749323609,"score":50.2804749323609},"GB2-03":{"attempts":9,"failed_attempts":2,"playable":57.7578446812102,"score":44.92276808538571},"GB2-04":{"attempts":3,"playable":57.36629461091437,"score":57.36629461091437},"GB2-05":{"attempts":3,"playable":49.49736873476317,"score":49.49736873476317},"GB2-06":{"attempts":2,"playable":27.83929602727124,"score":27.83929602727124},"GB2-07":{"attempts":3,"playable":45.69218768820833,"score":45.69218768820833},"GB2-08":{"attempts":3,"playable":59.20929315043867,"score":59.20929315043867}},"none":{"GB2-01":{"attempts":3,"playable":42.3833654874061,"score":42.3833654874061},"GB2-02":{"attempts":3,"playable":43.42787645087579,"score":43.42787645087579},"GB2-03":{"attempts":9,"failed_attempts":1,"playable":45.069051805591876,"score":40.061379382748335},"GB2-04":{"attempts":3,"playable":49.55695105671418,"score":49.55695105671418},"GB2-05":{"attempts":3,"playable":51.780648025130716,"score":51.780648025130716},"GB2-06":{"attempts":3,"playable":43.237630895783106,"score":43.237630895783106},"GB2-07":{"attempts":3,"playable":39.8636015069682,"score":39.8636015069682},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.4095847187772,"score":21.60638981251813}}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-10-22T10:41:54Z","match_totals_all":{"draws":8275,"losses":13790,"wins":15940},"match_totals_tracks":{"highest":{"draws":1315,"losses":3352,"wins":7408},"medium":{"draws":2809,"losses":4727,"wins":4960},"none":{"draws":4151,"losses":5711,"wins":3572}},"model_slug":"stealth-ox-alpha","overall":{"max":73.91105484821749,"mean":52.29192914632589,"min":21.60638981251813},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.6019384322153,"GB2-02":73.91105484821749,"GB2-03":71.42141763532382,"GB2-04":71.88138334902587,"GB2-05":62.78008659282264,"GB2-06":69.37527854165438,"GB2-07":66.57390714240803,"GB2-08":71.97027545718792},"per_game_all":{"GB2-01":54.54448380594672,"GB2-02":55.87313541048473,"GB2-03":58.08277137404196,"GB2-04":59.60154300555147,"GB2-05":54.68603445090551,"GB2-06":46.817401821569575,"GB2-07":50.70989877919485,"GB2-08":54.52971777546793},"per_game_match_totals_all":{"GB2-01":{"draws":618,"losses":1556,"wins":1734},"GB2-02":{"draws":2390,"losses":545,"wins":711},"GB2-03":{"draws":1795,"losses":3495,"wins":4077},"GB2-04":{"draws":2240,"losses":640,"wins":1356},"GB2-05":{"draws":0,"losses":2095,"wins":2447},"GB2-06":{"draws":147,"losses":1950,"wins":1727},"GB2-07":{"draws":0,"losses":2260,"wins":2180},"GB2-08":{"draws":1085,"losses":1249,"wins":1708}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":65,"losses":592,"wins":809},"GB2-02":{"draws":335,"losses":81,"wins":496},"GB2-03":{"draws":139,"losses":658,"wins":1546},"GB2-04":{"draws":526,"losses":146,"wins":738},"GB2-05":{"draws":0,"losses":579,"wins":935},"GB2-06":{"draws":93,"losses":414,"wins":927},"GB2-07":{"draws":0,"losses":514,"wins":966},"GB2-08":{"draws":157,"losses":368,"wins":991}},"medium":{"GB2-01":{"draws":207,"losses":271,"wins":498},"GB2-02":{"draws":999,"losses":197,"wins":170},"GB2-03":{"draws":368,"losses":1301,"wins":1609},"GB2-04":{"draws":826,"losses":207,"wins":379},"GB2-05":{"draws":0,"losses":777,"wins":739},"GB2-06":{"draws":21,"losses":699,"wins":236},"GB2-07":{"draws":0,"losses":824,"wins":654},"GB2-08":{"draws":388,"losses":451,"wins":675}},"none":{"GB2-01":{"draws":346,"losses":693,"wins":427},"GB2-02":{"draws":1056,"losses":267,"wins":45},"GB2-03":{"draws":1288,"losses":1536,"wins":922},"GB2-04":{"draws":888,"losses":287,"wins":239},"GB2-05":{"draws":0,"losses":739,"wins":773},"GB2-06":{"draws":33,"losses":837,"wins":564},"GB2-07":{"draws":0,"losses":922,"wins":560},"GB2-08":{"draws":540,"losses":430,"wins":42}}},"per_game_raw_elo_all":{"GB2-01":1516.3649647964676,"GB2-02":1531.9849294591695,"GB2-03":1531.5843213665103,"GB2-04":1567.1651664256697,"GB2-05":1502.4773753556158,"GB2-06":1381.1992528959283,"GB2-07":1454.9508126260328,"GB2-08":1501.4993989554584},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1557.3614094001161,"GB2-02":1694.9445590306545,"GB2-03":1684.347274885457,"GB2-04":1690.4484781560486,"GB2-05":1611.3965992968126,"GB2-06":1778.134718225356,"GB2-07":1671.9997911722132,"GB2-08":1750.6514420456194},"medium":{"GB2-01":1595.571662753826,"GB2-02":1477.0101273893515,"GB2-03":1521.7774866172053,"GB2-04":1536.2683052909972,"GB2-05":1433.6296904469866,"GB2-06":1040.3345692738935,"GB2-07":1385.137247695664,"GB2-08":1533.2974516242466},"none":{"GB2-01":1396.1618222354602,"GB2-02":1424.0001019575022,"GB2-03":1388.6282025968683,"GB2-04":1474.7787158299634,"GB2-05":1462.4058363230479,"GB2-06":1325.1284711885353,"GB2-07":1307.7153990102215,"GB2-08":1220.5493031965088}},"per_game_tracks":{"highest":{"GB2-01":58.6019384322153,"GB2-02":73.91105484821749,"GB2-03":71.42141763532382,"GB2-04":71.88138334902587,"GB2-05":62.78008659282264,"GB2-06":69.37527854165438,"GB2-07":66.57390714240803,"GB2-08":71.97027545718792},"medium":{"GB2-01":62.648147498218734,"GB2-02":50.280474932360896,"GB2-03":57.7578446812102,"GB2-04":57.36629461091437,"GB2-05":49.49736873476317,"GB2-06":27.83929602727124,"GB2-07":45.69218768820833,"GB2-08":59.20929315043867},"none":{"GB2-01":42.3833654874061,"GB2-02":43.42787645087579,"GB2-03":45.069051805591876,"GB2-04":49.556951056714176,"GB2-05":51.780648025130716,"GB2-06":43.237630895783106,"GB2-07":39.8636015069682,"GB2-08":32.4095847187772}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:44:03Z","reasoning":{"highest":68.31441774985693,"medium":47.07163936185269,"none":41.48973032726808},"reasoning_agg":{"highest":{"max":73.91105484821749,"mean":68.31441774985693,"min":58.6019384322153},"medium":{"max":59.20929315043867,"mean":47.07163936185269,"min":27.83929602727124},"none":{"max":51.780648025130716,"mean":41.48973032726808,"min":21.60638981251813}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.824687422588852}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:42f90a18a2f021f0","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-2026-10-09":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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.262825}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"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-2026-10-09":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-2026-10-09":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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":7.449890000000001}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":1.38945,"mean":0.43567666666666666,"median":0.20305499999999999,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":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":57.68068743300843,"highest":72.99264071629241,"medium":48.73330135822544,"none":48.85047083825833},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1,"infra_failures_excluded":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":55.52995598701497,"score":55.52995598701497},"GB2-02":{"attempts":3,"playable":53.640108881910415,"score":53.640108881910415},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":31.47375565448167,"score":10.491251884827223},"GB2-04":{"attempts":3,"playable":52.06913715980093,"score":52.06913715980093},"GB2-05":{"attempts":3,"playable":40.01199152919056,"score":40.01199152919056},"GB2-06":{"attempts":3,"playable":70.9810572381312,"score":70.9810572381312},"GB2-07":{"attempts":3,"playable":65.75641894696234,"score":65.75641894696234},"GB2-08":{"attempts":3,"playable":65.77614228804856,"score":65.77614228804856}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.64567486185582,"score":68.64567486185582},"GB2-02":{"attempts":1,"playable":79.37270717394055,"score":79.37270717394055},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":71.44538854507758,"score":71.44538854507758},"GB2-05":{"attempts":1,"playable":49.19920053295619,"score":49.19920053295619},"GB2-06":{"attempts":1,"playable":83.00080761782358,"score":83.00080761782358},"GB2-07":{"attempts":1,"playable":76.83990838735598,"score":76.83990838735598},"GB2-08":{"attempts":1,"playable":82.44479789503714,"score":82.44479789503714}},"medium":{"GB2-01":{"attempts":1,"playable":41.45333547965778,"score":41.45333547965778},"GB2-02":{"attempts":1,"playable":42.1189694736707,"score":42.1189694736707},"GB2-03":{"attempts":1,"playable":31.47375565448167,"score":31.47375565448167},"GB2-04":{"attempts":1,"playable":42.70532989027744,"score":42.70532989027744},"GB2-05":{"attempts":1,"playable":48.383868411977794,"score":48.383868411977794},"GB2-06":{"attempts":1,"playable":81.27604364988733,"score":81.27604364988733},"GB2-07":{"attempts":1,"playable":68.69705558865459,"score":68.69705558865459},"GB2-08":{"attempts":1,"playable":33.75805271719621,"score":33.75805271719621}},"none":{"GB2-01":{"attempts":1,"playable":56.49085761953131,"score":56.49085761953131},"GB2-02":{"attempts":1,"playable":39.42864999811999,"score":39.42864999811999},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.05669304404778,"score":42.05669304404778},"GB2-05":{"attempts":1,"playable":22.452905642637685,"score":22.452905642637685},"GB2-06":{"attempts":1,"playable":48.66632044668269,"score":48.66632044668269},"GB2-07":{"attempts":1,"playable":51.73229286487649,"score":51.73229286487649},"GB2-08":{"attempts":1,"playable":81.12557625191234,"score":81.12557625191234}}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-10-22T10:32:14Z","match_totals_all":{"draws":2417,"losses":3573,"wins":4680},"match_totals_tracks":{"highest":{"draws":470,"losses":720,"wins":2210},"medium":{"draws":1180,"losses":1445,"wins":1243},"none":{"draws":767,"losses":1408,"wins":1227}},"model_slug":"claude-opus-4-8","overall":{"max":83.00080761782358,"mean":51.78200798948578,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.64567486185582,"GB2-02":79.37270717394055,"GB2-04":71.44538854507758,"GB2-05":49.19920053295619,"GB2-06":83.00080761782358,"GB2-07":76.83990838735598,"GB2-08":82.44479789503714},"per_game_all":{"GB2-01":55.52995598701497,"GB2-02":53.640108881910415,"GB2-04":52.06913715980093,"GB2-05":40.01199152919056,"GB2-06":70.9810572381312,"GB2-07":65.75641894696234,"GB2-08":65.77614228804856},"per_game_match_totals_all":{"GB2-01":{"draws":239,"losses":556,"wins":669},"GB2-02":{"draws":865,"losses":217,"wins":284},"GB2-03":{"draws":147,"losses":260,"wins":61},"GB2-04":{"draws":828,"losses":279,"wins":305},"GB2-05":{"draws":0,"losses":921,"wins":593},"GB2-06":{"draws":66,"losses":410,"wins":958},"GB2-07":{"draws":0,"losses":528,"wins":962},"GB2-08":{"draws":272,"losses":402,"wins":848}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":65,"losses":128,"wins":295},"GB2-02":{"draws":174,"losses":11,"wins":269},"GB2-04":{"draws":201,"losses":39,"wins":230},"GB2-05":{"draws":0,"losses":261,"wins":245},"GB2-06":{"draws":29,"losses":71,"wins":378},"GB2-07":{"draws":0,"losses":117,"wins":379},"GB2-08":{"draws":1,"losses":93,"wins":414}},"medium":{"GB2-01":{"draws":70,"losses":259,"wins":159},"GB2-02":{"draws":370,"losses":85,"wins":1},"GB2-03":{"draws":147,"losses":260,"wins":61},"GB2-04":{"draws":315,"losses":118,"wins":39},"GB2-05":{"draws":0,"losses":266,"wins":238},"GB2-06":{"draws":9,"losses":91,"wins":378},"GB2-07":{"draws":0,"losses":160,"wins":338},"GB2-08":{"draws":269,"losses":206,"wins":29}},"none":{"GB2-01":{"draws":104,"losses":169,"wins":215},"GB2-02":{"draws":321,"losses":121,"wins":14},"GB2-04":{"draws":312,"losses":122,"wins":36},"GB2-05":{"draws":0,"losses":394,"wins":110},"GB2-06":{"draws":28,"losses":248,"wins":202},"GB2-07":{"draws":0,"losses":251,"wins":245},"GB2-08":{"draws":2,"losses":103,"wins":405}}},"per_game_raw_elo_all":{"GB2-01":1527.1040774841542,"GB2-02":1518.2724235312837,"GB2-04":1499.5568976726754,"GB2-05":1301.490442663562,"GB2-06":1798.3388425264845,"GB2-07":1667.4837228539834,"GB2-08":1689.8442280019624},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1658.633203523303,"GB2-02":1748.1200113140778,"GB2-04":1660.6621967640708,"GB2-05":1429.7942319472472,"GB2-06":2012.1458560034014,"GB2-07":1832.851615206258,"GB2-08":1932.7138519962123},"medium":{"GB2-01":1389.2636164795383,"GB2-02":1413.8657339322704,"GB2-03":1268.3171849985176,"GB2-04":1421.5277504738656,"GB2-05":1419.6537748824333,"GB2-06":1976.4806320137554,"GB2-07":1699.112158193268,"GB2-08":1234.5779236275846},"none":{"GB2-01":1533.415412449622,"GB2-02":1392.8315253475027,"GB2-04":1416.4807457800898,"GB2-05":1055.0233211610048,"GB2-06":1406.3900395622968,"GB2-07":1470.487395162424,"GB2-08":1902.2409083820905}},"per_game_tracks":{"highest":{"GB2-01":68.64567486185582,"GB2-02":79.37270717394055,"GB2-04":71.44538854507758,"GB2-05":49.19920053295619,"GB2-06":83.00080761782358,"GB2-07":76.83990838735598,"GB2-08":82.44479789503714},"medium":{"GB2-01":41.45333547965778,"GB2-02":42.1189694736707,"GB2-03":31.47375565448167,"GB2-04":42.70532989027744,"GB2-05":48.383868411977794,"GB2-06":81.27604364988733,"GB2-07":68.69705558865459,"GB2-08":33.75805271719621},"none":{"GB2-01":56.49085761953131,"GB2-02":39.42864999811999,"GB2-04":42.05669304404778,"GB2-05":22.452905642637685,"GB2-06":48.66632044668269,"GB2-07":51.73229286487649,"GB2-08":81.12557625191234}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:44:13Z","reasoning":{"highest":63.86856062675586,"medium":48.73330135822544,"none":42.74416198347604},"reasoning_agg":{"highest":{"max":83.00080761782358,"mean":63.86856062675586,"min":0.0},"medium":{"max":81.27604364988733,"mean":48.73330135822544,"min":31.47375565448167},"none":{"max":81.12557625191234,"mean":42.74416198347604,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":21.124398643279818}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:e7f24008d4acccc0","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":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":true,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478314},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.12650943660072694,"mean":0.07695988119919009,"median":0.07334251535992004,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":14,"run_count":16,"token_priced_attempt_count":11,"total":1.2313580991870416}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"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":1.5865090123478316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"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":true,"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":4.982416500000001},"codegen_output_tokens":{"attempt_count":32,"output_max":60921,"output_mean":18651.916666666668,"output_min":1790,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":60921,"output_mean":31693.5,"output_min":21144,"run_count":8},"medium":{"attempt_count":10,"output_max":28586,"output_mean":21214.875,"output_min":16507,"run_count":8},"none":{"attempt_count":11,"output_max":4623,"output_mean":3047.375,"output_min":1790,"run_count":8}},"display_name":"Gemini 3.5 Flash","economics":{"all":52.46888179455375,"highest":64.08847651108383,"medium":57.08199111204054,"none":36.23617776053691},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":11,"first_pass_rate":0.6875,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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":3,"repaired_rate":0.1875},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":4,"playable":71.20639717702915,"score":71.20639717702915},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":49.11738649959836,"score":42.52297338630776},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":55.29913356226074,"score":51.322972241853286},"GB2-04":{"attempts":4,"playable":45.50715037300365,"score":45.50715037300365},"GB2-05":{"attempts":4,"playable":45.196987389544425,"score":45.196987389544425},"GB2-06":{"attempts":4,"playable":63.19662855715598,"score":63.19662855715598},"GB2-07":{"attempts":4,"playable":50.57529838224523,"score":50.57529838224523},"GB2-08":{"attempts":4,"playable":39.6520724155925,"score":39.6520724155925}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":90.34074689731555,"score":90.34074689731555},"GB2-02":{"attempts":1,"playable":62.433786333483454,"score":62.433786333483454},"GB2-03":{"attempts":1,"playable":72.35897676764579,"score":72.35897676764579},"GB2-04":{"attempts":1,"playable":40.01158363915807,"score":40.01158363915807},"GB2-05":{"attempts":1,"playable":52.41090399377879,"score":52.41090399377879},"GB2-06":{"attempts":1,"playable":75.6377844183594,"score":75.6377844183594},"GB2-07":{"attempts":1,"playable":51.750771270351436,"score":51.750771270351436},"GB2-08":{"attempts":1,"playable":67.76325876857805,"score":67.76325876857805}},"medium":{"GB2-01":{"attempts":1,"playable":73.60228925045058,"score":73.60228925045058},"GB2-02":{"attempts":1,"playable":45.351894485568,"score":45.351894485568},"GB2-03":{"attempts":1,"playable":69.68145599669172,"score":69.68145599669172},"GB2-04":{"attempts":1,"playable":54.55783065584552,"score":54.55783065584552},"GB2-05":{"attempts":1,"playable":66.99498326041135,"score":66.99498326041135},"GB2-06":{"attempts":1,"playable":73.70168498504874,"score":73.70168498504874},"GB2-07":{"attempts":1,"playable":54.36213824632854,"score":54.36213824632854},"GB2-08":{"attempts":1,"playable":18.40365201597985,"score":18.40365201597985}},"none":{"GB2-01":{"attempts":2,"playable":49.67615538332133,"score":49.67615538332133},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.56647867974363,"score":19.783239339871816},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":23.856967922444703,"score":11.928483961222351},"GB2-04":{"attempts":2,"playable":41.95203682400736,"score":41.95203682400736},"GB2-05":{"attempts":2,"playable":16.185074914443145,"score":16.185074914443145},"GB2-06":{"attempts":2,"playable":40.25041626805981,"score":40.25041626805981},"GB2-07":{"attempts":2,"playable":45.61298563005572,"score":45.61298563005572},"GB2-08":{"attempts":2,"playable":32.7893064622196,"score":32.7893064622196}}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:29:16Z","match_totals_all":{"draws":3260,"losses":5962,"wins":5322},"match_totals_tracks":{"highest":{"draws":652,"losses":1128,"wins":2092},"medium":{"draws":875,"losses":1291,"wins":1700},"none":{"draws":1733,"losses":3543,"wins":1530}},"model_slug":"google-gemini-3-5-flash","overall":{"max":90.34074689731555,"mean":51.147559990341506,"min":11.928483961222351},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":90.34074689731555,"GB2-02":62.433786333483454,"GB2-03":72.35897676764579,"GB2-04":40.01158363915807,"GB2-05":52.41090399377879,"GB2-06":75.6377844183594,"GB2-07":51.750771270351436,"GB2-08":67.76325876857805},"per_game_all":{"GB2-01":71.20639717702915,"GB2-02":49.11738649959836,"GB2-03":55.29913356226074,"GB2-04":45.50715037300365,"GB2-05":45.196987389544425,"GB2-06":63.19662855715598,"GB2-07":50.57529838224523,"GB2-08":39.6520724155925},"per_game_match_totals_all":{"GB2-01":{"draws":208,"losses":589,"wins":1155},"GB2-02":{"draws":992,"losses":218,"wins":162},"GB2-03":{"draws":149,"losses":593,"wins":662},"GB2-04":{"draws":1133,"losses":499,"wins":250},"GB2-05":{"draws":0,"losses":1275,"wins":747},"GB2-06":{"draws":36,"losses":831,"wins":1045},"GB2-07":{"draws":0,"losses":1042,"wins":934},"GB2-08":{"draws":742,"losses":915,"wins":367}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":40,"wins":427},"GB2-02":{"draws":256,"losses":50,"wins":154},"GB2-03":{"draws":39,"losses":123,"wins":306},"GB2-04":{"draws":250,"losses":165,"wins":57},"GB2-05":{"draws":0,"losses":246,"wins":258},"GB2-06":{"draws":11,"losses":118,"wins":349},"GB2-07":{"draws":0,"losses":250,"wins":246},"GB2-08":{"draws":75,"losses":136,"wins":295}},"medium":{"GB2-01":{"draws":12,"losses":130,"wins":346},"GB2-02":{"draws":390,"losses":60,"wins":6},"GB2-03":{"draws":42,"losses":136,"wins":290},"GB2-04":{"draws":269,"losses":85,"wins":116},"GB2-05":{"draws":0,"losses":172,"wins":332},"GB2-06":{"draws":14,"losses":126,"wins":338},"GB2-07":{"draws":0,"losses":237,"wins":259},"GB2-08":{"draws":148,"losses":345,"wins":13}},"none":{"GB2-01":{"draws":175,"losses":419,"wins":382},"GB2-02":{"draws":346,"losses":108,"wins":2},"GB2-03":{"draws":68,"losses":334,"wins":66},"GB2-04":{"draws":614,"losses":249,"wins":77},"GB2-05":{"draws":0,"losses":857,"wins":157},"GB2-06":{"draws":11,"losses":587,"wins":358},"GB2-07":{"draws":0,"losses":555,"wins":429},"GB2-08":{"draws":519,"losses":434,"wins":59}}},"per_game_raw_elo_all":{"GB2-01":1726.489055353811,"GB2-02":1469.148125347243,"GB2-03":1493.2971921874607,"GB2-04":1443.194778057338,"GB2-05":1358.2999294771498,"GB2-06":1659.115344778228,"GB2-07":1456.2440053867729,"GB2-08":1309.2941615837797},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1994.8115363723537,"GB2-02":1574.6699412687317,"GB2-03":1660.2521533407626,"GB2-04":1400.470855265867,"GB2-05":1469.8424655900387,"GB2-06":1866.169659247766,"GB2-07":1470.7198269247856,"GB2-08":1643.5448960375832},"medium":{"GB2-01":1716.1461683629059,"GB2-02":1438.8576387195558,"GB2-03":1627.3506661518306,"GB2-04":1513.5253923364075,"GB2-05":1667.5855411123218,"GB2-06":1829.7459345441548,"GB2-07":1503.7727806780288,"GB2-08":1059.795904140139},"none":{"GB2-01":1468.509461326174,"GB2-02":1393.9167960534419,"GB2-03":1192.2887570697892,"GB2-04":1415.5880865697388,"GB2-05":937.4717817290887,"GB2-06":1281.430440542763,"GB2-07":1394.2394085575038,"GB2-08":1224.5416845736163}},"per_game_tracks":{"highest":{"GB2-01":90.34074689731555,"GB2-02":62.433786333483454,"GB2-03":72.35897676764579,"GB2-04":40.01158363915807,"GB2-05":52.41090399377879,"GB2-06":75.6377844183594,"GB2-07":51.750771270351436,"GB2-08":67.76325876857805},"medium":{"GB2-01":73.60228925045058,"GB2-02":45.351894485568,"GB2-03":69.68145599669172,"GB2-04":54.55783065584552,"GB2-05":66.99498326041135,"GB2-06":73.70168498504874,"GB2-07":54.36213824632854,"GB2-08":18.40365201597985},"none":{"GB2-01":49.67615538332133,"GB2-02":39.56647867974363,"GB2-03":23.856967922444703,"GB2-04":41.95203682400736,"GB2-05":16.185074914443145,"GB2-06":40.25041626805981,"GB2-07":45.61298563005572,"GB2-08":32.7893064622196}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:45:23Z","reasoning":{"highest":64.08847651108383,"medium":57.08199111204054,"none":32.27221234790014},"reasoning_agg":{"highest":{"max":90.34074689731555,"mean":64.08847651108383,"min":40.01158363915807},"medium":{"max":73.70168498504874,"mean":57.08199111204054,"min":18.40365201597985},"none":{"max":49.67615538332133,"mean":32.27221234790014,"min":11.928483961222351}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":31.81626416318369}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:91bf40a637189255","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-2026-10-09":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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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-2026-10-09":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-2026-10-09":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-2026-10-09":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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475000000003}},"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-2026-10-09":26},"run_count":24,"token_priced_attempt_count":26,"total":26.566349999999996},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":55.763588312471335,"highest":69.43670543467681,"medium":53.01913155120914,"none":42.97663124158816},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":65.39551540849862,"score":65.39551540849862},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":48.46498885679359,"score":32.30999257119573},"GB2-03":{"attempts":3,"playable":43.29097767402077,"score":43.29097767402077},"GB2-04":{"attempts":3,"playable":39.38292627551175,"score":39.38292627551175},"GB2-05":{"attempts":3,"playable":68.62072330007364,"score":68.62072330007364},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":55.18592090272843,"score":36.79061393515229},"GB2-07":{"attempts":3,"playable":62.37760711797288,"score":62.37760711797288},"GB2-08":{"attempts":3,"playable":55.51378009875032,"score":55.51378009875032}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.02996311896685,"score":80.02996311896685},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":51.400574059966154,"score":51.400574059966154},"GB2-04":{"attempts":1,"playable":36.22454958828693,"score":36.22454958828693},"GB2-05":{"attempts":1,"playable":76.67668232448622,"score":76.67668232448622},"GB2-06":{"attempts":1,"playable":80.98192479824989,"score":80.98192479824989},"GB2-07":{"attempts":1,"playable":87.41123345212185,"score":87.41123345212185},"GB2-08":{"attempts":1,"playable":73.33201070065978,"score":73.33201070065978}},"medium":{"GB2-01":{"attempts":1,"playable":64.90957596246812,"score":64.90957596246812},"GB2-02":{"attempts":1,"playable":55.16102118018552,"score":55.16102118018552},"GB2-03":{"attempts":1,"playable":39.96192170766266,"score":39.96192170766266},"GB2-04":{"attempts":1,"playable":39.965920758045456,"score":39.965920758045456},"GB2-05":{"attempts":1,"playable":76.71097862863417,"score":76.71097862863417},"GB2-06":{"attempts":1,"playable":29.38991700720696,"score":29.38991700720696},"GB2-07":{"attempts":1,"playable":61.3855713497928,"score":61.3855713497928},"GB2-08":{"attempts":1,"playable":56.66814581567745,"score":56.66814581567745}},"none":{"GB2-01":{"attempts":1,"playable":51.247007144060895,"score":51.247007144060895},"GB2-02":{"attempts":1,"playable":41.768956533401656,"score":41.768956533401656},"GB2-03":{"attempts":1,"playable":38.510437254433505,"score":38.510437254433505},"GB2-04":{"attempts":1,"playable":41.95830848020285,"score":41.95830848020285},"GB2-05":{"attempts":1,"playable":52.47450894710052,"score":52.47450894710052},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":38.33601655200399,"score":38.33601655200399},"GB2-08":{"attempts":1,"playable":36.541183779913716,"score":36.541183779913716}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:59:28Z","match_totals_all":{"draws":3210,"losses":3336,"wins":4122},"match_totals_tracks":{"highest":{"draws":685,"losses":726,"wins":2001},"medium":{"draws":1178,"losses":1293,"wins":1401},"none":{"draws":1347,"losses":1317,"wins":720}},"model_slug":"gpt-5-5","overall":{"max":87.41123345212185,"mean":50.460267047646994,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.02996311896685,"GB2-03":51.400574059966154,"GB2-04":36.22454958828693,"GB2-05":76.67668232448622,"GB2-06":80.98192479824989,"GB2-07":87.41123345212185,"GB2-08":73.33201070065978},"per_game_all":{"GB2-01":65.39551540849862,"GB2-03":43.29097767402077,"GB2-04":39.38292627551175,"GB2-05":68.62072330007364,"GB2-07":62.37760711797288,"GB2-08":55.51378009875032},"per_game_match_totals_all":{"GB2-01":{"draws":692,"losses":181,"wins":593},"GB2-02":{"draws":663,"losses":151,"wins":98},"GB2-03":{"draws":429,"losses":628,"wins":347},"GB2-04":{"draws":833,"losses":455,"wins":122},"GB2-05":{"draws":0,"losses":494,"wins":1024},"GB2-06":{"draws":43,"losses":426,"wins":487},"GB2-07":{"draws":0,"losses":573,"wins":907},"GB2-08":{"draws":550,"losses":428,"wins":544}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":122,"losses":40,"wins":326},"GB2-03":{"draws":140,"losses":173,"wins":155},"GB2-04":{"draws":273,"losses":168,"wins":29},"GB2-05":{"draws":0,"losses":122,"wins":384},"GB2-06":{"draws":32,"losses":79,"wins":367},"GB2-07":{"draws":0,"losses":61,"wins":435},"GB2-08":{"draws":118,"losses":83,"wins":305}},"medium":{"GB2-01":{"draws":271,"losses":43,"wins":176},"GB2-02":{"draws":296,"losses":63,"wins":97},"GB2-03":{"draws":159,"losses":217,"wins":92},"GB2-04":{"draws":272,"losses":152,"wins":46},"GB2-05":{"draws":0,"losses":125,"wins":381},"GB2-06":{"draws":11,"losses":347,"wins":120},"GB2-07":{"draws":0,"losses":197,"wins":295},"GB2-08":{"draws":169,"losses":149,"wins":194}},"none":{"GB2-01":{"draws":299,"losses":98,"wins":91},"GB2-02":{"draws":367,"losses":88,"wins":1},"GB2-03":{"draws":130,"losses":238,"wins":100},"GB2-04":{"draws":288,"losses":135,"wins":47},"GB2-05":{"draws":0,"losses":247,"wins":259},"GB2-07":{"draws":0,"losses":315,"wins":177},"GB2-08":{"draws":263,"losses":196,"wins":45}}},"per_game_raw_elo_all":{"GB2-01":1634.204245552902,"GB2-03":1373.8025052460328,"GB2-04":1395.360941741964,"GB2-05":1718.5983470746844,"GB2-07":1662.0350076988962,"GB2-08":1496.354842066962},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1801.4241416288255,"GB2-03":1444.6921032516304,"GB2-04":1370.2573354196793,"GB2-05":1842.2068125280841,"GB2-06":1970.5141451635563,"GB2-07":2087.072298128353,"GB2-08":1741.3083237383564},"medium":{"GB2-01":1618.3185907138175,"GB2-02":1515.01921690413,"GB2-03":1344.7293969491416,"GB2-04":1400.1113941296023,"GB2-05":1842.948869065031,"GB2-06":1113.6739432984537,"GB2-07":1595.6455798431505,"GB2-08":1484.5413752189525},"none":{"GB2-01":1482.8700043160638,"GB2-02":1411.1447845644686,"GB2-03":1331.9860155373262,"GB2-04":1415.7140956766104,"GB2-05":1470.6393596309385,"GB2-07":1303.3871451251848,"GB2-08":1263.2148272435768}},"per_game_tracks":{"highest":{"GB2-01":80.02996311896685,"GB2-03":51.400574059966154,"GB2-04":36.22454958828693,"GB2-05":76.67668232448622,"GB2-06":80.98192479824989,"GB2-07":87.41123345212185,"GB2-08":73.33201070065978},"medium":{"GB2-01":64.90957596246812,"GB2-02":55.16102118018552,"GB2-03":39.96192170766266,"GB2-04":39.965920758045456,"GB2-05":76.71097862863417,"GB2-06":29.38991700720696,"GB2-07":61.3855713497928,"GB2-08":56.66814581567745},"none":{"GB2-01":51.247007144060895,"GB2-02":41.768956533401656,"GB2-03":38.510437254433505,"GB2-04":41.95830848020285,"GB2-05":52.47450894710052,"GB2-07":38.33601655200399,"GB2-08":36.541183779913716}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:36:29Z","reasoning":{"highest":60.75711725534221,"medium":53.01913155120914,"none":37.60455233638964},"reasoning_agg":{"highest":{"max":87.41123345212185,"mean":60.75711725534221,"min":0.0},"medium":{"max":76.71097862863417,"mean":53.01913155120914,"min":29.38991700720696},"none":{"max":52.47450894710052,"mean":37.60455233638964,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":23.15256491895257}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:2fc81688d26723c1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"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":true,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.8354799999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.8354799999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"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":true,"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":6.45275},"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":51.032098124595194,"highest":54.175022202815086,"medium":50.56135528595664,"none":48.359916885013874},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":10,"failed_game_aliases":["GB2-02"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1,"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1,"performance_rejections":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-02","GB2-06","GB2-08"],"infra_failures_excluded":3,"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},"performance_rejected_game_aliases":["GB2-04"],"performance_rejections":1}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":33.90546601133974,"score":33.90546601133974},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":45.199861791910685,"score":36.55065312710921},"GB2-03":{"attempts":3,"playable":51.06690873708641,"score":51.06690873708641},"GB2-04":{"attempts":3,"playable":48.86555387257395,"score":48.86555387257395},"GB2-05":{"attempts":3,"playable":68.64862563664944,"score":68.64862563664944},"GB2-06":{"attempts":3,"playable":40.81461813487805,"score":40.81461813487805},"GB2-07":{"attempts":3,"playable":63.31172523027865,"score":63.31172523027865},"GB2-08":{"attempts":3,"playable":56.444025582044674,"score":56.444025582044674}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":33.01792048480009,"score":33.01792048480009},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":51.89525198880889,"score":25.947625994404444},"GB2-03":{"attempts":1,"playable":58.55870683970308,"score":58.55870683970308},"GB2-04":{"attempts":1,"playable":66.15873106524892,"score":66.15873106524892},"GB2-05":{"attempts":1,"playable":47.19106366334805,"score":47.19106366334805},"GB2-06":{"attempts":1,"playable":51.805344259547816,"score":51.805344259547816},"GB2-07":{"attempts":1,"playable":78.0576724667452,"score":78.0576724667452},"GB2-08":{"attempts":1,"playable":46.71548685431869,"score":46.71548685431869}},"medium":{"GB2-01":{"attempts":1,"playable":41.586291986960624,"score":41.586291986960624},"GB2-02":{"attempts":1,"playable":43.15321726645065,"score":43.15321726645065},"GB2-03":{"attempts":1,"playable":56.05474521975925,"score":56.05474521975925},"GB2-04":{"attempts":1,"playable":38.21860763463399,"score":38.21860763463399},"GB2-05":{"attempts":1,"playable":68.27349062784455,"score":68.27349062784455},"GB2-06":{"attempts":1,"playable":49.878611834242065,"score":49.878611834242065},"GB2-07":{"attempts":1,"playable":39.645567001995445,"score":39.645567001995445},"GB2-08":{"attempts":1,"playable":67.68031071576648,"score":67.68031071576648}},"none":{"GB2-01":{"attempts":1,"playable":27.11218556225851,"score":27.11218556225851},"GB2-02":{"attempts":1,"playable":40.55111612047252,"score":40.55111612047252},"GB2-03":{"attempts":1,"playable":38.587274151796905,"score":38.587274151796905},"GB2-04":{"attempts":1,"playable":42.21932291783895,"score":42.21932291783895},"GB2-05":{"attempts":1,"playable":90.48132261875571,"score":90.48132261875571},"GB2-06":{"attempts":1,"playable":20.75989831084429,"score":20.75989831084429},"GB2-07":{"attempts":1,"playable":72.2319362220953,"score":72.2319362220953},"GB2-08":{"attempts":1,"playable":54.93627917604886,"score":54.93627917604886}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-10-22T10:36:59Z","match_totals_all":{"draws":3118,"losses":4303,"wins":4189},"match_totals_tracks":{"highest":{"draws":927,"losses":1377,"wins":1564},"medium":{"draws":1057,"losses":1453,"wins":1358},"none":{"draws":1134,"losses":1473,"wins":1267}},"model_slug":"qwen-qwen3-8-max","overall":{"max":90.48132261875571,"mean":49.95094704149502,"min":20.75989831084429},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":33.01792048480009,"GB2-02":51.89525198880889,"GB2-03":58.55870683970308,"GB2-04":66.15873106524892,"GB2-05":47.19106366334805,"GB2-06":51.805344259547816,"GB2-07":78.0576724667452,"GB2-08":46.71548685431869},"per_game_all":{"GB2-01":33.90546601133974,"GB2-02":45.199861791910685,"GB2-03":51.06690873708641,"GB2-04":48.86555387257395,"GB2-05":68.64862563664944,"GB2-06":40.81461813487805,"GB2-07":63.31172523027865,"GB2-08":56.444025582044674},"per_game_match_totals_all":{"GB2-01":{"draws":369,"losses":804,"wins":295},"GB2-02":{"draws":1032,"losses":251,"wins":85},"GB2-03":{"draws":293,"losses":589,"wins":522},"GB2-04":{"draws":812,"losses":332,"wins":268},"GB2-05":{"draws":0,"losses":486,"wins":1030},"GB2-06":{"draws":103,"losses":840,"wins":491},"GB2-07":{"draws":0,"losses":560,"wins":922},"GB2-08":{"draws":509,"losses":441,"wins":576}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":94,"losses":287,"wins":109},"GB2-02":{"draws":333,"losses":58,"wins":65},"GB2-03":{"draws":35,"losses":194,"wins":239},"GB2-04":{"draws":196,"losses":66,"wins":208},"GB2-05":{"draws":0,"losses":272,"wins":232},"GB2-06":{"draws":41,"losses":224,"wins":213},"GB2-07":{"draws":0,"losses":112,"wins":384},"GB2-08":{"draws":228,"losses":164,"wins":114}},"medium":{"GB2-01":{"draws":159,"losses":212,"wins":117},"GB2-02":{"draws":364,"losses":84,"wins":8},"GB2-03":{"draws":97,"losses":173,"wins":198},"GB2-04":{"draws":314,"losses":140,"wins":18},"GB2-05":{"draws":0,"losses":166,"wins":340},"GB2-06":{"draws":38,"losses":237,"wins":203},"GB2-07":{"draws":0,"losses":309,"wins":185},"GB2-08":{"draws":85,"losses":132,"wins":289}},"none":{"GB2-01":{"draws":116,"losses":305,"wins":69},"GB2-02":{"draws":335,"losses":109,"wins":12},"GB2-03":{"draws":161,"losses":222,"wins":85},"GB2-04":{"draws":302,"losses":126,"wins":42},"GB2-05":{"draws":0,"losses":48,"wins":458},"GB2-06":{"draws":24,"losses":379,"wins":75},"GB2-07":{"draws":0,"losses":139,"wins":353},"GB2-08":{"draws":196,"losses":145,"wins":173}}},"per_game_raw_elo_all":{"GB2-01":1312.4001481175142,"GB2-02":1437.6361828511838,"GB2-03":1443.3030432384585,"GB2-04":1471.516472787347,"GB2-05":1791.237770691432,"GB2-06":1286.585137783875,"GB2-07":1643.1610203355988,"GB2-08":1491.518860258737},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1305.245285612385,"GB2-02":1489.3800003567055,"GB2-03":1510.3833595396077,"GB2-04":1610.526139959846,"GB2-05":1404.807753289723,"GB2-06":1455.3419122399596,"GB2-07":1855.724703564798,"GB2-08":1369.2798994709246},"medium":{"GB2-01":1390.5487342333222,"GB2-02":1421.8848777890605,"GB2-03":1486.8630022604675,"GB2-04":1386.2759325589018,"GB2-05":1687.6004783945384,"GB2-06":1425.2120876669715,"GB2-07":1319.8785785575105,"GB2-08":1642.1891081766664},"none":{"GB2-01":1241.4064245068353,"GB2-02":1401.6436704077855,"GB2-03":1332.6627679153,"GB2-04":1417.7473458432935,"GB2-05":2281.305080390034,"GB2-06":979.2014134446941,"GB2-07":1753.8797788844881,"GB2-08":1463.0875731286208}},"per_game_tracks":{"highest":{"GB2-01":33.01792048480009,"GB2-02":51.89525198880889,"GB2-03":58.55870683970308,"GB2-04":66.15873106524892,"GB2-05":47.19106366334805,"GB2-06":51.805344259547816,"GB2-07":78.0576724667452,"GB2-08":46.71548685431869},"medium":{"GB2-01":41.586291986960624,"GB2-02":43.15321726645065,"GB2-03":56.05474521975925,"GB2-04":38.21860763463399,"GB2-05":68.27349062784455,"GB2-06":49.878611834242065,"GB2-07":39.645567001995445,"GB2-08":67.68031071576648},"none":{"GB2-01":27.11218556225851,"GB2-02":40.55111612047252,"GB2-03":38.587274151796905,"GB2-04":42.21932291783895,"GB2-05":90.48132261875571,"GB2-06":20.75989831084429,"GB2-07":72.2319362220953,"GB2-08":54.93627917604886}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:17:45Z","reasoning":{"highest":50.931568953514535,"medium":50.56135528595664,"none":48.359916885013874},"reasoning_agg":{"highest":{"max":78.0576724667452,"mean":50.931568953514535,"min":25.947625994404444},"medium":{"max":68.27349062784455,"mean":50.56135528595664,"min":38.21860763463399},"none":{"max":90.48132261875571,"mean":48.359916885013874,"min":20.75989831084429}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":2.5716520685006614}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:7f30fe95c34317c7","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":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.007622525,"mean":0.0031813812500000004,"median":0.0022472374999999998,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.02545105}},"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":0.030688900000000005},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.007622525,"mean":0.0031813812500000004,"median":0.0022472374999999998,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.025451049999999996},"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":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.00625249375,"median":0.0043227375,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16,"boardgame-list-prices-2026-10-09":11},"run_count":24,"token_priced_attempt_count":27,"total":0.15005985000000002},"codegen_latency_ms":{"attempt_count":11,"max_ms":86701,"mean_ms":33803.25,"min_ms":21457,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":86701,"mean_ms":33803.25,"min_ms":21457,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":26534,"output_mean":10296.416666666666,"output_min":1575,"run_count":24},"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":11,"output_max":9509,"output_mean":3610.5,"output_min":1575,"run_count":8}},"display_name":"GPT-6 Luna","economics":{"all":48.89082038989473,"highest":57.50156969812907,"medium":44.10669904492882,"none":45.06419242662629},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[65536,128000],"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,"requested_max_output_token_observations":27,"requested_max_output_tokens":[65536,128000],"total_output_tokens":247114,"total_reasoning_output_tokens":163396,"total_visible_output_tokens":83718,"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-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":38.73297473717107,"score":38.73297473717107},"GB2-02":{"attempts":3,"playable":50.54062903849465,"score":50.54062903849465},"GB2-03":{"attempts":3,"playable":49.08852246465713,"score":49.08852246465713},"GB2-04":{"attempts":3,"playable":53.0508524686962,"score":53.0508524686962},"GB2-05":{"attempts":3,"playable":46.94035000356384,"score":46.94035000356384},"GB2-06":{"attempts":3,"playable":64.33952023130435,"score":64.33952023130435},"GB2-07":{"attempts":3,"playable":42.17965120815088,"score":42.17965120815088},"GB2-08":{"attempts":3,"playable":46.25406296711967,"score":46.25406296711967}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":29.562035574308894,"score":29.562035574308894},"GB2-02":{"attempts":1,"playable":62.73997881732375,"score":62.73997881732375},"GB2-03":{"attempts":1,"playable":49.705727730027796,"score":49.705727730027796},"GB2-04":{"attempts":1,"playable":63.67208990961923,"score":63.67208990961923},"GB2-05":{"attempts":1,"playable":54.35297855687203,"score":54.35297855687203},"GB2-06":{"attempts":1,"playable":86.16758011832168,"score":86.16758011832168},"GB2-07":{"attempts":1,"playable":38.74280635717264,"score":38.74280635717264},"GB2-08":{"attempts":1,"playable":75.06936052138656,"score":75.06936052138656}},"medium":{"GB2-01":{"attempts":1,"playable":38.64577928238832,"score":38.64577928238832},"GB2-02":{"attempts":1,"playable":44.6921769781043,"score":44.6921769781043},"GB2-03":{"attempts":1,"playable":51.155041629475676,"score":51.155041629475676},"GB2-04":{"attempts":1,"playable":51.01516185929073,"score":51.01516185929073},"GB2-05":{"attempts":1,"playable":50.69627270463538,"score":50.69627270463538},"GB2-06":{"attempts":1,"playable":34.50556905609082,"score":34.50556905609082},"GB2-07":{"attempts":1,"playable":54.05257950614269,"score":54.05257950614269},"GB2-08":{"attempts":1,"playable":28.091011343302547,"score":28.091011343302547}},"none":{"GB2-01":{"attempts":1,"playable":47.99110935481599,"score":47.99110935481599},"GB2-02":{"attempts":1,"playable":44.189731320055884,"score":44.189731320055884},"GB2-03":{"attempts":1,"playable":46.404798034467916,"score":46.404798034467916},"GB2-04":{"attempts":1,"playable":44.465305637178616,"score":44.465305637178616},"GB2-05":{"attempts":1,"playable":35.77179874918413,"score":35.77179874918413},"GB2-06":{"attempts":1,"playable":72.34541151950053,"score":72.34541151950053},"GB2-07":{"attempts":1,"playable":33.74356776113729,"score":33.74356776113729},"GB2-08":{"attempts":1,"playable":35.60181703666993,"score":35.60181703666993}}},"id":"gpt-6-luna","is_recent_addition":false,"last_measured_at":"2026-10-22T10:56:42Z","match_totals_all":{"draws":3021,"losses":4635,"wins":3942},"match_totals_tracks":{"highest":{"draws":555,"losses":1435,"wins":1880},"medium":{"draws":1190,"losses":1646,"wins":1034},"none":{"draws":1276,"losses":1554,"wins":1028}},"model_slug":"gpt-6-luna","overall":{"max":86.16758011832168,"mean":48.890820389894735,"min":28.091011343302547},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.562035574308894,"GB2-02":62.73997881732375,"GB2-03":49.705727730027796,"GB2-04":63.67208990961923,"GB2-05":54.35297855687203,"GB2-06":86.16758011832168,"GB2-07":38.74280635717264,"GB2-08":75.06936052138656},"per_game_all":{"GB2-01":38.73297473717107,"GB2-02":50.54062903849465,"GB2-03":49.08852246465713,"GB2-04":53.0508524686962,"GB2-05":46.94035000356384,"GB2-06":64.33952023130435,"GB2-07":42.17965120815088,"GB2-08":46.25406296711967},"per_game_match_totals_all":{"GB2-01":{"draws":450,"losses":695,"wins":321},"GB2-02":{"draws":1006,"losses":190,"wins":166},"GB2-03":{"draws":199,"losses":666,"wins":543},"GB2-04":{"draws":805,"losses":278,"wins":329},"GB2-05":{"draws":0,"losses":816,"wins":696},"GB2-06":{"draws":70,"losses":500,"wins":862},"GB2-07":{"draws":0,"losses":893,"wins":593},"GB2-08":{"draws":491,"losses":597,"wins":432}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":350,"wins":137},"GB2-02":{"draws":259,"losses":45,"wins":150},"GB2-03":{"draws":22,"losses":242,"wins":206},"GB2-04":{"draws":220,"losses":67,"wins":183},"GB2-05":{"draws":0,"losses":237,"wins":267},"GB2-06":{"draws":26,"losses":54,"wins":398},"GB2-07":{"draws":0,"losses":320,"wins":182},"GB2-08":{"draws":27,"losses":120,"wins":357}},"medium":{"GB2-01":{"draws":183,"losses":216,"wins":91},"GB2-02":{"draws":375,"losses":71,"wins":8},"GB2-03":{"draws":93,"losses":199,"wins":178},"GB2-04":{"draws":276,"losses":98,"wins":96},"GB2-05":{"draws":0,"losses":253,"wins":251},"GB2-06":{"draws":22,"losses":318,"wins":138},"GB2-07":{"draws":0,"losses":234,"wins":258},"GB2-08":{"draws":241,"losses":257,"wins":14}},"none":{"GB2-01":{"draws":266,"losses":129,"wins":93},"GB2-02":{"draws":372,"losses":74,"wins":8},"GB2-03":{"draws":84,"losses":225,"wins":159},"GB2-04":{"draws":309,"losses":113,"wins":50},"GB2-05":{"draws":0,"losses":326,"wins":178},"GB2-06":{"draws":22,"losses":128,"wins":326},"GB2-07":{"draws":0,"losses":339,"wins":153},"GB2-08":{"draws":223,"losses":220,"wins":61}}},"per_game_raw_elo_all":{"GB2-01":1360.7814448558906,"GB2-02":1480.3205776128245,"GB2-03":1424.334314467731,"GB2-04":1503.1686095725508,"GB2-05":1400.1016378570669,"GB2-06":1692.4034101896705,"GB2-07":1350.9355967532974,"GB2-08":1401.015354279309},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1268.6009357357352,"GB2-02":1577.292875089046,"GB2-03":1429.6911976288604,"GB2-04":1588.5462143183504,"GB2-05":1494.2887528091874,"GB2-06":2081.7191659266946,"GB2-07":1308.5212443630285,"GB2-08":1774.6338507185828},"medium":{"GB2-01":1361.909445253132,"GB2-02":1433.772691575842,"GB2-03":1442.5096139513037,"GB2-04":1485.790410975745,"GB2-05":1448.4268529233618,"GB2-06":1190.926543961654,"GB2-07":1499.8309710431834,"GB2-08":1174.8417252179831},"none":{"GB2-01":1451.833953578805,"GB2-02":1429.8961661735852,"GB2-03":1400.8021318230287,"GB2-04":1435.1692034235568,"GB2-05":1257.5893078386512,"GB2-06":1804.5645206806635,"GB2-07":1244.4545748536802,"GB2-08":1253.5704869013605}},"per_game_tracks":{"highest":{"GB2-01":29.562035574308894,"GB2-02":62.73997881732375,"GB2-03":49.705727730027796,"GB2-04":63.67208990961923,"GB2-05":54.35297855687203,"GB2-06":86.16758011832168,"GB2-07":38.74280635717264,"GB2-08":75.06936052138656},"medium":{"GB2-01":38.64577928238832,"GB2-02":44.6921769781043,"GB2-03":51.155041629475676,"GB2-04":51.01516185929073,"GB2-05":50.69627270463538,"GB2-06":34.50556905609082,"GB2-07":54.05257950614269,"GB2-08":28.091011343302547},"none":{"GB2-01":47.99110935481599,"GB2-02":44.189731320055884,"GB2-03":46.404798034467916,"GB2-04":44.465305637178616,"GB2-05":35.77179874918413,"GB2-06":72.34541151950053,"GB2-07":33.74356776113729,"GB2-08":35.60181703666993}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:14:17Z","reasoning":{"highest":57.50156969812907,"medium":44.10669904492882,"none":45.06419242662629},"reasoning_agg":{"highest":{"max":86.16758011832168,"mean":57.50156969812907,"min":29.562035574308894},"medium":{"max":54.05257950614269,"mean":44.10669904492882,"min":28.091011343302547},"none":{"max":72.34541151950053,"mean":45.06419242662629,"min":33.74356776113729}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.39487065320025}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:2466b135b7f9af0c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.46446825,"median":0.4896297,"min":0.2393742,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.715746},"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-2026-10-09":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-2026-10-09":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-2026-10-09":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-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262000000001},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.46446825,"median":0.4896297,"min":0.2393742,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.7157459999999998}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.27696257500000004,"median":0.2537256,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":6.6471018},"codegen_latency_ms":{"attempt_count":35,"max_ms":754602,"mean_ms":294629.0833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":415982,"mean_ms":310768.0,"min_ms":108461,"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":35,"output_max":41670,"output_mean":16512.916666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":41670,"output_mean":28939.0,"output_min":14510,"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":50.81263048243006,"highest":51.44703905461432,"medium":49.468079558901366,"none":51.66615792374492},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[262144],"finish_reason_observations":35,"finish_reasons":["length","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":10,"provider_post_attempts":13,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[262144],"total_output_tokens":396310,"total_reasoning_output_tokens":285325,"total_visible_output_tokens":110985,"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":"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-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":42.51532856386424,"score":42.51532856386424},"GB2-02":{"attempts":3,"playable":42.47603995983531,"score":42.47603995983531},"GB2-03":{"attempts":3,"playable":64.70156886650567,"score":64.70156886650567},"GB2-04":{"attempts":3,"playable":49.079338560478966,"score":49.079338560478966},"GB2-05":{"attempts":3,"playable":56.64701886515229,"score":56.64701886515229},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":51.06896655621961,"score":34.0459777041464},"GB2-07":{"attempts":3,"playable":48.80556550063172,"score":48.80556550063172},"GB2-08":{"attempts":3,"playable":51.463553060542274,"score":51.463553060542274}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":6.447595049515101,"score":6.447595049515101},"GB2-02":{"attempts":1,"playable":43.304080169986534,"score":43.304080169986534},"GB2-03":{"attempts":1,"playable":77.48104122778503,"score":77.48104122778503},"GB2-04":{"attempts":1,"playable":52.97416082145187,"score":52.97416082145187},"GB2-05":{"attempts":1,"playable":62.535870635350086,"score":62.535870635350086},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":93.41690961688025,"score":93.41690961688025},"GB2-08":{"attempts":1,"playable":23.96961586133144,"score":23.96961586133144}},"medium":{"GB2-01":{"attempts":1,"playable":69.27552039709313,"score":69.27552039709313},"GB2-02":{"attempts":1,"playable":41.76256547018016,"score":41.76256547018016},"GB2-03":{"attempts":1,"playable":66.795953835595,"score":66.795953835595},"GB2-04":{"attempts":1,"playable":47.64359781672563,"score":47.64359781672563},"GB2-05":{"attempts":1,"playable":51.79056117886017,"score":51.79056117886017},"GB2-06":{"attempts":1,"playable":55.438341763986855,"score":55.438341763986855},"GB2-07":{"attempts":1,"playable":25.60477123875054,"score":25.60477123875054},"GB2-08":{"attempts":1,"playable":37.43332477001948,"score":37.43332477001948}},"none":{"GB2-01":{"attempts":1,"playable":51.822870244984486,"score":51.822870244984486},"GB2-02":{"attempts":1,"playable":42.361474239339245,"score":42.361474239339245},"GB2-03":{"attempts":1,"playable":49.82771153613699,"score":49.82771153613699},"GB2-04":{"attempts":1,"playable":46.62025704325941,"score":46.62025704325941},"GB2-05":{"attempts":1,"playable":55.61462478124661,"score":55.61462478124661},"GB2-06":{"attempts":1,"playable":46.699591348452365,"score":46.699591348452365},"GB2-07":{"attempts":1,"playable":27.395015646264376,"score":27.395015646264376},"GB2-08":{"attempts":1,"playable":92.9877185502759,"score":92.9877185502759}}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-10-22T10:58:54Z","match_totals_all":{"draws":2844,"losses":4216,"wins":4048},"match_totals_tracks":{"highest":{"draws":778,"losses":1293,"wins":1309},"medium":{"draws":1114,"losses":1478,"wins":1272},"none":{"draws":952,"losses":1445,"wins":1467}},"model_slug":"moonshotai-kimi-k3","overall":{"max":93.41690961688025,"mean":48.716798885144605,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":6.447595049515101,"GB2-02":43.304080169986534,"GB2-03":77.48104122778503,"GB2-04":52.97416082145187,"GB2-05":62.535870635350086,"GB2-07":93.41690961688025,"GB2-08":23.96961586133144},"per_game_all":{"GB2-01":42.51532856386424,"GB2-02":42.47603995983531,"GB2-03":64.70156886650567,"GB2-04":49.079338560478966,"GB2-05":56.64701886515229,"GB2-07":48.80556550063172,"GB2-08":51.463553060542274},"per_game_match_totals_all":{"GB2-01":{"draws":346,"losses":687,"wins":431},"GB2-02":{"draws":1026,"losses":291,"wins":49},"GB2-03":{"draws":191,"losses":445,"wins":768},"GB2-04":{"draws":779,"losses":347,"wins":284},"GB2-05":{"draws":0,"losses":671,"wins":841},"GB2-06":{"draws":59,"losses":468,"wins":429},"GB2-07":{"draws":0,"losses":776,"wins":702},"GB2-08":{"draws":443,"losses":531,"wins":544}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":456,"wins":24},"GB2-02":{"draws":321,"losses":104,"wins":29},"GB2-03":{"draws":31,"losses":101,"wins":336},"GB2-04":{"draws":238,"losses":109,"wins":123},"GB2-05":{"draws":0,"losses":195,"wins":309},"GB2-07":{"draws":0,"losses":29,"wins":463},"GB2-08":{"draws":180,"losses":299,"wins":25}},"medium":{"GB2-01":{"draws":83,"losses":116,"wins":289},"GB2-02":{"draws":343,"losses":100,"wins":13},"GB2-03":{"draws":70,"losses":137,"wins":261},"GB2-04":{"draws":320,"losses":92,"wins":58},"GB2-05":{"draws":0,"losses":249,"wins":255},"GB2-06":{"draws":35,"losses":209,"wins":234},"GB2-07":{"draws":0,"losses":379,"wins":113},"GB2-08":{"draws":263,"losses":196,"wins":49}},"none":{"GB2-01":{"draws":255,"losses":115,"wins":118},"GB2-02":{"draws":362,"losses":87,"wins":7},"GB2-03":{"draws":90,"losses":207,"wins":171},"GB2-04":{"draws":221,"losses":146,"wins":103},"GB2-05":{"draws":0,"losses":227,"wins":277},"GB2-06":{"draws":24,"losses":259,"wins":195},"GB2-07":{"draws":0,"losses":368,"wins":126},"GB2-08":{"draws":0,"losses":36,"wins":470}}},"per_game_raw_elo_all":{"GB2-01":1347.8260889903456,"GB2-02":1416.6320233510826,"GB2-03":1585.6330970616164,"GB2-04":1470.8609431976654,"GB2-05":1524.9149622931518,"GB2-07":1545.7072400990085,"GB2-08":1548.9616615810737},"per_game_raw_elo_tracks":{"highest":{"GB2-01":889.4469687742506,"GB2-02":1423.0523100198586,"GB2-03":1731.7238183231775,"GB2-04":1501.067991610358,"GB2-05":1602.3329965360929,"GB2-07":2346.6224200880815,"GB2-08":1128.7955298507054},"medium":{"GB2-01":1665.6556181061253,"GB2-02":1411.0950643433034,"GB2-03":1594.409283606154,"GB2-04":1459.7051690602264,"GB2-05":1462.0807711525076,"GB2-06":1513.0443499473445,"GB2-07":1132.3079306387563,"GB2-08":1272.3670333828957},"none":{"GB2-01":1488.3756800906613,"GB2-02":1415.7486956900862,"GB2-03":1430.7661892555172,"GB2-04":1451.8096689224114,"GB2-05":1510.331119190855,"GB2-06":1376.0414024605186,"GB2-07":1158.1913695701878,"GB2-08":2245.72242150962}},"per_game_tracks":{"highest":{"GB2-01":6.447595049515101,"GB2-02":43.304080169986534,"GB2-03":77.48104122778503,"GB2-04":52.97416082145187,"GB2-05":62.535870635350086,"GB2-07":93.41690961688025,"GB2-08":23.96961586133144},"medium":{"GB2-01":69.27552039709313,"GB2-02":41.76256547018016,"GB2-03":66.795953835595,"GB2-04":47.64359781672563,"GB2-05":51.79056117886017,"GB2-06":55.438341763986855,"GB2-07":25.60477123875054,"GB2-08":37.43332477001948},"none":{"GB2-01":51.822870244984486,"GB2-02":42.361474239339245,"GB2-03":49.82771153613699,"GB2-04":46.62025704325941,"GB2-05":55.61462478124661,"GB2-06":46.699591348452365,"GB2-07":27.395015646264376,"GB2-08":92.9877185502759}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:22:04Z","reasoning":{"highest":45.01615917278753,"medium":49.468079558901366,"none":51.66615792374492},"reasoning_agg":{"highest":{"max":93.41690961688025,"mean":45.01615917278753,"min":0.0},"medium":{"max":69.27552039709313,"mean":49.468079558901366,"min":25.60477123875054},"none":{"max":92.9877185502759,"mean":51.66615792374492,"min":27.395015646264376}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.649998750957387}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:e60b710fc11a55ac","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-2026-10-09":9},"run_count":16,"token_priced_attempt_count":17,"total":6.887695},"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-2026-10-09":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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.19681749999999998,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.4245200000000002},"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-2026-10-09":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-2026-10-09":17},"run_count":16,"token_priced_attempt_count":17,"total":4.09607}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-10-09":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203785000000002},"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":49.833370973798694,"highest":50.111203217411195,"medium":51.67353462885778,"none":47.71537507512707},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":47.014334358053844,"score":47.014334358053844},"GB2-02":{"attempts":5,"playable":44.030744473553476,"score":44.030744473553476},"GB2-03":{"attempts":4,"playable":47.32690637392016,"score":47.32690637392016},"GB2-04":{"attempts":5,"playable":43.64529647023122,"score":43.64529647023122},"GB2-05":{"attempts":5,"playable":46.46607237505645,"score":46.46607237505645},"GB2-06":{"attempts":5,"playable":47.92255132877551,"score":47.92255132877551},"GB2-07":{"attempts":5,"playable":45.48627998567059,"score":45.48627998567059},"GB2-08":{"attempts":5,"playable":66.87493357493531,"score":66.87493357493531}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":49.745297279069156,"score":49.745297279069156},"GB2-02":{"attempts":2,"playable":43.64624969372639,"score":43.64624969372639},"GB2-03":{"attempts":1,"playable":50.14310466702629,"score":50.14310466702629},"GB2-04":{"attempts":2,"playable":40.964157708195614,"score":40.964157708195614},"GB2-05":{"attempts":2,"playable":47.50407117280003,"score":47.50407117280003},"GB2-06":{"attempts":2,"playable":50.9024855468799,"score":50.9024855468799},"GB2-07":{"attempts":2,"playable":55.2682393368915,"score":55.2682393368915},"GB2-08":{"attempts":2,"playable":57.82608561603875,"score":57.82608561603875}},"medium":{"GB2-01":{"attempts":2,"playable":47.09053119531063,"score":47.09053119531063},"GB2-02":{"attempts":2,"playable":44.02042943525356,"score":44.02042943525356},"GB2-03":{"attempts":2,"playable":49.13883257243435,"score":49.13883257243435},"GB2-04":{"attempts":2,"playable":41.451973924734176,"score":41.451973924734176},"GB2-05":{"attempts":2,"playable":44.71830373805775,"score":44.71830373805775},"GB2-06":{"attempts":2,"playable":47.58539117832297,"score":47.58539117832297},"GB2-07":{"attempts":2,"playable":49.10334643708869,"score":49.10334643708869},"GB2-08":{"attempts":2,"playable":65.46985671774338,"score":65.46985671774338}},"none":{"GB2-01":{"attempts":1,"playable":44.20717459978176,"score":44.20717459978176},"GB2-02":{"attempts":1,"playable":44.42555429168047,"score":44.42555429168047},"GB2-03":{"attempts":1,"playable":42.698781882299826,"score":42.698781882299826},"GB2-04":{"attempts":1,"playable":48.5197577777639,"score":48.5197577777639},"GB2-05":{"attempts":1,"playable":47.175842214311565,"score":47.175842214311565},"GB2-06":{"attempts":1,"playable":45.27977726112367,"score":45.27977726112367},"GB2-07":{"attempts":1,"playable":32.0872541830316,"score":32.0872541830316},"GB2-08":{"attempts":1,"playable":77.32885839102381,"score":77.32885839102381}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:06:40Z","match_totals_all":{"draws":3121,"losses":4480,"wins":4023},"match_totals_tracks":{"highest":{"draws":1036,"losses":1483,"wins":1347},"medium":{"draws":979,"losses":1450,"wins":1449},"none":{"draws":1106,"losses":1547,"wins":1227}},"model_slug":"claude-opus-4-5","overall":{"max":77.32885839102381,"mean":48.59588986752457,"min":32.0872541830316},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":72.45091644705572,"GB2-02":43.68455689109013,"GB2-03":50.14310466702629,"GB2-04":41.33816077361679,"GB2-05":51.07151104268098,"GB2-06":55.11772752445643,"GB2-07":49.867037013173935,"GB2-08":37.21661138018923},"per_game_all":{"GB2-01":58.0719176484468,"GB2-02":43.9879301812451,"GB2-03":46.60350481587849,"GB2-04":44.5706341605729,"GB2-05":48.330078255277705,"GB2-06":50.82847426009537,"GB2-07":42.60256885234847,"GB2-08":63.67185961652465},"per_game_match_totals_all":{"GB2-01":{"draws":403,"losses":436,"wins":627},"GB2-02":{"draws":1077,"losses":249,"wins":44},"GB2-03":{"draws":380,"losses":609,"wins":419},"GB2-04":{"draws":901,"losses":351,"wins":162},"GB2-05":{"draws":0,"losses":794,"wins":724},"GB2-06":{"draws":78,"losses":710,"wins":646},"GB2-07":{"draws":0,"losses":895,"wins":597},"GB2-08":{"draws":282,"losses":436,"wins":804}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":58,"losses":114,"wins":316},"GB2-02":{"draws":367,"losses":80,"wins":9},"GB2-03":{"draws":72,"losses":214,"wins":182},"GB2-04":{"draws":267,"losses":147,"wins":56},"GB2-05":{"draws":0,"losses":251,"wins":255},"GB2-06":{"draws":33,"losses":209,"wins":236},"GB2-07":{"draws":0,"losses":260,"wins":234},"GB2-08":{"draws":239,"losses":208,"wins":59}},"medium":{"GB2-01":{"draws":122,"losses":154,"wins":214},"GB2-02":{"draws":358,"losses":85,"wins":15},"GB2-03":{"draws":142,"losses":194,"wins":134},"GB2-04":{"draws":327,"losses":107,"wins":38},"GB2-05":{"draws":0,"losses":273,"wins":233},"GB2-06":{"draws":28,"losses":231,"wins":219},"GB2-07":{"draws":0,"losses":282,"wins":216},"GB2-08":{"draws":2,"losses":124,"wins":380}},"none":{"GB2-01":{"draws":223,"losses":168,"wins":97},"GB2-02":{"draws":352,"losses":84,"wins":20},"GB2-03":{"draws":166,"losses":201,"wins":103},"GB2-04":{"draws":307,"losses":97,"wins":68},"GB2-05":{"draws":0,"losses":270,"wins":236},"GB2-06":{"draws":17,"losses":270,"wins":191},"GB2-07":{"draws":0,"losses":353,"wins":147},"GB2-08":{"draws":41,"losses":104,"wins":365}}},"per_game_raw_elo_all":{"GB2-01":1553.9604692895616,"GB2-02":1428.3371832852533,"GB2-03":1402.6178279455726,"GB2-04":1435.9270641724222,"GB2-05":1418.9814820006197,"GB2-06":1440.6458611224061,"GB2-07":1355.6332445837545,"GB2-08":1630.9166524675263},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1702.2839826019622,"GB2-02":1425.9943405290387,"GB2-03":1433.5487427913204,"GB2-04":1410.8741329248546,"GB2-05":1453.1043484832537,"GB2-06":1507.8980068905164,"GB2-07":1447.1089435413405,"GB2-08":1270.1439973429635},"medium":{"GB2-01":1543.8552312352492,"GB2-02":1427.3011224389854,"GB2-03":1405.7149917265974,"GB2-04":1430.4382180404632,"GB2-05":1399.221965913149,"GB2-06":1459.7855639980255,"GB2-07":1397.1781646932384,"GB2-08":1802.5228681948238},"none":{"GB2-01":1415.742194031474,"GB2-02":1431.7160868877354,"GB2-03":1368.5897493187997,"GB2-04":1466.4688415519483,"GB2-05":1404.6181316054567,"GB2-06":1354.2540124786763,"GB2-07":1222.6126255166846,"GB2-08":1820.0830918647916}},"per_game_tracks":{"highest":{"GB2-01":72.45091644705572,"GB2-02":43.68455689109013,"GB2-03":50.14310466702629,"GB2-04":41.33816077361679,"GB2-05":51.07151104268098,"GB2-06":55.11772752445643,"GB2-07":49.867037013173935,"GB2-08":37.21661138018923},"medium":{"GB2-01":57.55766189850292,"GB2-02":43.85367936096469,"GB2-03":46.968627898309336,"GB2-04":43.853983930337996,"GB2-05":46.74288150884057,"GB2-06":52.087917994706025,"GB2-07":45.85341536083987,"GB2-08":76.4701090783609},"none":{"GB2-01":44.20717459978176,"GB2-02":44.42555429168047,"GB2-03":42.698781882299826,"GB2-04":48.5197577777639,"GB2-05":47.175842214311565,"GB2-06":45.27977726112367,"GB2-07":32.0872541830316,"GB2-08":77.32885839102381}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:39:05Z","reasoning":{"highest":49.49996137757846,"medium":48.57233314986819,"none":47.71537507512707},"reasoning_agg":{"highest":{"max":57.82608561603875,"mean":49.49996137757846,"min":40.964157708195614},"medium":{"max":65.46985671774338,"mean":48.57233314986819,"min":41.451973924734176},"none":{"max":77.32885839102381,"mean":47.71537507512707,"min":32.0872541830316}},"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":{"reasoning_variance":1.7845863024513875}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:bce32b2d16383de8","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"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":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"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":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"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":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.826309999999999},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":48.034331465364104,"highest":56.55841297212911,"medium":43.88332062722655,"none":43.661260796736634},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":53.22871763112567,"score":53.22871763112567},"GB2-02":{"attempts":3,"playable":43.08860494688856,"score":43.08860494688856},"GB2-03":{"attempts":3,"playable":52.761666822192915,"score":52.761666822192915},"GB2-04":{"attempts":3,"playable":47.033319937395014,"score":47.033319937395014},"GB2-05":{"attempts":3,"playable":40.41727491068182,"score":40.41727491068182},"GB2-06":{"attempts":3,"playable":38.96748012647919,"score":38.96748012647919},"GB2-07":{"attempts":3,"playable":51.278732155170395,"score":51.278732155170395},"GB2-08":{"attempts":3,"playable":57.49885519297925,"score":57.49885519297925}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":64.54221905900656,"score":64.54221905900656},"GB2-02":{"attempts":1,"playable":42.308306688646574,"score":42.308306688646574},"GB2-03":{"attempts":1,"playable":59.97187061969617,"score":59.97187061969617},"GB2-04":{"attempts":1,"playable":52.80523400999012,"score":52.80523400999012},"GB2-05":{"attempts":1,"playable":55.11078735588991,"score":55.11078735588991},"GB2-06":{"attempts":1,"playable":28.482978520712678,"score":28.482978520712678},"GB2-07":{"attempts":1,"playable":68.00480273642616,"score":68.00480273642616},"GB2-08":{"attempts":1,"playable":81.2411047866647,"score":81.2411047866647}},"medium":{"GB2-01":{"attempts":1,"playable":45.642583510159746,"score":45.642583510159746},"GB2-02":{"attempts":1,"playable":43.91143866778921,"score":43.91143866778921},"GB2-03":{"attempts":1,"playable":42.0079519254068,"score":42.0079519254068},"GB2-04":{"attempts":1,"playable":45.16873917864411,"score":45.16873917864411},"GB2-05":{"attempts":1,"playable":43.11895551717808,"score":43.11895551717808},"GB2-06":{"attempts":1,"playable":39.850491842630746,"score":39.850491842630746},"GB2-07":{"attempts":1,"playable":50.67975935212081,"score":50.67975935212081},"GB2-08":{"attempts":1,"playable":40.686645023882946,"score":40.686645023882946}},"none":{"GB2-01":{"attempts":1,"playable":49.50135032421071,"score":49.50135032421071},"GB2-02":{"attempts":1,"playable":43.04606948422989,"score":43.04606948422989},"GB2-03":{"attempts":1,"playable":56.30517792147578,"score":56.30517792147578},"GB2-04":{"attempts":1,"playable":43.12598662355081,"score":43.12598662355081},"GB2-05":{"attempts":1,"playable":23.022081858977465,"score":23.022081858977465},"GB2-06":{"attempts":1,"playable":48.568970016094134,"score":48.568970016094134},"GB2-07":{"attempts":1,"playable":35.15163437696423,"score":35.15163437696423},"GB2-08":{"attempts":1,"playable":50.56881576839009,"score":50.56881576839009}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:20:19Z","match_totals_all":{"draws":2987,"losses":4750,"wins":3863},"match_totals_tracks":{"highest":{"draws":800,"losses":1332,"wins":1732},"medium":{"draws":1148,"losses":1669,"wins":1049},"none":{"draws":1039,"losses":1749,"wins":1082}},"model_slug":"claude-sonnet-5","overall":{"max":81.2411047866647,"mean":48.0343314653641,"min":23.022081858977465},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.54221905900656,"GB2-02":42.308306688646574,"GB2-03":59.97187061969617,"GB2-04":52.80523400999012,"GB2-05":55.11078735588991,"GB2-06":28.482978520712678,"GB2-07":68.00480273642616,"GB2-08":81.2411047866647},"per_game_all":{"GB2-01":53.22871763112567,"GB2-02":43.08860494688856,"GB2-03":52.761666822192915,"GB2-04":47.033319937395014,"GB2-05":40.41727491068182,"GB2-06":38.96748012647919,"GB2-07":51.278732155170395,"GB2-08":57.49885519297925},"per_game_match_totals_all":{"GB2-01":{"draws":232,"losses":592,"wins":642},"GB2-02":{"draws":1086,"losses":254,"wins":28},"GB2-03":{"draws":314,"losses":556,"wins":538},"GB2-04":{"draws":875,"losses":328,"wins":209},"GB2-05":{"draws":0,"losses":917,"wins":601},"GB2-06":{"draws":45,"losses":899,"wins":490},"GB2-07":{"draws":0,"losses":750,"wins":726},"GB2-08":{"draws":435,"losses":454,"wins":629}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":154,"wins":283},"GB2-02":{"draws":357,"losses":91,"wins":8},"GB2-03":{"draws":102,"losses":154,"wins":214},"GB2-04":{"draws":274,"losses":90,"wins":106},"GB2-05":{"draws":0,"losses":232,"wins":274},"GB2-06":{"draws":12,"losses":351,"wins":115},"GB2-07":{"draws":0,"losses":162,"wins":330},"GB2-08":{"draws":4,"losses":98,"wins":402}},"medium":{"GB2-01":{"draws":99,"losses":222,"wins":169},"GB2-02":{"draws":371,"losses":76,"wins":9},"GB2-03":{"draws":116,"losses":229,"wins":123},"GB2-04":{"draws":298,"losses":116,"wins":58},"GB2-05":{"draws":0,"losses":292,"wins":214},"GB2-06":{"draws":18,"losses":295,"wins":165},"GB2-07":{"draws":0,"losses":254,"wins":238},"GB2-08":{"draws":246,"losses":185,"wins":73}},"none":{"GB2-01":{"draws":82,"losses":216,"wins":190},"GB2-02":{"draws":358,"losses":87,"wins":11},"GB2-03":{"draws":96,"losses":173,"wins":201},"GB2-04":{"draws":303,"losses":122,"wins":45},"GB2-05":{"draws":0,"losses":393,"wins":113},"GB2-06":{"draws":15,"losses":253,"wins":210},"GB2-07":{"draws":0,"losses":334,"wins":158},"GB2-08":{"draws":185,"losses":171,"wins":154}}},"per_game_raw_elo_all":{"GB2-01":1503.3790148150547,"GB2-02":1421.3795719312857,"GB2-03":1458.5867189328947,"GB2-04":1455.0486278402575,"GB2-05":1307.4658279240437,"GB2-06":1258.8024116881008,"GB2-07":1469.6147656340238,"GB2-08":1540.843785404861},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1614.4631549159749,"GB2-02":1415.3360191043005,"GB2-03":1523.9945042109018,"GB2-04":1499.7454087761694,"GB2-05":1503.9065337502536,"GB2-06":1099.8982226987089,"GB2-07":1688.8215471837914,"GB2-08":1904.8661571682994},"medium":{"GB2-01":1429.4569096909158,"GB2-02":1427.7472935541866,"GB2-03":1362.5809325038672,"GB2-04":1440.6059044992867,"GB2-05":1353.7250757238035,"GB2-06":1271.6263744453909,"GB2-07":1457.2761536688604,"GB2-08":1305.821675501548},"none":{"GB2-01":1466.2169798382733,"GB2-02":1421.05540313537,"GB2-03":1489.1847200839145,"GB2-04":1424.794570245316,"GB2-05":1064.7658742980743,"GB2-06":1404.882637920203,"GB2-07":1262.7465960494203,"GB2-08":1411.8435235447357}},"per_game_tracks":{"highest":{"GB2-01":64.54221905900656,"GB2-02":42.308306688646574,"GB2-03":59.97187061969617,"GB2-04":52.80523400999012,"GB2-05":55.11078735588991,"GB2-06":28.482978520712678,"GB2-07":68.00480273642616,"GB2-08":81.2411047866647},"medium":{"GB2-01":45.642583510159746,"GB2-02":43.91143866778921,"GB2-03":42.0079519254068,"GB2-04":45.16873917864411,"GB2-05":43.11895551717808,"GB2-06":39.850491842630746,"GB2-07":50.67975935212081,"GB2-08":40.686645023882946},"none":{"GB2-01":49.50135032421071,"GB2-02":43.04606948422989,"GB2-03":56.30517792147578,"GB2-04":43.12598662355081,"GB2-05":23.022081858977465,"GB2-06":48.568970016094134,"GB2-07":35.15163437696423,"GB2-08":50.56881576839009}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:20:03Z","reasoning":{"highest":56.55841297212911,"medium":43.88332062722655,"none":43.661260796736634},"reasoning_agg":{"highest":{"max":81.2411047866647,"mean":56.55841297212911,"min":28.482978520712678},"medium":{"max":50.67975935212081,"mean":43.88332062722655,"min":39.850491842630746},"none":{"max":56.30517792147578,"mean":43.661260796736634,"min":23.022081858977465}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.897152175392478}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-3:d167eec84c07b1fa","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.04598051,"mean":0.037044270000000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":11,"run_count":8,"total":0.29635416000000003},"medium":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.046827143749999994,"median":0.045572185,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":11,"run_count":8,"total":0.37461715},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0094142,"mean":0.0028034124999999997,"median":0.001882025,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.022427299999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.046827143749999994,"median":0.045572185,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":11,"run_count":8,"total":0.37461715000000007},"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":0.0094142,"mean":0.0028034124999999997,"median":0.001882025,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.0224273},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.04598051,"mean":0.037044270000000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":11,"run_count":8,"total":0.29635416000000003}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.028891608750000006,"median":0.03513247,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"recorded_attempt_count":31,"run_count":24,"total":0.6933986099999999},"codegen_latency_ms":{"attempt_count":24,"max_ms":377102,"mean_ms":133492.94444444444,"min_ms":3791,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319339,"mean_ms":217388.6,"min_ms":142770,"run_count":5},"medium":{"attempt_count":7,"max_ms":377102,"mean_ms":248372.6,"min_ms":146739,"run_count":5},"none":{"attempt_count":9,"max_ms":30086,"mean_ms":9258.375,"min_ms":3791,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":230653,"output_mean":79571.75,"output_min":2342,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":129270,"output_mean":102689.5,"output_min":67386,"run_count":8},"medium":{"attempt_count":11,"output_max":230653,"output_mean":130579.0,"output_min":68315,"run_count":8},"none":{"attempt_count":9,"output_max":22506,"output_mean":5446.75,"output_min":2342,"run_count":8}},"display_name":"Mercury 3","economics":{"all":47.787393919719435,"highest":59.62027177850329,"medium":60.13145974319872,"none":39.07399389175},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":31,"effective_max_output_tokens":[131072],"finish_reason_observations":24,"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,"requested_max_output_token_observations":31,"requested_max_output_tokens":[131072],"total_output_tokens":1909722,"total_reasoning_output_tokens":1808452,"total_visible_output_tokens":101270,"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":"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":"inception","provider_model":"inception/mercury-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":3,"evaluated_cells":4,"failed_game_aliases":["GB2-03"],"first_pass_admitted":2,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"infra_failures_excluded":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06"],"infra_failures_excluded":4,"model_code_failure_rate":0.25,"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":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":5,"evaluated_cells":5,"first_pass_admitted":2,"first_pass_rate":0.4,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"admitted":1},"GB2-07":{"infra_failures_excluded":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-04","GB2-05","GB2-07"],"infra_failures_excluded":3,"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":3,"repaired_rate":0.6}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.07335888547274,"score":42.07335888547274},"GB2-02":{"attempts":3,"playable":43.91806587054425,"score":43.91806587054425},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":48.96307692315299,"score":32.642051282101995},"GB2-04":{"attempts":1,"playable":40.671849256680275,"score":40.671849256680275},"GB2-05":{"attempts":1,"playable":24.79400718733226,"score":24.79400718733226},"GB2-06":{"attempts":2,"playable":73.89179112541508,"score":73.89179112541508},"GB2-07":{"attempts":2,"playable":54.52050771285088,"score":54.52050771285088},"GB2-08":{"attempts":3,"playable":51.65672196889462,"score":51.65672196889462}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":49.463909984865374,"score":49.463909984865374},"GB2-02":{"attempts":1,"playable":44.29514854453784,"score":44.29514854453784},"GB2-03":{"attempts":1,"playable":63.122052802476546,"score":63.122052802476546},"GB2-06":{"attempts":1,"playable":79.64070452324302,"score":79.64070452324302},"GB2-08":{"attempts":1,"playable":61.57954303739367,"score":61.57954303739367}},"medium":{"GB2-02":{"attempts":1,"playable":45.578023437480894,"score":45.578023437480894},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":76.04120640675734,"score":76.04120640675734},"GB2-08":{"attempts":1,"playable":58.775149385357906,"score":58.775149385357906}},"none":{"GB2-01":{"attempts":1,"playable":34.68280778608012,"score":34.68280778608012},"GB2-02":{"attempts":1,"playable":41.88102562961402,"score":41.88102562961402},"GB2-03":{"attempts":1,"playable":34.804101043829434,"score":34.804101043829434},"GB2-04":{"attempts":1,"playable":40.671849256680275,"score":40.671849256680275},"GB2-05":{"attempts":1,"playable":24.79400718733226,"score":24.79400718733226},"GB2-06":{"attempts":1,"playable":68.14287772758715,"score":68.14287772758715},"GB2-07":{"attempts":1,"playable":32.99980901894442,"score":32.99980901894442},"GB2-08":{"attempts":1,"playable":34.61547348393229,"score":34.61547348393229}}},"id":"inception/mercury-3","is_recent_addition":false,"last_measured_at":"2026-10-22T10:59:24Z","match_totals_all":{"draws":1239,"losses":1714,"wins":1388},"match_totals_tracks":{"highest":{"draws":526,"losses":414,"wins":546},"medium":{"draws":182,"losses":229,"wins":341},"none":{"draws":531,"losses":1071,"wins":501}},"model_slug":"inception-mercury-3","overall":{"max":79.64070452324302,"mean":47.93095349255078,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":40,"overall_ranking_status":"partial","per_game":{"GB2-01":49.463909984865374,"GB2-02":44.29514854453784,"GB2-03":63.122052802476546,"GB2-06":79.64070452324302,"GB2-08":61.57954303739367},"per_game_all":{"GB2-02":43.91806587054425,"GB2-08":51.65672196889462},"per_game_match_totals_all":{"GB2-01":{"draws":234,"losses":200,"wins":98},"GB2-02":{"draws":719,"losses":220,"wins":63},"GB2-03":{"draws":114,"losses":216,"wins":172},"GB2-04":{"draws":165,"losses":85,"wins":20},"GB2-05":{"draws":0,"losses":233,"wins":63},"GB2-06":{"draws":7,"losses":153,"wins":383},"GB2-07":{"draws":0,"losses":216,"wins":260},"GB2-08":{"draws":0,"losses":391,"wins":329}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":136,"losses":76,"wins":62},"GB2-02":{"draws":329,"losses":95,"wins":30},"GB2-03":{"draws":56,"losses":77,"wins":119},"GB2-06":{"draws":5,"losses":58,"wins":201},"GB2-08":{"draws":0,"losses":108,"wins":134}},"medium":{"GB2-02":{"draws":182,"losses":62,"wins":28},"GB2-07":{"draws":0,"losses":52,"wins":188},"GB2-08":{"draws":0,"losses":115,"wins":125}},"none":{"GB2-01":{"draws":98,"losses":124,"wins":36},"GB2-02":{"draws":208,"losses":63,"wins":5},"GB2-03":{"draws":58,"losses":139,"wins":53},"GB2-04":{"draws":165,"losses":85,"wins":20},"GB2-05":{"draws":0,"losses":233,"wins":63},"GB2-06":{"draws":2,"losses":95,"wins":182},"GB2-07":{"draws":0,"losses":164,"wins":72},"GB2-08":{"draws":0,"losses":168,"wins":70}}},"per_game_raw_elo_all":{"GB2-02":1427.7752763449218,"GB2-08":1434.969733355322},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1465.86024545215,"GB2-02":1430.7098137647772,"GB2-03":1555.4109410946805,"GB2-06":1943.6612208731678,"GB2-08":1549.8059542180358},"medium":{"GB2-02":1440.599592160646,"GB2-07":1818.371900244811,"GB2-08":1511.6791531542624},"none":{"GB2-01":1322.332861533967,"GB2-02":1412.0164231093431,"GB2-03":1298.9460799293631,"GB2-04":1405.6579818761738,"GB2-05":1094.3513360678191,"GB2-06":1728.1904839123254,"GB2-07":1234.6936516589235,"GB2-08":1243.4240926936673}},"per_game_tracks":{"highest":{"GB2-01":49.463909984865374,"GB2-02":44.29514854453784,"GB2-03":63.122052802476546,"GB2-06":79.64070452324302,"GB2-08":61.57954303739367},"medium":{"GB2-02":45.578023437480894,"GB2-07":76.04120640675734,"GB2-08":58.775149385357906},"none":{"GB2-01":34.68280778608012,"GB2-02":41.88102562961402,"GB2-03":34.804101043829434,"GB2-04":40.671849256680275,"GB2-05":24.79400718733226,"GB2-06":68.14287772758715,"GB2-07":32.99980901894442,"GB2-08":34.61547348393229}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":59.62027177850329,"medium":45.098594807399046,"none":39.07399389175},"reasoning_agg":{"highest":{"max":79.64070452324302,"mean":59.62027177850329,"min":44.29514854453784},"medium":{"max":76.04120640675734,"mean":45.098594807399046,"min":0.0},"none":{"max":68.14287772758715,"mean":39.07399389175,"min":24.79400718733226}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":20.546277886753288}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:e742d808cb7b3e65","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"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":true,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7756987500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"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":0.6137424999999999}},"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":0.146648125,"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":true,"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":true,"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":3.06723375}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"cost_is_complete":true,"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":4.456675000000001},"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":48.36679861846141,"highest":54.43004660238909,"medium":50.63262314851059,"none":41.23676387442039},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":68.08336574754877,"score":68.08336574754877},"GB2-02":{"attempts":3,"playable":49.82155276962536,"score":49.82155276962536},"GB2-03":{"attempts":3,"playable":34.8191593012107,"score":34.8191593012107},"GB2-04":{"attempts":3,"playable":43.673193620627046,"score":43.673193620627046},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.727967070225326,"score":37.81864471348355},"GB2-06":{"attempts":3,"playable":51.97058684737224,"score":51.97058684737224},"GB2-07":{"attempts":3,"playable":45.17033342891347,"score":45.17033342891347},"GB2-08":{"attempts":3,"playable":45.02939861393225,"score":45.02939861393225}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":71.9635770400897,"score":71.9635770400897},"GB2-02":{"attempts":1,"playable":59.292186600575945,"score":59.292186600575945},"GB2-03":{"attempts":1,"playable":37.13872838729152,"score":37.13872838729152},"GB2-04":{"attempts":1,"playable":42.48271669021906,"score":42.48271669021906},"GB2-05":{"attempts":1,"playable":55.61994621866197,"score":55.61994621866197},"GB2-06":{"attempts":1,"playable":79.87156301293622,"score":79.87156301293622},"GB2-07":{"attempts":1,"playable":44.68481824422169,"score":44.68481824422169},"GB2-08":{"attempts":1,"playable":44.386836625116665,"score":44.386836625116665}},"medium":{"GB2-01":{"attempts":1,"playable":77.71296874167211,"score":77.71296874167211},"GB2-02":{"attempts":1,"playable":45.72986484640931,"score":45.72986484640931},"GB2-03":{"attempts":1,"playable":33.886993568853526,"score":33.886993568853526},"GB2-04":{"attempts":1,"playable":43.92960765684436,"score":43.92960765684436},"GB2-05":{"attempts":1,"playable":57.83598792178868,"score":57.83598792178868},"GB2-06":{"attempts":1,"playable":39.19862242931729,"score":39.19862242931729},"GB2-07":{"attempts":1,"playable":60.97475173411018,"score":60.97475173411018},"GB2-08":{"attempts":1,"playable":45.792188289089275,"score":45.792188289089275}},"none":{"GB2-01":{"attempts":1,"playable":54.573551460884474,"score":54.573551460884474},"GB2-02":{"attempts":1,"playable":44.44260686189085,"score":44.44260686189085},"GB2-03":{"attempts":1,"playable":33.43175594748706,"score":33.43175594748706},"GB2-04":{"attempts":1,"playable":44.60725651481772,"score":44.60725651481772},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":36.841575099863206,"score":36.841575099863206},"GB2-07":{"attempts":1,"playable":29.85143030840857,"score":29.85143030840857},"GB2-08":{"attempts":1,"playable":44.90917092759083,"score":44.90917092759083}}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-10-22T10:58:28Z","match_totals_all":{"draws":3254,"losses":4214,"wins":3626},"match_totals_tracks":{"highest":{"draws":986,"losses":1337,"wins":1547},"medium":{"draws":1018,"losses":1456,"wins":1390},"none":{"draws":1250,"losses":1421,"wins":689}},"model_slug":"gpt-5-6-terra","overall":{"max":79.87156301293622,"mean":47.04827938033918,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":41,"overall_ranking_status":"ranked","per_game":{"GB2-01":71.9635770400897,"GB2-02":59.292186600575945,"GB2-03":37.13872838729152,"GB2-04":42.48271669021906,"GB2-05":55.61994621866197,"GB2-06":79.87156301293622,"GB2-07":44.68481824422169,"GB2-08":44.386836625116665},"per_game_all":{"GB2-01":68.08336574754877,"GB2-02":49.82155276962536,"GB2-03":34.8191593012107,"GB2-04":43.673193620627046,"GB2-06":51.97058684737224,"GB2-07":45.17033342891347,"GB2-08":45.02939861393225},"per_game_match_totals_all":{"GB2-01":{"draws":229,"losses":374,"wins":861},"GB2-02":{"draws":1000,"losses":204,"wins":164},"GB2-03":{"draws":529,"losses":694,"wins":181},"GB2-04":{"draws":869,"losses":378,"wins":165},"GB2-05":{"draws":0,"losses":448,"wins":564},"GB2-06":{"draws":87,"losses":681,"wins":666},"GB2-07":{"draws":0,"losses":844,"wins":638},"GB2-08":{"draws":540,"losses":591,"wins":387}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":67,"losses":111,"wins":310},"GB2-02":{"draws":258,"losses":62,"wins":136},"GB2-03":{"draws":148,"losses":234,"wins":86},"GB2-04":{"draws":312,"losses":121,"wins":39},"GB2-05":{"draws":0,"losses":231,"wins":277},"GB2-06":{"draws":35,"losses":83,"wins":360},"GB2-07":{"draws":0,"losses":287,"wins":207},"GB2-08":{"draws":166,"losses":208,"wins":132}},"medium":{"GB2-01":{"draws":3,"losses":113,"wins":372},"GB2-02":{"draws":366,"losses":70,"wins":20},"GB2-03":{"draws":213,"losses":218,"wins":37},"GB2-04":{"draws":241,"losses":149,"wins":80},"GB2-05":{"draws":0,"losses":217,"wins":287},"GB2-06":{"draws":51,"losses":281,"wins":146},"GB2-07":{"draws":0,"losses":198,"wins":296},"GB2-08":{"draws":144,"losses":210,"wins":152}},"none":{"GB2-01":{"draws":159,"losses":150,"wins":179},"GB2-02":{"draws":376,"losses":72,"wins":8},"GB2-03":{"draws":168,"losses":242,"wins":58},"GB2-04":{"draws":316,"losses":108,"wins":46},"GB2-06":{"draws":1,"losses":317,"wins":160},"GB2-07":{"draws":0,"losses":359,"wins":135},"GB2-08":{"draws":230,"losses":173,"wins":103}}},"per_game_raw_elo_all":{"GB2-01":1660.0664120157408,"GB2-02":1473.987216720816,"GB2-03":1298.9771136131822,"GB2-04":1429.029234056234,"GB2-06":1478.7189980309374,"GB2-07":1388.413598122035,"GB2-08":1351.246485064952},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1696.5168698248083,"GB2-02":1548.3449351445627,"GB2-03":1319.8556093342543,"GB2-04":1419.797005511756,"GB2-05":1510.3991125950645,"GB2-06":1948.2447771317613,"GB2-07":1382.6780172448405,"GB2-08":1344.4250397887015},"medium":{"GB2-01":1768.8744420515095,"GB2-02":1441.7690616485309,"GB2-03":1290.618616798186,"GB2-04":1431.0238335071588,"GB2-05":1539.0049522329325,"GB2-06":1261.760352670291,"GB2-07":1590.1125523280703,"GB2-08":1359.359912210502},"none":{"GB2-01":1514.8079241709047,"GB2-02":1431.8476533693542,"GB2-03":1286.4571147071065,"GB2-04":1436.2668631497875,"GB2-06":1226.1518642907595,"GB2-07":1192.4502247931941,"GB2-08":1349.9545031956523}},"per_game_tracks":{"highest":{"GB2-01":71.9635770400897,"GB2-02":59.292186600575945,"GB2-03":37.13872838729152,"GB2-04":42.48271669021906,"GB2-05":55.61994621866197,"GB2-06":79.87156301293622,"GB2-07":44.68481824422169,"GB2-08":44.386836625116665},"medium":{"GB2-01":77.71296874167211,"GB2-02":45.72986484640931,"GB2-03":33.886993568853526,"GB2-04":43.92960765684436,"GB2-05":57.83598792178868,"GB2-06":39.19862242931729,"GB2-07":60.97475173411018,"GB2-08":45.792188289089275},"none":{"GB2-01":54.573551460884474,"GB2-02":44.44260686189085,"GB2-03":33.43175594748706,"GB2-04":44.60725651481772,"GB2-06":36.841575099863206,"GB2-07":29.85143030840857,"GB2-08":44.90917092759083}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:37:59Z","reasoning":{"highest":54.43004660238909,"medium":50.63262314851059,"none":36.08216839011784},"reasoning_agg":{"highest":{"max":79.87156301293622,"mean":54.43004660238909,"min":37.13872838729152},"medium":{"max":77.71296874167211,"mean":50.63262314851059,"min":33.886993568853526},"none":{"max":54.573551460884474,"mean":36.08216839011784,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":18.347878212271247}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:a373251d683bf7c2","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":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.5923719999999997},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.642066},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.3670399999999999}},"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":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.642066},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704},"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":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.592372}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.15006158333333333,"median":0.080065,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":3.601478},"codegen_latency_ms":{"attempt_count":28,"max_ms":255692,"mean_ms":76920.70833333333,"min_ms":12384,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":255692,"mean_ms":175619.75,"min_ms":52003,"run_count":8},"medium":{"attempt_count":8,"max_ms":58005,"mean_ms":37933.625,"min_ms":21700,"run_count":8},"none":{"attempt_count":9,"max_ms":20748,"mean_ms":17208.75,"min_ms":12384,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":36035,"output_mean":10826.541666666666,"output_min":1554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":36035,"output_mean":24993.125,"output_min":6631,"run_count":8},"medium":{"attempt_count":8,"output_max":7812,"output_mean":5238.375,"output_min":2903,"run_count":8},"none":{"attempt_count":9,"output_max":3115,"output_mean":2248.125,"output_min":1554,"run_count":8}},"display_name":"Gemini 3.1 Pro Preview","economics":{"all":46.4380888905438,"highest":66.01189924435101,"medium":42.927621742152795,"none":30.374745685127593},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[65536],"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,"requested_max_output_token_observations":28,"requested_max_output_tokens":[65536],"total_output_tokens":259837,"total_reasoning_output_tokens":197903,"total_visible_output_tokens":61934,"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":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-3.1-pro-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"google","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":50.18242988487042,"score":50.18242988487042},"GB2-02":{"attempts":3,"playable":43.50607211395134,"score":43.50607211395134},"GB2-03":{"attempts":3,"playable":53.89583410067712,"score":53.89583410067712},"GB2-04":{"attempts":3,"playable":56.66801295573804,"score":56.66801295573804},"GB2-05":{"attempts":3,"playable":39.530641354605926,"score":39.530641354605926},"GB2-06":{"attempts":3,"playable":21.00701923592286,"score":21.00701923592286},"GB2-07":{"attempts":3,"playable":56.45801716080305,"score":56.45801716080305},"GB2-08":{"attempts":3,"playable":50.25668431778164,"score":50.25668431778164}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.67136487750906,"score":74.67136487750906},"GB2-02":{"attempts":1,"playable":42.9820995815276,"score":42.9820995815276},"GB2-03":{"attempts":1,"playable":65.675969416065,"score":65.675969416065},"GB2-04":{"attempts":1,"playable":81.19097777070584,"score":81.19097777070584},"GB2-05":{"attempts":1,"playable":85.12601340423696,"score":85.12601340423696},"GB2-06":{"attempts":1,"playable":18.924286217665593,"score":18.924286217665593},"GB2-07":{"attempts":1,"playable":74.43584478547874,"score":74.43584478547874},"GB2-08":{"attempts":1,"playable":85.08863790161938,"score":85.08863790161938}},"medium":{"GB2-01":{"attempts":1,"playable":34.888735221716715,"score":34.888735221716715},"GB2-02":{"attempts":1,"playable":44.60919582148337,"score":44.60919582148337},"GB2-03":{"attempts":1,"playable":67.5490678262518,"score":67.5490678262518},"GB2-04":{"attempts":1,"playable":46.155521887295436,"score":46.155521887295436},"GB2-05":{"attempts":1,"playable":17.495321686698524,"score":17.495321686698524},"GB2-06":{"attempts":1,"playable":29.1642649244181,"score":29.1642649244181},"GB2-07":{"attempts":1,"playable":70.73691945912063,"score":70.73691945912063},"GB2-08":{"attempts":1,"playable":32.82194711023775,"score":32.82194711023775}},"none":{"GB2-01":{"attempts":1,"playable":40.98718955538549,"score":40.98718955538549},"GB2-02":{"attempts":1,"playable":42.92692093884305,"score":42.92692093884305},"GB2-03":{"attempts":1,"playable":28.46246505971457,"score":28.46246505971457},"GB2-04":{"attempts":1,"playable":42.65753920921284,"score":42.65753920921284},"GB2-05":{"attempts":1,"playable":15.970588972882293,"score":15.970588972882293},"GB2-06":{"attempts":1,"playable":14.932506565684896,"score":14.932506565684896},"GB2-07":{"attempts":1,"playable":24.201287237809783,"score":24.201287237809783},"GB2-08":{"attempts":1,"playable":32.85946794148779,"score":32.85946794148779}}},"id":"gemini-3.1-pro-preview","is_recent_addition":false,"last_measured_at":"2026-10-22T10:58:47Z","match_totals_all":{"draws":2839,"losses":4954,"wins":3787},"match_totals_tracks":{"highest":{"draws":508,"losses":1091,"wins":2259},"medium":{"draws":1163,"losses":1689,"wins":1006},"none":{"draws":1168,"losses":2174,"wins":522}},"model_slug":"gemini-3-1-pro-preview","overall":{"max":85.12601340423696,"mean":46.4380888905438,"min":14.932506565684896},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":42,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.67136487750906,"GB2-02":42.9820995815276,"GB2-03":65.675969416065,"GB2-04":81.19097777070584,"GB2-05":85.12601340423696,"GB2-06":18.924286217665593,"GB2-07":74.43584478547874,"GB2-08":85.08863790161938},"per_game_all":{"GB2-01":50.18242988487042,"GB2-02":43.50607211395134,"GB2-03":53.89583410067712,"GB2-04":56.66801295573804,"GB2-05":39.530641354605926,"GB2-06":21.00701923592286,"GB2-07":56.45801716080305,"GB2-08":50.25668431778164},"per_game_match_totals_all":{"GB2-01":{"draws":266,"losses":615,"wins":583},"GB2-02":{"draws":1097,"losses":239,"wins":26},"GB2-03":{"draws":267,"losses":558,"wins":585},"GB2-04":{"draws":658,"losses":297,"wins":455},"GB2-05":{"draws":0,"losses":922,"wins":590},"GB2-06":{"draws":19,"losses":1153,"wins":256},"GB2-07":{"draws":0,"losses":659,"wins":817},"GB2-08":{"draws":532,"losses":511,"wins":475}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":121,"wins":348},"GB2-02":{"draws":357,"losses":87,"wins":10},"GB2-03":{"draws":30,"losses":161,"wins":279},"GB2-04":{"draws":99,"losses":43,"wins":328},"GB2-05":{"draws":0,"losses":77,"wins":427},"GB2-06":{"draws":2,"losses":396,"wins":78},"GB2-07":{"draws":0,"losses":127,"wins":365},"GB2-08":{"draws":1,"losses":79,"wins":424}},"medium":{"GB2-01":{"draws":167,"losses":240,"wins":81},"GB2-02":{"draws":366,"losses":74,"wins":14},"GB2-03":{"draws":86,"losses":123,"wins":261},"GB2-04":{"draws":263,"losses":127,"wins":80},"GB2-05":{"draws":0,"losses":419,"wins":85},"GB2-06":{"draws":15,"losses":344,"wins":117},"GB2-07":{"draws":0,"losses":148,"wins":344},"GB2-08":{"draws":266,"losses":214,"wins":24}},"none":{"GB2-01":{"draws":80,"losses":254,"wins":154},"GB2-02":{"draws":374,"losses":78,"wins":2},"GB2-03":{"draws":151,"losses":274,"wins":45},"GB2-04":{"draws":296,"losses":127,"wins":47},"GB2-05":{"draws":0,"losses":426,"wins":78},"GB2-06":{"draws":2,"losses":413,"wins":61},"GB2-07":{"draws":0,"losses":384,"wins":108},"GB2-08":{"draws":265,"losses":218,"wins":27}}},"per_game_raw_elo_all":{"GB2-01":1479.505570887534,"GB2-02":1424.6084898975198,"GB2-03":1474.8254179647417,"GB2-04":1547.515574920969,"GB2-05":1322.9478186446695,"GB2-06":979.0134969532174,"GB2-07":1543.9818506605427,"GB2-08":1482.5499928416614},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1729.3402693655758,"GB2-02":1420.5600529455057,"GB2-03":1582.2081826478425,"GB2-04":1773.1665483426427,"GB2-05":2070.6602346706622,"GB2-06":948.7943637664126,"GB2-07":1790.3536321092652,"GB2-08":1997.496700802281},"medium":{"GB2-01":1324.4249497802837,"GB2-02":1433.132720614416,"GB2-03":1602.7870017561831,"GB2-04":1448.2238657594203,"GB2-05":964.3307388876254,"GB2-06":1110.250236631174,"GB2-07":1730.2231655068736,"GB2-08":1224.881870369622},"none":{"GB2-01":1384.7514935167424,"GB2-02":1420.1326961326374,"GB2-03":1239.4810694901998,"GB2-04":1421.1563106608435,"GB2-05":933.8524823757208,"GB2-06":877.9958904620657,"GB2-07":1111.3687543654896,"GB2-08":1225.2714073530815}},"per_game_tracks":{"highest":{"GB2-01":74.67136487750906,"GB2-02":42.9820995815276,"GB2-03":65.675969416065,"GB2-04":81.19097777070584,"GB2-05":85.12601340423696,"GB2-06":18.924286217665593,"GB2-07":74.43584478547874,"GB2-08":85.08863790161938},"medium":{"GB2-01":34.888735221716715,"GB2-02":44.60919582148337,"GB2-03":67.5490678262518,"GB2-04":46.155521887295436,"GB2-05":17.495321686698524,"GB2-06":29.1642649244181,"GB2-07":70.73691945912063,"GB2-08":32.82194711023775},"none":{"GB2-01":40.98718955538549,"GB2-02":42.92692093884305,"GB2-03":28.46246505971457,"GB2-04":42.65753920921284,"GB2-05":15.970588972882293,"GB2-06":14.932506565684896,"GB2-07":24.201287237809783,"GB2-08":32.85946794148779}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:42:10Z","reasoning":{"highest":66.01189924435101,"medium":42.927621742152795,"none":30.374745685127593},"reasoning_agg":{"highest":{"max":85.12601340423696,"mean":66.01189924435101,"min":18.924286217665593},"medium":{"max":70.73691945912063,"mean":42.927621742152795,"min":17.495321686698524},"none":{"max":42.92692093884305,"mean":30.374745685127593,"min":14.932506565684896}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":35.63715355922342}},{"canonical_public_row_identity":"publication-row.v1:overall:reflection-beam-1-0-501b-a23b:7eebc3dfc49f5865","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":0.04917425,"mean":0.028458624999999998,"median":0.0242415,"min":0.016261,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.22766899999999998},"medium":{"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":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975000000001},"none":{"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":0.013563249999999999,"mean":0.0084324375,"median":0.007856624999999999,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.0674595}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975000000001},"historical-provider-setting-baseline":{"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":0.013563249999999999,"mean":0.0084324375,"median":0.007856624999999999,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.0674595},"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":0.04917425,"mean":0.028458624999999998,"median":0.0242415,"min":0.016261,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.22766899999999998}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04917425,"mean":0.015867427083333333,"median":0.01165575,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":36},"recorded_attempt_count":36,"run_count":24,"total":0.38081825},"codegen_latency_ms":{"attempt_count":36,"max_ms":225177,"mean_ms":82986.79166666667,"min_ms":14518,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":225177,"mean_ms":159627.75,"min_ms":89322,"run_count":8},"medium":{"attempt_count":11,"max_ms":118131,"mean_ms":55222.125,"min_ms":14518,"run_count":8},"none":{"attempt_count":14,"max_ms":72565,"mean_ms":34110.5,"min_ms":18316,"run_count":8}},"codegen_output_tokens":{"attempt_count":36,"output_max":44106,"output_mean":12952.291666666666,"output_min":2213,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":44106,"output_mean":25586.0,"output_min":14383,"run_count":8},"medium":{"attempt_count":11,"output_max":15405,"output_mean":8034.75,"output_min":4457,"run_count":8},"none":{"attempt_count":14,"output_max":8725,"output_mean":5236.125,"output_min":2213,"run_count":8}},"display_name":"Beam 1.0 501B A23B","economics":{"all":48.925350976564836,"highest":55.99801477751303,"medium":43.859999333331885,"none":46.55422817546503},"first_seen_at":"2026-10-22T10:56:58Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":36,"effective_max_output_tokens":[131072],"finish_reason_observations":36,"finish_reasons":["stop"],"indexed_attempts":36,"output_token_observations":36,"provider_post_attempt_observations":36,"provider_post_attempts":36,"reasoning_token_observations":36,"reconciliation_get_attempt_observations":36,"requested_max_output_token_observations":36,"requested_max_output_tokens":[131072],"total_output_tokens":310855,"total_reasoning_output_tokens":208237,"total_visible_output_tokens":102618,"visible_token_observations":36},"generation_policy":{"generation_policy":"quality_generation_policy","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":"other","provider_model":"reflection/beam-1.0-501b-a23b","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":["GB2-01"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":35.29691164220398,"score":23.531274428135987},"GB2-02":{"attempts":3,"playable":42.884046015239896,"score":42.884046015239896},"GB2-03":{"attempts":3,"playable":52.87750491782324,"score":52.87750491782324},"GB2-04":{"attempts":3,"playable":46.555897757368065,"score":46.555897757368065},"GB2-05":{"attempts":3,"playable":53.092489485210734,"score":53.092489485210734},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":64.81678495955379,"score":43.21118997303586},"GB2-07":{"attempts":3,"playable":29.543759229023106,"score":29.543759229023106},"GB2-08":{"attempts":3,"playable":68.59840845472401,"score":68.59840845472401}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":25.20343736905481,"score":25.20343736905481},"GB2-02":{"attempts":1,"playable":49.202390090747556,"score":49.202390090747556},"GB2-03":{"attempts":1,"playable":79.22395843100819,"score":79.22395843100819},"GB2-04":{"attempts":1,"playable":59.90592412929252,"score":59.90592412929252},"GB2-05":{"attempts":1,"playable":55.586729506464316,"score":55.586729506464316},"GB2-06":{"attempts":1,"playable":74.40541600191756,"score":74.40541600191756},"GB2-07":{"attempts":1,"playable":42.795785782670485,"score":42.795785782670485},"GB2-08":{"attempts":1,"playable":61.660476908948816,"score":61.660476908948816}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":33.71410869399859,"score":33.71410869399859},"GB2-03":{"attempts":1,"playable":38.63152658204521,"score":38.63152658204521},"GB2-04":{"attempts":1,"playable":41.030525059730785,"score":41.030525059730785},"GB2-05":{"attempts":1,"playable":41.5897892321354,"score":41.5897892321354},"GB2-06":{"attempts":1,"playable":55.22815391719003,"score":55.22815391719003},"GB2-07":{"attempts":1,"playable":35.26415906479106,"score":35.26415906479106},"GB2-08":{"attempts":1,"playable":61.56173278343214,"score":61.56173278343214}},"none":{"GB2-01":{"attempts":1,"playable":45.39038591535316,"score":45.39038591535316},"GB2-02":{"attempts":1,"playable":45.735639260973535,"score":45.735639260973535},"GB2-03":{"attempts":1,"playable":40.777029740416296,"score":40.777029740416296},"GB2-04":{"attempts":1,"playable":38.73124408308089,"score":38.73124408308089},"GB2-05":{"attempts":1,"playable":62.100949717032485,"score":62.100949717032485},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":10.571332839607775,"score":10.571332839607775},"GB2-08":{"attempts":1,"playable":82.57301567179105,"score":82.57301567179105}}},"id":"reflection/beam-1.0-501b-a23b","is_recent_addition":true,"last_measured_at":"2026-10-22T10:56:58Z","match_totals_all":{"draws":1319,"losses":2370,"wins":1967},"match_totals_tracks":{"highest":{"draws":393,"losses":795,"wins":882},"medium":{"draws":420,"losses":861,"wins":533},"none":{"draws":506,"losses":714,"wins":552}},"model_slug":"reflection-beam-1-0-501b-a23b","overall":{"max":82.57301567179105,"mean":45.03682128257011,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":43,"overall_ranking_status":"ranked","per_game":{"GB2-01":25.20343736905481,"GB2-02":49.202390090747556,"GB2-03":79.22395843100819,"GB2-04":59.90592412929252,"GB2-05":55.586729506464316,"GB2-06":74.40541600191756,"GB2-07":42.795785782670485,"GB2-08":61.660476908948816},"per_game_all":{"GB2-02":42.884046015239896,"GB2-03":52.87750491782324,"GB2-04":46.555897757368065,"GB2-05":53.092489485210734,"GB2-07":29.543759229023106,"GB2-08":68.59840845472401},"per_game_match_totals_all":{"GB2-01":{"draws":159,"losses":286,"wins":93},"GB2-02":{"draws":551,"losses":206,"wins":59},"GB2-03":{"draws":156,"losses":308,"wins":294},"GB2-04":{"draws":429,"losses":213,"wins":138},"GB2-05":{"draws":0,"losses":415,"wins":415},"GB2-06":{"draws":24,"losses":224,"wins":324},"GB2-07":{"draws":0,"losses":472,"wins":176},"GB2-08":{"draws":0,"losses":246,"wins":468}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":68,"losses":179,"wins":27},"GB2-02":{"draws":183,"losses":47,"wins":34},"GB2-03":{"draws":16,"losses":58,"wins":184},"GB2-04":{"draws":110,"losses":55,"wins":103},"GB2-05":{"draws":0,"losses":139,"wins":137},"GB2-06":{"draws":16,"losses":79,"wins":187},"GB2-07":{"draws":0,"losses":137,"wins":79},"GB2-08":{"draws":0,"losses":101,"wins":131}},"medium":{"GB2-02":{"draws":171,"losses":105,"wins":6},"GB2-03":{"draws":88,"losses":119,"wins":45},"GB2-04":{"draws":153,"losses":77,"wins":20},"GB2-05":{"draws":0,"losses":169,"wins":109},"GB2-06":{"draws":8,"losses":145,"wins":137},"GB2-07":{"draws":0,"losses":146,"wins":76},"GB2-08":{"draws":0,"losses":100,"wins":140}},"none":{"GB2-01":{"draws":91,"losses":107,"wins":66},"GB2-02":{"draws":197,"losses":54,"wins":19},"GB2-03":{"draws":52,"losses":131,"wins":65},"GB2-04":{"draws":166,"losses":81,"wins":15},"GB2-05":{"draws":0,"losses":107,"wins":169},"GB2-07":{"draws":0,"losses":189,"wins":21},"GB2-08":{"draws":0,"losses":45,"wins":197}}},"per_game_raw_elo_all":{"GB2-02":1419.0205289380738,"GB2-03":1481.452229135926,"GB2-04":1451.8333592479303,"GB2-05":1480.1673267797057,"GB2-07":1158.1453394165214,"GB2-08":1678.7450284084716},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1219.3307996941694,"GB2-02":1468.5182951280656,"GB2-03":1759.4505949561456,"GB2-04":1556.6797002713301,"GB2-05":1509.9747424505683,"GB2-06":1842.91793842335,"GB2-07":1359.2162563003437,"GB2-08":1550.9433789973248},"medium":{"GB2-02":1346.7297591014767,"GB2-03":1333.0524078834699,"GB2-04":1408.4680077156581,"GB2-05":1334.2496502794113,"GB2-06":1509.6692315842165,"GB2-07":1264.1987368938587,"GB2-08":1549.555945432217},"none":{"GB2-01":1427.0502235015433,"GB2-02":1441.8135325846783,"GB2-03":1351.8536845681622,"GB2-04":1390.3523697568025,"GB2-05":1596.2775876091375,"GB2-07":851.0210250553617,"GB2-08":1935.7357607958725}},"per_game_tracks":{"highest":{"GB2-01":25.20343736905481,"GB2-02":49.202390090747556,"GB2-03":79.22395843100819,"GB2-04":59.90592412929252,"GB2-05":55.586729506464316,"GB2-06":74.40541600191756,"GB2-07":42.795785782670485,"GB2-08":61.660476908948816},"medium":{"GB2-02":33.71410869399859,"GB2-03":38.63152658204521,"GB2-04":41.030525059730785,"GB2-05":41.5897892321354,"GB2-06":55.22815391719003,"GB2-07":35.26415906479106,"GB2-08":61.56173278343214},"none":{"GB2-01":45.39038591535316,"GB2-02":45.735639260973535,"GB2-03":40.777029740416296,"GB2-04":38.73124408308089,"GB2-05":62.100949717032485,"GB2-07":10.571332839607775,"GB2-08":82.57301567179105}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.99801477751303,"medium":38.3774994166654,"none":40.7349496535319},"reasoning_agg":{"highest":{"max":79.22395843100819,"mean":55.99801477751303,"min":25.20343736905481},"medium":{"max":61.56173278343214,"mean":38.3774994166654,"min":0.0},"none":{"max":82.57301567179105,"mean":40.7349496535319,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.620515360847627}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:4f7f8021116dc716","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303000003},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14635563000000001,"mean":0.0939111476625,"median":0.10304704349999999,"min":0.032703412,"recorded_attempt_count":26,"run_count":16,"total":1.5025783626},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.03729904666666666,"mean":0.023546225995833333,"median":0.024102434966666666,"min":0.013816857666666668,"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":0.5271659940000001},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.3591713804},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.050486600000000006,"mean":0.0257422554375,"median":0.02408436405,"min":0.0093287,"recorded_attempt_count":13,"run_count":8,"total":0.2059380435},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"provider_reported":72},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.09944282164861112,"median":0.056673037849999996,"min":0.013816857666666668,"recorded_attempt_count":72,"run_count":48,"total":3.5146565168},"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":44.02566016592118,"highest":44.10754751657526,"medium":48.13742321348612,"none":39.83200976770216},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":6,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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":10,"repaired_rate":0.625},"baseline":{"admitted_plugins":24,"evaluated_cells":24,"first_pass_admitted":13,"first_pass_rate":0.5416666666666666,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":3},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"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":11,"repaired_rate":0.4583333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":40.524502353266186,"score":40.524502353266186},"GB2-02":{"attempts":6,"playable":50.67754589537687,"score":50.67754589537687},"GB2-03":{"attempts":6,"playable":36.06774436649127,"score":36.06774436649127},"GB2-04":{"attempts":6,"playable":49.83664482673682,"score":49.83664482673682},"GB2-05":{"attempts":6,"playable":49.35060496671742,"score":49.35060496671742},"GB2-06":{"attempts":6,"playable":55.796623307672064,"score":55.796623307672064},"GB2-07":{"attempts":6,"playable":39.0299007689409,"score":39.0299007689409},"GB2-08":{"attempts":6,"playable":35.534544897278245,"score":35.534544897278245}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":53.73091677979556,"score":53.73091677979556},"GB2-02":{"attempts":1,"playable":62.08937877277858,"score":62.08937877277858},"GB2-03":{"attempts":1,"playable":37.465851685848094,"score":37.465851685848094},"GB2-04":{"attempts":1,"playable":58.394290418980475,"score":58.394290418980475},"GB2-05":{"attempts":1,"playable":58.933959172423656,"score":58.933959172423656},"GB2-06":{"attempts":1,"playable":41.926482362262014,"score":41.926482362262014},"GB2-07":{"attempts":1,"playable":9.999947285460275,"score":9.999947285460275},"GB2-08":{"attempts":1,"playable":30.319553655053433,"score":30.319553655053433}},"medium":{"GB2-01":{"attempts":2,"playable":39.2576718127971,"score":39.2576718127971},"GB2-02":{"attempts":2,"playable":48.855378151929735,"score":48.855378151929735},"GB2-03":{"attempts":2,"playable":30.571431247102783,"score":30.571431247102783},"GB2-04":{"attempts":2,"playable":48.169684190025,"score":48.169684190025},"GB2-05":{"attempts":2,"playable":53.83810490868933,"score":53.83810490868933},"GB2-06":{"attempts":2,"playable":78.7538502336756,"score":78.7538502336756},"GB2-07":{"attempts":2,"playable":59.05623980217375,"score":59.05623980217375},"GB2-08":{"attempts":2,"playable":26.597025361495703,"score":26.597025361495703}},"none":{"GB2-01":{"attempts":3,"playable":28.584918467205895,"score":28.584918467205895},"GB2-02":{"attempts":3,"playable":41.087880761422284,"score":41.087880761422284},"GB2-03":{"attempts":3,"playable":40.16595016652294,"score":40.16595016652294},"GB2-04":{"attempts":3,"playable":42.945959871205,"score":42.945959871205},"GB2-05":{"attempts":3,"playable":35.27975081903928,"score":35.27975081903928},"GB2-06":{"attempts":3,"playable":46.70953732707857,"score":46.70953732707857},"GB2-07":{"attempts":3,"playable":48.03351521918865,"score":48.03351521918865},"GB2-08":{"attempts":3,"playable":49.68705567528561,"score":49.68705567528561}}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-10-22T10:14:35Z","match_totals_all":{"draws":6701,"losses":10009,"wins":6488},"match_totals_tracks":{"highest":{"draws":1092,"losses":1692,"wins":1078},"medium":{"draws":2364,"losses":2949,"wins":2425},"none":{"draws":3245,"losses":5368,"wins":2985}},"model_slug":"z-ai-glm-5-2","overall":{"max":78.7538502336756,"mean":44.602263922809975,"min":9.999947285460275},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":53.73091677979556,"GB2-02":62.08937877277858,"GB2-03":37.465851685848094,"GB2-04":58.394290418980475,"GB2-05":58.933959172423656,"GB2-06":41.926482362262014,"GB2-07":9.999947285460275,"GB2-08":30.319553655053433},"per_game_all":{"GB2-01":40.67329364832498,"GB2-02":50.79277688712583,"GB2-03":35.67036035186051,"GB2-04":49.76332440753908,"GB2-05":48.09505095138051,"GB2-06":54.46501966301821,"GB2-07":38.58493568935476,"GB2-08":34.16051972876557},"per_game_match_totals_all":{"GB2-01":{"draws":737,"losses":1538,"wins":655},"GB2-02":{"draws":1978,"losses":493,"wins":267},"GB2-03":{"draws":1044,"losses":1349,"wins":417},"GB2-04":{"draws":1601,"losses":723,"wins":498},"GB2-05":{"draws":0,"losses":1686,"wins":1346},"GB2-06":{"draws":130,"losses":1242,"wins":1496},"GB2-07":{"draws":0,"losses":1675,"wins":1287},"GB2-08":{"draws":1211,"losses":1303,"wins":522}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":178,"losses":145,"wins":165},"GB2-02":{"draws":223,"losses":67,"wins":166},"GB2-03":{"draws":166,"losses":224,"wins":78},"GB2-04":{"draws":225,"losses":89,"wins":156},"GB2-05":{"draws":0,"losses":213,"wins":293},"GB2-06":{"draws":25,"losses":282,"wins":171},"GB2-07":{"draws":0,"losses":449,"wins":43},"GB2-08":{"draws":275,"losses":223,"wins":6}},"medium":{"GB2-01":{"draws":270,"losses":472,"wins":234},"GB2-02":{"draws":692,"losses":132,"wins":90},"GB2-03":{"draws":403,"losses":475,"wins":58},"GB2-04":{"draws":540,"losses":229,"wins":173},"GB2-05":{"draws":0,"losses":479,"wins":531},"GB2-06":{"draws":40,"losses":190,"wins":726},"GB2-07":{"draws":0,"losses":422,"wins":568},"GB2-08":{"draws":419,"losses":550,"wins":45}},"none":{"GB2-01":{"draws":289,"losses":921,"wins":256},"GB2-02":{"draws":1063,"losses":294,"wins":11},"GB2-03":{"draws":475,"losses":650,"wins":281},"GB2-04":{"draws":836,"losses":405,"wins":169},"GB2-05":{"draws":0,"losses":994,"wins":522},"GB2-06":{"draws":65,"losses":770,"wins":599},"GB2-07":{"draws":0,"losses":804,"wins":676},"GB2-08":{"draws":517,"losses":530,"wins":471}}},"per_game_raw_elo_all":{"GB2-01":1378.1563453834103,"GB2-02":1482.0881668216225,"GB2-03":1305.8767139219563,"GB2-04":1476.6641089286588,"GB2-05":1406.2388486305574,"GB2-06":1520.1874741230247,"GB2-07":1270.7893091832063,"GB2-08":1254.2266116363608},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1506.6828414106808,"GB2-02":1571.732800393724,"GB2-03":1322.7574362855948,"GB2-04":1544.2741679954304,"GB2-05":1553.4308445223298,"GB2-06":1303.1139432865255,"GB2-07":835.8717944176922,"GB2-08":1198.6792613800972},"medium":{"GB2-01":1366.3156933590517,"GB2-02":1466.0321415750504,"GB2-03":1259.1446007367279,"GB2-04":1464.039994173175,"GB2-05":1487.867311937688,"GB2-06":1933.8259358258051,"GB2-07":1567.414648528588,"GB2-08":1157.7112122394992},"none":{"GB2-01":1261.4705013804987,"GB2-02":1408.4995584960932,"GB2-03":1335.728104743546,"GB2-04":1421.6781646173713,"GB2-05":1177.4183894316545,"GB2-06":1323.622543256743,"GB2-07":1409.0814846033388,"GB2-08":1406.289361289486}},"per_game_tracks":{"highest":{"GB2-01":53.73091677979556,"GB2-02":62.08937877277858,"GB2-03":37.465851685848094,"GB2-04":58.394290418980475,"GB2-05":58.933959172423656,"GB2-06":41.926482362262014,"GB2-07":9.999947285460275,"GB2-08":30.319553655053433},"medium":{"GB2-01":39.2576718127971,"GB2-02":48.855378151929735,"GB2-03":30.571431247102783,"GB2-04":48.169684190025,"GB2-05":53.83810490868933,"GB2-06":78.7538502336756,"GB2-07":59.05623980217375,"GB2-08":26.597025361495703},"none":{"GB2-01":29.031292352382284,"GB2-02":41.4335737366692,"GB2-03":38.973798122630654,"GB2-04":42.72599861361177,"GB2-05":31.51308877302855,"GB2-06":42.71472639311703,"GB2-07":46.69861998043024,"GB2-08":45.56498016974759}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:36:34Z","reasoning":{"highest":44.10754751657526,"medium":48.13742321348612,"none":41.56182103836853},"reasoning_agg":{"highest":{"max":62.08937877277858,"mean":44.10754751657526,"min":9.999947285460275},"medium":{"max":78.7538502336756,"mean":48.13742321348612,"min":26.597025361495703},"none":{"max":49.68705567528561,"mean":41.56182103836853,"min":28.584918467205895}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":6.575602175117595}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:5eb8a92443d870fd","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":0.21636246784000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.98845232184},"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":2.3773764379600006},"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":47.4675262538373,"highest":56.25954239099514,"medium":46.89141234726422,"none":38.94474624334523},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":43.58886020669786,"score":43.58886020669786},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.58150199040735,"score":28.387667993604897},"GB2-03":{"attempts":3,"playable":48.02412544710209,"score":48.02412544710209},"GB2-04":{"attempts":3,"playable":40.75039161111729,"score":40.75039161111729},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.64881940813009,"score":39.76587960542006},"GB2-06":{"attempts":3,"playable":55.92756820898964,"score":55.92756820898964},"GB2-07":{"attempts":3,"playable":58.957695445916045,"score":58.957695445916045},"GB2-08":{"attempts":3,"playable":37.55651660320088,"score":37.55651660320088}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":43.7336025520135,"score":43.7336025520135},"GB2-02":{"attempts":1,"playable":44.70370914710583,"score":44.70370914710583},"GB2-03":{"attempts":1,"playable":64.23733356120061,"score":64.23733356120061},"GB2-04":{"attempts":1,"playable":43.39074857518106,"score":43.39074857518106},"GB2-05":{"attempts":1,"playable":75.18060950858687,"score":75.18060950858687},"GB2-06":{"attempts":1,"playable":68.03368125265283,"score":68.03368125265283},"GB2-07":{"attempts":1,"playable":79.3667645839029,"score":79.3667645839029},"GB2-08":{"attempts":1,"playable":31.429889947317513,"score":31.429889947317513}},"medium":{"GB2-01":{"attempts":1,"playable":51.476596551571795,"score":51.476596551571795},"GB2-02":{"attempts":1,"playable":40.45929483370886,"score":40.45929483370886},"GB2-03":{"attempts":1,"playable":42.898486175202116,"score":42.898486175202116},"GB2-04":{"attempts":1,"playable":34.49952354608491,"score":34.49952354608491},"GB2-05":{"attempts":1,"playable":44.117029307673306,"score":44.117029307673306},"GB2-06":{"attempts":1,"playable":38.64474380409151,"score":38.64474380409151},"GB2-07":{"attempts":1,"playable":73.88004953954773,"score":73.88004953954773},"GB2-08":{"attempts":1,"playable":49.15557502023352,"score":49.15557502023352}},"none":{"GB2-01":{"attempts":1,"playable":35.55638151650827,"score":35.55638151650827},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.93655660490352,"score":36.93655660490352},"GB2-04":{"attempts":1,"playable":44.360902712085895,"score":44.360902712085895},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":61.104279570224584,"score":61.104279570224584},"GB2-07":{"attempts":1,"playable":23.626272214297504,"score":23.626272214297504},"GB2-08":{"attempts":1,"playable":32.0840848420516,"score":32.0840848420516}}},"id":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-10-22T10:17:38Z","match_totals_all":{"draws":2604,"losses":4402,"wins":3640},"match_totals_tracks":{"highest":{"draws":750,"losses":1373,"wins":1743},"medium":{"draws":967,"losses":1633,"wins":1268},"none":{"draws":887,"losses":1396,"wins":629}},"model_slug":"deepseek-deepseek-v4-pro-0813","overall":{"max":79.3667645839029,"mean":44.11983814025609,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":45,"overall_ranking_status":"ranked","per_game":{"GB2-01":43.7336025520135,"GB2-02":44.70370914710583,"GB2-03":64.23733356120061,"GB2-04":43.39074857518106,"GB2-05":75.18060950858687,"GB2-06":68.03368125265283,"GB2-07":79.3667645839029,"GB2-08":31.429889947317513},"per_game_all":{"GB2-01":43.58886020669786,"GB2-03":48.02412544710209,"GB2-04":40.75039161111729,"GB2-06":55.92756820898964,"GB2-07":58.957695445916045,"GB2-08":37.55651660320088},"per_game_match_totals_all":{"GB2-01":{"draws":382,"losses":657,"wins":425},"GB2-02":{"draws":681,"losses":195,"wins":36},"GB2-03":{"draws":265,"losses":645,"wins":494},"GB2-04":{"draws":765,"losses":470,"wins":177},"GB2-05":{"draws":0,"losses":418,"wins":596},"GB2-06":{"draws":31,"losses":653,"wins":750},"GB2-07":{"draws":0,"losses":632,"wins":856},"GB2-08":{"draws":480,"losses":732,"wins":306}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":274,"wins":199},"GB2-02":{"draws":355,"losses":81,"wins":20},"GB2-03":{"draws":24,"losses":171,"wins":273},"GB2-04":{"draws":236,"losses":154,"wins":82},"GB2-05":{"draws":0,"losses":130,"wins":376},"GB2-06":{"draws":12,"losses":156,"wins":310},"GB2-07":{"draws":0,"losses":105,"wins":387},"GB2-08":{"draws":108,"losses":302,"wins":96}},"medium":{"GB2-01":{"draws":269,"losses":111,"wins":108},"GB2-02":{"draws":326,"losses":114,"wins":16},"GB2-03":{"draws":40,"losses":264,"wins":164},"GB2-04":{"draws":183,"losses":222,"wins":65},"GB2-05":{"draws":0,"losses":288,"wins":220},"GB2-06":{"draws":15,"losses":302,"wins":161},"GB2-07":{"draws":0,"losses":132,"wins":362},"GB2-08":{"draws":134,"losses":200,"wins":172}},"none":{"GB2-01":{"draws":98,"losses":272,"wins":118},"GB2-03":{"draws":201,"losses":210,"wins":57},"GB2-04":{"draws":346,"losses":94,"wins":30},"GB2-06":{"draws":4,"losses":195,"wins":279},"GB2-07":{"draws":0,"losses":395,"wins":107},"GB2-08":{"draws":238,"losses":230,"wins":38}}},"per_game_raw_elo_all":{"GB2-01":1409.1496391849134,"GB2-03":1418.4448259740823,"GB2-04":1405.7875411704326,"GB2-06":1528.5772789641233,"GB2-07":1588.367767718277,"GB2-08":1274.5197810633565},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1411.2067580549813,"GB2-02":1433.8616231290046,"GB2-03":1566.9496404165254,"GB2-04":1426.8484511914412,"GB2-05":1810.9124887199573,"GB2-06":1726.2396570939766,"GB2-07":1881.5437709630335,"GB2-08":1210.3653898544735},"medium":{"GB2-01":1485.064157160733,"GB2-02":1400.9249471961994,"GB2-03":1370.3257142931552,"GB2-04":1356.1524824259413,"GB2-05":1366.3327066650966,"GB2-06":1253.3842315432769,"GB2-07":1780.9551753735718,"GB2-08":1395.9900558230645},"none":{"GB2-01":1331.1780023390265,"GB2-03":1318.059123212566,"GB2-04":1434.3616898939154,"GB2-06":1606.1079482551165,"GB2-07":1102.6043568182258,"GB2-08":1217.2038975125317}},"per_game_tracks":{"highest":{"GB2-01":43.7336025520135,"GB2-02":44.70370914710583,"GB2-03":64.23733356120061,"GB2-04":43.39074857518106,"GB2-05":75.18060950858687,"GB2-06":68.03368125265283,"GB2-07":79.3667645839029,"GB2-08":31.429889947317513},"medium":{"GB2-01":51.476596551571795,"GB2-02":40.45929483370886,"GB2-03":42.898486175202116,"GB2-04":34.49952354608491,"GB2-05":44.117029307673306,"GB2-06":38.64474380409151,"GB2-07":73.88004953954773,"GB2-08":49.15557502023352},"none":{"GB2-01":35.55638151650827,"GB2-03":36.93655660490352,"GB2-04":44.360902712085895,"GB2-06":61.104279570224584,"GB2-07":23.626272214297504,"GB2-08":32.0840848420516}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:42:11Z","reasoning":{"highest":56.25954239099514,"medium":46.89141234726422,"none":29.20855968250892},"reasoning_agg":{"highest":{"max":79.3667645839029,"mean":56.25954239099514,"min":31.429889947317513},"medium":{"max":73.88004953954773,"mean":46.89141234726422,"min":34.49952354608491},"none":{"max":61.104279570224584,"mean":29.20855968250892,"min":0.0}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.050982708486224}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:497ead746931241f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.913572594249},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.372620130294},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.202372454421}},"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":0.372620130294},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.202372454421},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.9135725942490001}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.176790095,"mean":0.062023549123500006,"median":0.0458058365,"min":0.014466934,"recorded_attempt_count":35,"run_count":24,"total":1.4885651789640002},"codegen_latency_ms":{"attempt_count":35,"max_ms":1560134,"mean_ms":432334.7916666667,"min_ms":52746,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1560134,"mean_ms":818090.375,"min_ms":426935,"run_count":8},"medium":{"attempt_count":12,"max_ms":673313,"mean_ms":392142.875,"min_ms":86869,"run_count":8},"none":{"attempt_count":12,"max_ms":170011,"mean_ms":86771.125,"min_ms":52746,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":74570,"output_mean":21422.416666666668,"output_min":2493,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":74570,"output_mean":43080.25,"output_min":21434,"run_count":8},"medium":{"attempt_count":12,"output_max":23131,"output_mean":16655.5,"output_min":5286,"run_count":8},"none":{"attempt_count":12,"output_max":8274,"output_mean":4531.5,"output_min":2493,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"all":46.673114893048705,"highest":48.66087916785606,"medium":53.59906688046658,"none":39.090461744887},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":39.679757899984104,"score":39.679757899984104},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.41673228124158,"score":28.277821520827718},"GB2-03":{"attempts":3,"playable":39.785302873609204,"score":39.785302873609204},"GB2-04":{"attempts":3,"playable":44.926446334203256,"score":44.926446334203256},"GB2-05":{"attempts":3,"playable":43.0336283597723,"score":43.0336283597723},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":63.836403109271686,"score":42.55760207284779},"GB2-07":{"attempts":3,"playable":66.57493997903667,"score":66.57493997903667},"GB2-08":{"attempts":3,"playable":46.03861391168669,"score":46.03861391168669}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":26.76025895314459,"score":26.76025895314459},"GB2-02":{"attempts":1,"playable":45.72291841826717,"score":45.72291841826717},"GB2-03":{"attempts":1,"playable":46.91244106034137,"score":46.91244106034137},"GB2-04":{"attempts":1,"playable":46.58599658196596,"score":46.58599658196596},"GB2-05":{"attempts":1,"playable":44.77795862910551,"score":44.77795862910551},"GB2-06":{"attempts":1,"playable":79.08151854326171,"score":79.08151854326171},"GB2-07":{"attempts":1,"playable":74.58333241559734,"score":74.58333241559734},"GB2-08":{"attempts":1,"playable":24.86260874116482,"score":24.86260874116482}},"medium":{"GB2-01":{"attempts":1,"playable":63.01274730604109,"score":63.01274730604109},"GB2-02":{"attempts":1,"playable":39.11054614421599,"score":39.11054614421599},"GB2-03":{"attempts":1,"playable":29.48020292684777,"score":29.48020292684777},"GB2-04":{"attempts":1,"playable":43.5497109160689,"score":43.5497109160689},"GB2-05":{"attempts":1,"playable":49.586979772087574,"score":49.586979772087574},"GB2-06":{"attempts":1,"playable":48.59128767528167,"score":48.59128767528167},"GB2-07":{"attempts":1,"playable":71.19498274641307,"score":71.19498274641307},"GB2-08":{"attempts":1,"playable":84.2660775567766,"score":84.2660775567766}},"none":{"GB2-01":{"attempts":1,"playable":29.26626744076663,"score":29.26626744076663},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":42.963264633638474,"score":42.963264633638474},"GB2-04":{"attempts":1,"playable":44.643631504574905,"score":44.643631504574905},"GB2-05":{"attempts":1,"playable":34.7359466781238,"score":34.7359466781238},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":53.94650477509957,"score":53.94650477509957},"GB2-08":{"attempts":1,"playable":28.987155437118652,"score":28.987155437118652}}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-10-22T10:14:58Z","match_totals_all":{"draws":2579,"losses":4437,"wins":3660},"match_totals_tracks":{"highest":{"draws":962,"losses":1566,"wins":1342},"medium":{"draws":768,"losses":1454,"wins":1646},"none":{"draws":849,"losses":1417,"wins":672}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":84.2660775567766,"mean":43.85926411899596,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":46,"overall_ranking_status":"ranked","per_game":{"GB2-01":26.76025895314459,"GB2-02":45.72291841826717,"GB2-03":46.91244106034137,"GB2-04":46.58599658196596,"GB2-05":44.77795862910551,"GB2-06":79.08151854326171,"GB2-07":74.58333241559734,"GB2-08":24.86260874116482},"per_game_all":{"GB2-01":39.679757899984104,"GB2-03":39.785302873609204,"GB2-04":44.926446334203256,"GB2-05":43.0336283597723,"GB2-07":66.57493997903667,"GB2-08":46.03861391168669},"per_game_match_totals_all":{"GB2-01":{"draws":205,"losses":801,"wins":460},"GB2-02":{"draws":676,"losses":200,"wins":36},"GB2-03":{"draws":418,"losses":682,"wins":304},"GB2-04":{"draws":893,"losses":348,"wins":173},"GB2-05":{"draws":0,"losses":876,"wins":640},"GB2-06":{"draws":21,"losses":354,"wins":581},"GB2-07":{"draws":0,"losses":520,"wins":970},"GB2-08":{"draws":366,"losses":656,"wins":496}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":42,"losses":345,"wins":103},"GB2-02":{"draws":344,"losses":82,"wins":30},"GB2-03":{"draws":164,"losses":183,"wins":121},"GB2-04":{"draws":282,"losses":117,"wins":73},"GB2-05":{"draws":0,"losses":284,"wins":222},"GB2-06":{"draws":13,"losses":97,"wins":368},"GB2-07":{"draws":0,"losses":130,"wins":364},"GB2-08":{"draws":117,"losses":328,"wins":61}},"medium":{"GB2-01":{"draws":35,"losses":169,"wins":284},"GB2-02":{"draws":332,"losses":118,"wins":6},"GB2-03":{"draws":97,"losses":295,"wins":76},"GB2-04":{"draws":295,"losses":124,"wins":53},"GB2-05":{"draws":0,"losses":259,"wins":245},"GB2-06":{"draws":8,"losses":257,"wins":213},"GB2-07":{"draws":0,"losses":147,"wins":349},"GB2-08":{"draws":1,"losses":85,"wins":420}},"none":{"GB2-01":{"draws":128,"losses":287,"wins":73},"GB2-03":{"draws":157,"losses":204,"wins":107},"GB2-04":{"draws":316,"losses":107,"wins":47},"GB2-05":{"draws":0,"losses":333,"wins":173},"GB2-07":{"draws":0,"losses":243,"wins":257},"GB2-08":{"draws":248,"losses":243,"wins":15}}},"per_game_raw_elo_all":{"GB2-01":1367.122099011897,"GB2-03":1341.8288866757473,"GB2-04":1438.7247513159482,"GB2-05":1350.8811377408572,"GB2-07":1676.2474326227739,"GB2-08":1433.430192475714},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1237.3997714374568,"GB2-02":1441.715564307572,"GB2-03":1405.2251172828837,"GB2-04":1451.5453424292382,"GB2-05":1374.6443254605404,"GB2-06":1932.6191159225905,"GB2-07":1792.8722920345979,"GB2-08":1139.045369353069},"medium":{"GB2-01":1598.5888814479329,"GB2-02":1390.3230506722994,"GB2-03":1249.372810459159,"GB2-04":1428.0808208593028,"GB2-05":1434.6176593252644,"GB2-06":1405.2281598917684,"GB2-07":1737.3881562111224,"GB2-08":1976.7481939153088},"none":{"GB2-01":1265.377644150301,"GB2-03":1370.8887322851988,"GB2-04":1436.5480906593039,"GB2-05":1243.381428436766,"GB2-07":1498.4818496226014,"GB2-08":1184.4970141587648}},"per_game_tracks":{"highest":{"GB2-01":26.76025895314459,"GB2-02":45.72291841826717,"GB2-03":46.91244106034137,"GB2-04":46.58599658196596,"GB2-05":44.77795862910551,"GB2-06":79.08151854326171,"GB2-07":74.58333241559734,"GB2-08":24.86260874116482},"medium":{"GB2-01":63.01274730604109,"GB2-02":39.11054614421599,"GB2-03":29.48020292684777,"GB2-04":43.5497109160689,"GB2-05":49.586979772087574,"GB2-06":48.59128767528167,"GB2-07":71.19498274641307,"GB2-08":84.2660775567766},"none":{"GB2-01":29.26626744076663,"GB2-03":42.963264633638474,"GB2-04":44.643631504574905,"GB2-05":34.7359466781238,"GB2-07":53.94650477509957,"GB2-08":28.987155437118652}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:30:11Z","reasoning":{"highest":48.66087916785606,"medium":53.59906688046658,"none":29.317846308665253},"reasoning_agg":{"highest":{"max":79.08151854326171,"mean":48.66087916785606,"min":24.86260874116482},"medium":{"max":84.2660775567766,"mean":53.59906688046658,"min":29.48020292684777},"none":{"max":53.94650477509957,"mean":29.317846308665253,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.281220571801327}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:b8b69826a88a8a88","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-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":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":0.779305}},"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-2026-10-09":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-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-10-09":19},"run_count":24,"token_priced_attempt_count":31,"total":4.45591875},"codegen_latency_ms":{"attempt_count":19,"max_ms":452838,"mean_ms":201000.75,"min_ms":115295,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":452838,"mean_ms":260996.125,"min_ms":140461,"run_count":8},"medium":{"attempt_count":9,"max_ms":181508,"mean_ms":141005.375,"min_ms":115295,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43637,"output_mean":21815.875,"output_min":13286,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43637,"output_mean":26965.5,"output_min":16148,"run_count":8},"medium":{"attempt_count":9,"output_max":19618,"output_mean":16666.25,"output_min":13286,"run_count":8}},"display_name":"GPT-5","economics":{"all":44.25067215585729,"highest":49.72400647627398,"medium":42.972800676487296,"none":41.601149945779035},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"first_pass_admitted":4,"first_pass_rate":0.6666666666666666,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"performance_rejections":1},"GB2-05":{"admitted":1},"GB2-06":{"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"performance_rejected_game_aliases":["GB2-04","GB2-06"],"performance_rejections":2,"repaired_admitted":2,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":43.85185074009586,"score":43.85185074009586},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.51257989044548,"score":27.00838659363032},"GB2-03":{"attempts":3,"playable":28.36401569724829,"score":28.36401569724829},"GB2-04":{"attempts":2,"playable":41.702013513006804,"score":41.702013513006804},"GB2-05":{"attempts":3,"playable":61.62804746955515,"score":61.62804746955515},"GB2-06":{"attempts":2,"playable":60.009643537756574,"score":60.009643537756574},"GB2-07":{"attempts":3,"playable":52.48259429885312,"score":52.48259429885312},"GB2-08":{"attempts":3,"playable":34.926852573534035,"score":34.926852573534035}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":39.88516968199495,"score":39.88516968199495},"GB2-02":{"attempts":1,"playable":42.13532105455252,"score":42.13532105455252},"GB2-03":{"attempts":1,"playable":37.3216534305196,"score":37.3216534305196},"GB2-04":{"attempts":1,"playable":40.32256245167176,"score":40.32256245167176},"GB2-05":{"attempts":1,"playable":75.85994355352197,"score":75.85994355352197},"GB2-06":{"attempts":1,"playable":71.00609136533129,"score":71.00609136533129},"GB2-07":{"attempts":1,"playable":53.151679935327536,"score":53.151679935327536},"GB2-08":{"attempts":1,"playable":38.10963033727216,"score":38.10963033727216}},"medium":{"GB2-01":{"attempts":1,"playable":21.102991173626982,"score":21.102991173626982},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.68167324318949,"score":31.68167324318949},"GB2-04":{"attempts":1,"playable":43.08146457434185,"score":43.08146457434185},"GB2-05":{"attempts":1,"playable":61.12400203797746,"score":61.12400203797746},"GB2-06":{"attempts":1,"playable":49.013195710181854,"score":49.013195710181854},"GB2-07":{"attempts":1,"playable":62.7419039670474,"score":62.7419039670474},"GB2-08":{"attempts":1,"playable":32.06437402904601,"score":32.06437402904601}},"none":{"GB2-01":{"attempts":1,"playable":70.56739136466564,"score":70.56739136466564},"GB2-02":{"attempts":1,"playable":38.88983872633843,"score":38.88983872633843},"GB2-03":{"attempts":1,"playable":16.08872041803578,"score":16.08872041803578},"GB2-05":{"attempts":1,"playable":47.900196817166005,"score":47.900196817166005},"GB2-07":{"attempts":1,"playable":41.55419899418444,"score":41.55419899418444},"GB2-08":{"attempts":1,"playable":34.60655335428394,"score":34.60655335428394}}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-10-22T10:48:27Z","match_totals_all":{"draws":2493,"losses":4511,"wins":3198},"match_totals_tracks":{"highest":{"draws":1153,"losses":1432,"wins":1287},"medium":{"draws":753,"losses":1629,"wins":1028},"none":{"draws":587,"losses":1450,"wins":883}},"model_slug":"gpt-5","overall":{"max":75.85994355352197,"mean":42.97545233799314,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":47,"overall_ranking_status":"partial","per_game":{"GB2-01":39.88516968199495,"GB2-02":42.13532105455252,"GB2-03":37.3216534305196,"GB2-04":40.32256245167176,"GB2-05":75.85994355352197,"GB2-06":71.00609136533129,"GB2-07":53.151679935327536,"GB2-08":38.10963033727216},"per_game_all":{"GB2-01":43.85185074009586,"GB2-03":28.36401569724829,"GB2-05":61.62804746955515,"GB2-07":52.48259429885312,"GB2-08":34.926852573534035},"per_game_match_totals_all":{"GB2-01":{"draws":197,"losses":741,"wins":526},"GB2-02":{"draws":692,"losses":210,"wins":16},"GB2-03":{"draws":402,"losses":843,"wins":159},"GB2-04":{"draws":574,"losses":275,"wins":93},"GB2-05":{"draws":0,"losses":598,"wins":920},"GB2-06":{"draws":32,"losses":392,"wins":532},"GB2-07":{"draws":0,"losses":737,"wins":745},"GB2-08":{"draws":596,"losses":715,"wins":207}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":78,"losses":262,"wins":148},"GB2-02":{"draws":355,"losses":95,"wins":12},"GB2-03":{"draws":150,"losses":234,"wins":84},"GB2-04":{"draws":316,"losses":130,"wins":26},"GB2-05":{"draws":0,"losses":126,"wins":380},"GB2-06":{"draws":13,"losses":141,"wins":324},"GB2-07":{"draws":0,"losses":243,"wins":249},"GB2-08":{"draws":241,"losses":201,"wins":64}},"medium":{"GB2-01":{"draws":62,"losses":360,"wins":66},"GB2-03":{"draws":182,"losses":243,"wins":43},"GB2-04":{"draws":258,"losses":145,"wins":67},"GB2-05":{"draws":0,"losses":202,"wins":304},"GB2-06":{"draws":19,"losses":251,"wins":208},"GB2-07":{"draws":0,"losses":192,"wins":302},"GB2-08":{"draws":232,"losses":236,"wins":38}},"none":{"GB2-01":{"draws":57,"losses":119,"wins":312},"GB2-02":{"draws":337,"losses":115,"wins":4},"GB2-03":{"draws":70,"losses":366,"wins":32},"GB2-05":{"draws":0,"losses":270,"wins":236},"GB2-07":{"draws":0,"losses":302,"wins":194},"GB2-08":{"draws":123,"losses":278,"wins":105}}},"per_game_raw_elo_all":{"GB2-01":1407.6016436427371,"GB2-03":1229.8857052997657,"GB2-05":1607.1145624584162,"GB2-07":1482.0811395884448,"GB2-08":1246.5454414275403},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1374.0403693405876,"GB2-02":1413.9927539670325,"GB2-03":1321.479031967501,"GB2-04":1402.9163475823598,"GB2-05":1824.868837727629,"GB2-06":1779.9539132896182,"GB2-07":1488.3975044184424,"GB2-08":1279.3058158572485},"medium":{"GB2-01":1168.467126363401,"GB2-03":1270.2636305980182,"GB2-04":1424.4490264744743,"GB2-05":1582.8383987827865,"GB2-06":1411.765916283855,"GB2-07":1614.0902992915317,"GB2-08":1216.9983053223523},"none":{"GB2-01":1680.297435224223,"GB2-02":1388.5794716462267,"GB2-03":1097.9144533337783,"GB2-05":1413.636450864834,"GB2-07":1343.75561505536,"GB2-08":1243.33220310302}},"per_game_tracks":{"highest":{"GB2-01":39.88516968199495,"GB2-02":42.13532105455252,"GB2-03":37.3216534305196,"GB2-04":40.32256245167176,"GB2-05":75.85994355352197,"GB2-06":71.00609136533129,"GB2-07":53.151679935327536,"GB2-08":38.10963033727216},"medium":{"GB2-01":21.102991173626982,"GB2-03":31.68167324318949,"GB2-04":43.08146457434185,"GB2-05":61.12400203797746,"GB2-06":49.013195710181854,"GB2-07":62.7419039670474,"GB2-08":32.06437402904601},"none":{"GB2-01":70.56739136466564,"GB2-02":38.88983872633843,"GB2-03":16.08872041803578,"GB2-05":47.900196817166005,"GB2-07":41.55419899418444,"GB2-08":34.60655335428394}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.72400647627398,"medium":37.601200591926386,"none":41.601149945779035},"reasoning_agg":{"highest":{"max":75.85994355352197,"mean":49.72400647627398,"min":37.3216534305196},"medium":{"max":62.7419039670474,"mean":37.601200591926386,"min":0.0},"none":{"max":70.56739136466564,"mean":41.601149945779035,"min":16.08872041803578}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":12.122805884347592}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:3d3f517232a395ad","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":0.0377622,"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":0.24666659999999999},"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":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054445},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"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":0.050544449999999984},"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":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"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":0.24666659999999999}},"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":0.0377622,"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":0.33399885000000007},"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":41.67769757666166,"highest":55.944079576511385,"medium":43.09830547732108,"none":25.990707676152496},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":51.27803535306779,"score":51.27803535306779},"GB2-02":{"attempts":3,"playable":43.82330728127939,"score":43.82330728127939},"GB2-03":{"attempts":3,"playable":38.51124290336671,"score":38.51124290336671},"GB2-04":{"attempts":3,"playable":42.03888755383161,"score":42.03888755383161},"GB2-05":{"attempts":3,"playable":40.020046334228574,"score":40.020046334228574},"GB2-06":{"attempts":3,"playable":52.59650149727735,"score":52.59650149727735},"GB2-07":{"attempts":3,"playable":39.20976987607681,"score":39.20976987607681},"GB2-08":{"attempts":3,"playable":25.94378981416501,"score":25.94378981416501}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":81.72246510648223,"score":81.72246510648223},"GB2-02":{"attempts":1,"playable":45.041034525671854,"score":45.041034525671854},"GB2-03":{"attempts":1,"playable":41.630423501094974,"score":41.630423501094974},"GB2-04":{"attempts":1,"playable":38.65772356241845,"score":38.65772356241845},"GB2-05":{"attempts":1,"playable":51.679841330210394,"score":51.679841330210394},"GB2-06":{"attempts":1,"playable":82.50812385667902,"score":82.50812385667902},"GB2-07":{"attempts":1,"playable":73.08001032541452,"score":73.08001032541452},"GB2-08":{"attempts":1,"playable":33.23301440411967,"score":33.23301440411967}},"medium":{"GB2-01":{"attempts":1,"playable":46.32814936741447,"score":46.32814936741447},"GB2-02":{"attempts":1,"playable":43.577838973325676,"score":43.577838973325676},"GB2-03":{"attempts":1,"playable":44.51671976389262,"score":44.51671976389262},"GB2-04":{"attempts":1,"playable":47.68144661820771,"score":47.68144661820771},"GB2-05":{"attempts":1,"playable":44.520205060639164,"score":44.520205060639164},"GB2-06":{"attempts":1,"playable":55.894370502391624,"score":55.894370502391624},"GB2-07":{"attempts":1,"playable":29.186551768443152,"score":29.186551768443152},"GB2-08":{"attempts":1,"playable":33.08116176425418,"score":33.08116176425418}},"none":{"GB2-01":{"attempts":1,"playable":25.783491585306674,"score":25.783491585306674},"GB2-02":{"attempts":1,"playable":42.85104834484064,"score":42.85104834484064},"GB2-03":{"attempts":1,"playable":29.386585445112534,"score":29.386585445112534},"GB2-04":{"attempts":1,"playable":39.77749248086865,"score":39.77749248086865},"GB2-05":{"attempts":1,"playable":23.860092611836148,"score":23.860092611836148},"GB2-06":{"attempts":1,"playable":19.387010132761397,"score":19.387010132761397},"GB2-07":{"attempts":1,"playable":15.362747534372776,"score":15.362747534372776},"GB2-08":{"attempts":1,"playable":11.517193274121183,"score":11.517193274121183}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-10-22T10:41:55Z","match_totals_all":{"draws":3421,"losses":5249,"wins":2920},"match_totals_tracks":{"highest":{"draws":1174,"losses":1167,"wins":1523},"medium":{"draws":1188,"losses":1681,"wins":995},"none":{"draws":1059,"losses":2401,"wins":402}},"model_slug":"gpt-5-6-luna","overall":{"max":82.50812385667902,"mean":41.67769757666165,"min":11.517193274121183},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":48,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.72246510648223,"GB2-02":45.041034525671854,"GB2-03":41.630423501094974,"GB2-04":38.65772356241845,"GB2-05":51.679841330210394,"GB2-06":82.50812385667902,"GB2-07":73.08001032541452,"GB2-08":33.23301440411967},"per_game_all":{"GB2-01":51.27803535306779,"GB2-02":43.82330728127939,"GB2-03":38.51124290336671,"GB2-04":42.03888755383161,"GB2-05":40.020046334228574,"GB2-06":52.59650149727735,"GB2-07":39.20976987607681,"GB2-08":25.94378981416501},"per_game_match_totals_all":{"GB2-01":{"draws":158,"losses":653,"wins":653},"GB2-02":{"draws":1079,"losses":248,"wins":39},"GB2-03":{"draws":552,"losses":631,"wins":221},"GB2-04":{"draws":914,"losses":377,"wins":119},"GB2-05":{"draws":0,"losses":924,"wins":594},"GB2-06":{"draws":80,"losses":669,"wins":685},"GB2-07":{"draws":0,"losses":924,"wins":556},"GB2-08":{"draws":638,"losses":823,"wins":53}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":95,"wins":392},"GB2-02":{"draws":344,"losses":85,"wins":27},"GB2-03":{"draws":197,"losses":191,"wins":80},"GB2-04":{"draws":286,"losses":150,"wins":34},"GB2-05":{"draws":0,"losses":251,"wins":255},"GB2-06":{"draws":43,"losses":65,"wins":370},"GB2-07":{"draws":0,"losses":136,"wins":358},"GB2-08":{"draws":303,"losses":194,"wins":7}},"medium":{"GB2-01":{"draws":64,"losses":235,"wins":189},"GB2-02":{"draws":367,"losses":81,"wins":8},"GB2-03":{"draws":151,"losses":199,"wins":118},"GB2-04":{"draws":331,"losses":86,"wins":53},"GB2-05":{"draws":0,"losses":285,"wins":221},"GB2-06":{"draws":15,"losses":218,"wins":245},"GB2-07":{"draws":0,"losses":361,"wins":131},"GB2-08":{"draws":260,"losses":216,"wins":30}},"none":{"GB2-01":{"draws":93,"losses":323,"wins":72},"GB2-02":{"draws":368,"losses":82,"wins":4},"GB2-03":{"draws":204,"losses":241,"wins":23},"GB2-04":{"draws":297,"losses":141,"wins":32},"GB2-05":{"draws":0,"losses":388,"wins":118},"GB2-06":{"draws":22,"losses":386,"wins":70},"GB2-07":{"draws":0,"losses":427,"wins":67},"GB2-08":{"draws":75,"losses":413,"wins":16}}},"per_game_raw_elo_all":{"GB2-01":1496.3368001559957,"GB2-02":1427.0588669163324,"GB2-03":1330.7161312983637,"GB2-04":1416.1309840284791,"GB2-05":1303.665988565172,"GB2-06":1492.92401186265,"GB2-07":1303.4749378342703,"GB2-08":1136.270699527475},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1826.8844970678897,"GB2-02":1436.4622060063948,"GB2-03":1359.2941290192314,"GB2-04":1389.7686799823766,"GB2-05":1460.6972811150617,"GB2-06":2001.8297458932973,"GB2-07":1767.6707832898958,"GB2-08":1229.1452299289494},"medium":{"GB2-01":1435.9943409190528,"GB2-02":1425.1694551062437,"GB2-03":1384.3846778567265,"GB2-04":1459.9972428932635,"GB2-05":1371.4061022778285,"GB2-06":1520.3842241833468,"GB2-07":1183.30461108164,"GB2-08":1227.5713796271684},"none":{"GB2-01":1226.1315624810447,"GB2-02":1419.5449396363579,"GB2-03":1248.4695870191333,"GB2-04":1398.6270292097968,"GB2-05":1078.8945823026256,"GB2-06":956.5580655113064,"GB2-07":959.4494191312749,"GB2-08":952.0954890263074}},"per_game_tracks":{"highest":{"GB2-01":81.72246510648223,"GB2-02":45.041034525671854,"GB2-03":41.630423501094974,"GB2-04":38.65772356241845,"GB2-05":51.679841330210394,"GB2-06":82.50812385667902,"GB2-07":73.08001032541452,"GB2-08":33.23301440411967},"medium":{"GB2-01":46.32814936741447,"GB2-02":43.577838973325676,"GB2-03":44.51671976389262,"GB2-04":47.68144661820771,"GB2-05":44.520205060639164,"GB2-06":55.894370502391624,"GB2-07":29.186551768443152,"GB2-08":33.08116176425418},"none":{"GB2-01":25.783491585306674,"GB2-02":42.85104834484064,"GB2-03":29.386585445112534,"GB2-04":39.77749248086865,"GB2-05":23.860092611836148,"GB2-06":19.387010132761397,"GB2-07":15.362747534372776,"GB2-08":11.517193274121183}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:34:53Z","reasoning":{"highest":55.944079576511385,"medium":43.09830547732108,"none":25.990707676152496},"reasoning_agg":{"highest":{"max":82.50812385667902,"mean":55.944079576511385,"min":33.23301440411967},"medium":{"max":55.894370502391624,"mean":43.09830547732108,"min":29.186551768443152},"none":{"max":42.85104834484064,"mean":25.990707676152496,"min":11.517193274121183}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.95337190035889}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3-1-flash:63124d7f1bcf1b26","codegen_cost_by_reasoning":{"highest":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"medium":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"none":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"historical-provider-setting-intensive":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":35,"max_ms":926386,"mean_ms":167464.70833333334,"min_ms":7440,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":12,"max_ms":926386,"mean_ms":393879.0,"min_ms":180915,"run_count":8},"medium":{"attempt_count":12,"max_ms":181663,"mean_ms":86858.125,"min_ms":40176,"run_count":8},"none":{"attempt_count":11,"max_ms":29718,"mean_ms":21657.0,"min_ms":7440,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":73160,"output_mean":16631.416666666668,"output_min":1375,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":12,"output_max":73160,"output_mean":36727.625,"output_min":23210,"run_count":8},"medium":{"attempt_count":12,"output_max":16723,"output_mean":9745.875,"output_min":4629,"run_count":8},"none":{"attempt_count":11,"output_max":6152,"output_mean":3420.75,"output_min":1375,"run_count":8}},"display_name":"Minimax M3.1 Flash","economics":{"all":44.66834956030138,"highest":45.783314018428065,"medium":48.609266973733476,"none":36.34070786337965},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":35,"effective_max_output_tokens":[524288],"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,"requested_max_output_token_observations":35,"requested_max_output_tokens":[524288],"total_output_tokens":399154,"total_reasoning_output_tokens":282019,"total_visible_output_tokens":117135,"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":524288,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3.1-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":38.885585796835166,"score":38.885585796835166},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.075137657478976,"score":27.383425104985985},"GB2-03":{"attempts":3,"playable":35.24943518699292,"score":35.24943518699292},"GB2-04":{"attempts":3,"playable":39.60594348983037,"score":39.60594348983037},"GB2-05":{"attempts":3,"playable":48.35776938826535,"score":48.35776938826535},"GB2-06":{"attempts":3,"playable":51.44164072930627,"score":51.44164072930627},"GB2-07":{"attempts":3,"playable":54.46972277057821,"score":54.46972277057821},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":28.952454588405473,"score":9.650818196135157}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":13.390431803074259,"score":13.390431803074259},"GB2-02":{"attempts":1,"playable":40.67958344281956,"score":40.67958344281956},"GB2-03":{"attempts":1,"playable":50.54959727007778,"score":50.54959727007778},"GB2-04":{"attempts":1,"playable":40.58088752661237,"score":40.58088752661237},"GB2-05":{"attempts":1,"playable":73.95238485765051,"score":73.95238485765051},"GB2-06":{"attempts":1,"playable":31.891909739455425,"score":31.891909739455425},"GB2-07":{"attempts":1,"playable":69.43840348930651,"score":69.43840348930651},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":68.03368590115801,"score":68.03368590115801},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.93167646471018,"score":31.93167646471018},"GB2-04":{"attempts":1,"playable":38.31206917209383,"score":38.31206917209383},"GB2-05":{"attempts":1,"playable":49.30620423283803,"score":49.30620423283803},"GB2-06":{"attempts":1,"playable":52.07186797591189,"score":52.07186797591189},"GB2-07":{"attempts":1,"playable":71.65691048101692,"score":71.65691048101692},"GB2-08":{"attempts":1,"playable":28.952454588405473,"score":28.952454588405473}},"none":{"GB2-01":{"attempts":1,"playable":35.23263968627323,"score":35.23263968627323},"GB2-02":{"attempts":1,"playable":41.470691872138396,"score":41.470691872138396},"GB2-03":{"attempts":1,"playable":23.26703182619079,"score":23.26703182619079},"GB2-04":{"attempts":1,"playable":39.92487377078491,"score":39.92487377078491},"GB2-05":{"attempts":1,"playable":21.81471907430751,"score":21.81471907430751},"GB2-06":{"attempts":1,"playable":70.3611444725515,"score":70.3611444725515},"GB2-07":{"attempts":1,"playable":22.31385434141116,"score":22.31385434141116},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"minimax/minimax-m3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T11:01:48Z","match_totals_all":{"draws":1423,"losses":3037,"wins":1919},"match_totals_tracks":{"highest":{"draws":429,"losses":951,"wins":643},"medium":{"draws":409,"losses":978,"wins":795},"none":{"draws":585,"losses":1108,"wins":481}},"model_slug":"minimax-minimax-m3-1-flash","overall":{"max":73.95238485765051,"mean":38.13054258286618,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["unknown_capability_evidence"],"overall_official_rank":49,"overall_ranking_status":"partial","per_game":{"GB2-01":13.390431803074259,"GB2-02":40.67958344281956,"GB2-03":50.54959727007778,"GB2-04":40.58088752661237,"GB2-05":73.95238485765051,"GB2-06":31.891909739455425,"GB2-07":69.43840348930651},"per_game_all":{"GB2-01":38.885585796835166,"GB2-03":35.24943518699292,"GB2-04":39.60594348983037,"GB2-05":48.35776938826535,"GB2-06":51.44164072930627,"GB2-07":54.46972277057821},"per_game_match_totals_all":{"GB2-01":{"draws":91,"losses":483,"wins":344},"GB2-02":{"draws":422,"losses":114,"wins":12},"GB2-03":{"draws":278,"losses":541,"wins":137},"GB2-04":{"draws":620,"losses":305,"wins":67},"GB2-05":{"draws":0,"losses":457,"wins":395},"GB2-06":{"draws":12,"losses":608,"wins":539},"GB2-07":{"draws":0,"losses":309,"wins":347},"GB2-08":{"draws":0,"losses":220,"wins":78}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":217,"wins":26},"GB2-02":{"draws":202,"losses":64,"wins":8},"GB2-03":{"draws":44,"losses":111,"wins":89},"GB2-04":{"draws":162,"losses":78,"wins":20},"GB2-05":{"draws":0,"losses":74,"wins":210},"GB2-06":{"draws":6,"losses":338,"wins":133},"GB2-07":{"draws":0,"losses":69,"wins":157}},"medium":{"GB2-01":{"draws":63,"losses":103,"wins":242},"GB2-03":{"draws":62,"losses":145,"wins":37},"GB2-04":{"draws":279,"losses":157,"wins":34},"GB2-05":{"draws":0,"losses":154,"wins":126},"GB2-06":{"draws":5,"losses":144,"wins":121},"GB2-07":{"draws":0,"losses":55,"wins":157},"GB2-08":{"draws":0,"losses":220,"wins":78}},"none":{"GB2-01":{"draws":13,"losses":163,"wins":76},"GB2-02":{"draws":220,"losses":50,"wins":4},"GB2-03":{"draws":172,"losses":285,"wins":11},"GB2-04":{"draws":179,"losses":70,"wins":13},"GB2-05":{"draws":0,"losses":229,"wins":59},"GB2-06":{"draws":1,"losses":126,"wins":285},"GB2-07":{"draws":0,"losses":185,"wins":33}}},"per_game_raw_elo_all":{"GB2-01":1343.8478156987233,"GB2-03":1298.5428591002885,"GB2-04":1397.2509928721945,"GB2-05":1420.580148385842,"GB2-06":1459.746926771153,"GB2-07":1512.3713304324694},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1051.7566065973201,"GB2-02":1402.6486420553556,"GB2-03":1437.1420048044706,"GB2-04":1404.944505660186,"GB2-05":1786.6627218559458,"GB2-06":1151.515261061546,"GB2-07":1710.2766610221354},"medium":{"GB2-01":1651.877813152917,"GB2-03":1272.5973547858773,"GB2-04":1387.020287044288,"GB2-05":1431.1251064513792,"GB2-06":1459.532985297705,"GB2-07":1744.6866293574492,"GB2-08":1184.125005348467},"none":{"GB2-01":1327.9090273459326,"GB2-02":1408.8229084190225,"GB2-03":1185.8892177105176,"GB2-04":1399.7881859121096,"GB2-05":1043.9526168502007,"GB2-06":1768.1925339542086,"GB2-07":1082.1507009178245}},"per_game_tracks":{"highest":{"GB2-01":13.390431803074259,"GB2-02":40.67958344281956,"GB2-03":50.54959727007778,"GB2-04":40.58088752661237,"GB2-05":73.95238485765051,"GB2-06":31.891909739455425,"GB2-07":69.43840348930651},"medium":{"GB2-01":68.03368590115801,"GB2-03":31.93167646471018,"GB2-04":38.31206917209383,"GB2-05":49.30620423283803,"GB2-06":52.07186797591189,"GB2-07":71.65691048101692,"GB2-08":28.952454588405473},"none":{"GB2-01":35.23263968627323,"GB2-02":41.470691872138396,"GB2-03":23.26703182619079,"GB2-04":39.92487377078491,"GB2-05":21.81471907430751,"GB2-06":70.3611444725515,"GB2-07":22.31385434141116}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.060399766124554,"medium":42.53310860201679,"none":31.79811938045719},"reasoning_agg":{"highest":{"max":73.95238485765051,"mean":40.060399766124554,"min":0.0},"medium":{"max":71.65691048101692,"mean":42.53310860201679,"min":0.0},"none":{"max":70.3611444725515,"mean":31.79811938045719,"min":0.0}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":10.734989221559598}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:4cb2c3e36848a3c5","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08754999999999999,"mean":0.04313775,"median":0.033532,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.34510199999999996}},"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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.39097600000000005},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08754999999999999,"mean":0.04313775,"median":0.033532,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.34510199999999996},"historical-provider-setting-intensive":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552}},"codegen_cost_usd":{"admitted_cell_count":33,"cell_count":24,"cost_basis_counts":{"estimated":32,"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":15,"max":0.1097735,"mean":0.06116525,"median":0.054719000000000004,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":58},"recorded_attempt_count":32,"run_count":48,"token_priced_attempt_count":26,"total":3.6636299999999995},"codegen_latency_ms":{"attempt_count":26,"max_ms":79649,"mean_ms":37254.041666666664,"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":10,"max_ms":74310,"mean_ms":41174.25,"min_ms":21597,"run_count":8}},"codegen_output_tokens":{"attempt_count":58,"output_max":15813,"output_mean":7191.916666666667,"output_min":1943,"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":10,"output_max":6022,"output_mean":2920.75,"output_min":1943,"run_count":8}},"display_name":"o3","economics":{"all":45.66421959842963,"highest":46.11341994462908,"medium":45.88283496481851,"none":42.42313836324628},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[100000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":82,"output_token_observations":58,"provider_post_attempt_observations":10,"provider_post_attempts":10,"reasoning_token_observations":10,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[100000],"total_output_tokens":345212,"total_reasoning_output_tokens":5824,"total_visible_output_tokens":17542,"visible_token_observations":10},"generation_policy":{"generation_policy":"quality_generation_policy","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6785714285714286,"game_attempts":{"GB2-01":{"admitted":3,"model_code_failures":1},"GB2-02":{"performance_rejections":4},"GB2-03":{"admitted":1,"model_code_failures":3},"GB2-04":{"model_code_failures":4},"GB2-05":{"admitted":4},"GB2-06":{"admitted":4},"GB2-07":{"admitted":4},"GB2-08":{"admitted":3,"model_code_failures":1}},"model_code_failure_rate":0.32142857142857145,"model_code_failures":9,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-02"],"performance_rejections":4}},"headline_games_all":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":45.52519816947478,"score":40.45682254018322},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.61423590854792,"score":21.30711795427396},"GB2-03":{"attempts":6,"failed_attempts":4,"playable":39.04927795816515,"score":17.11989393657737},"GB2-04":{"attempts":6,"failed_attempts":4,"playable":42.843275280666475,"score":28.562183520444318},"GB2-05":{"attempts":6,"playable":48.40016824429063,"score":48.40016824429063},"GB2-06":{"attempts":6,"playable":44.968797508590875,"score":44.968797508590875},"GB2-07":{"attempts":6,"playable":46.981979614981555,"score":46.981979614981555},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":42.44495445481035,"score":38.53701380480354}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":60.8205075514987,"score":45.61538066362402},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":35.65183214213093,"score":8.912958035532732},"GB2-04":{"attempts":4,"failed_attempts":4,"score":0.0},"GB2-05":{"attempts":4,"playable":48.901739943330185,"score":48.901739943330185},"GB2-06":{"attempts":4,"playable":41.3521692574829,"score":41.3521692574829},"GB2-07":{"attempts":4,"playable":43.0589829732501,"score":43.0589829732501},"GB2-08":{"attempts":4,"failed_attempts":1,"playable":46.895287800081654,"score":35.17146585006124}},"medium":{"GB2-01":{"attempts":1,"playable":37.714378352125756,"score":37.714378352125756},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":41.30089972848673,"score":41.30089972848673},"GB2-05":{"attempts":1,"playable":44.951329299796704,"score":44.951329299796704},"GB2-06":{"attempts":1,"playable":45.5079637460376,"score":45.5079637460376},"GB2-07":{"attempts":1,"playable":58.66898009922765,"score":58.66898009922765},"GB2-08":{"attempts":1,"playable":47.1534585632366,"score":47.1534585632366}},"none":{"GB2-01":{"attempts":1,"playable":38.04070860479989,"score":38.04070860479989},"GB2-02":{"attempts":1,"playable":42.61423590854792,"score":42.61423590854792},"GB2-03":{"attempts":1,"playable":42.44672377419938,"score":42.44672377419938},"GB2-04":{"attempts":1,"playable":44.38565083284622,"score":44.38565083284622},"GB2-05":{"attempts":1,"playable":51.34743548974502,"score":51.34743548974502},"GB2-06":{"attempts":1,"playable":48.04625952225212,"score":48.04625952225212},"GB2-07":{"attempts":1,"playable":39.21797577246691,"score":39.21797577246691},"GB2-08":{"attempts":1,"playable":33.2861170011128,"score":33.2861170011128}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-10-22T10:48:59Z","match_totals_all":{"draws":2269,"losses":7949,"wins":5958},"match_totals_tracks":{"highest":{"draws":661,"losses":4804,"wins":3897},"medium":{"draws":538,"losses":1377,"wins":1035},"none":{"draws":1070,"losses":1768,"wins":1026}},"model_slug":"o3","overall":{"max":58.66898009922765,"mean":36.23140708720487,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":50,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.8205075514987,"GB2-03":35.65183214213093,"GB2-05":48.901739943330185,"GB2-06":41.3521692574829,"GB2-07":43.0589829732501,"GB2-08":46.89528780008164},"per_game_all":{"GB2-01":45.52519816947478,"GB2-05":48.40016824429063,"GB2-06":44.968797508590875,"GB2-07":46.981979614981555,"GB2-08":42.44495445481034},"per_game_match_totals_all":{"GB2-01":{"draws":277,"losses":1078,"wins":1089},"GB2-02":{"draws":365,"losses":87,"wins":6},"GB2-03":{"draws":252,"losses":474,"wins":212},"GB2-04":{"draws":573,"losses":265,"wins":106},"GB2-05":{"draws":0,"losses":1585,"wins":1447},"GB2-06":{"draws":62,"losses":1683,"wins":1121},"GB2-07":{"draws":0,"losses":1690,"wins":1276},"GB2-08":{"draws":740,"losses":1087,"wins":701}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":144,"losses":521,"wins":799},"GB2-03":{"draws":124,"losses":254,"wins":92},"GB2-05":{"draws":0,"losses":1054,"wins":968},"GB2-06":{"draws":25,"losses":1164,"wins":723},"GB2-07":{"draws":0,"losses":1163,"wins":813},"GB2-08":{"draws":368,"losses":648,"wins":502}},"medium":{"GB2-01":{"draws":94,"losses":267,"wins":131},"GB2-04":{"draws":322,"losses":122,"wins":28},"GB2-05":{"draws":0,"losses":280,"wins":224},"GB2-06":{"draws":29,"losses":261,"wins":188},"GB2-07":{"draws":0,"losses":214,"wins":284},"GB2-08":{"draws":93,"losses":233,"wins":180}},"none":{"GB2-01":{"draws":39,"losses":290,"wins":159},"GB2-02":{"draws":365,"losses":87,"wins":6},"GB2-03":{"draws":128,"losses":220,"wins":120},"GB2-04":{"draws":251,"losses":143,"wins":78},"GB2-05":{"draws":0,"losses":251,"wins":255},"GB2-06":{"draws":8,"losses":258,"wins":210},"GB2-07":{"draws":0,"losses":313,"wins":179},"GB2-08":{"draws":279,"losses":206,"wins":19}}},"per_game_raw_elo_all":{"GB2-01":1428.950298889357,"GB2-05":1419.7680752482802,"GB2-06":1349.6504036394729,"GB2-07":1411.6351355025915,"GB2-08":1336.9026263814924},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1578.1758610444256,"GB2-03":1306.5828017000717,"GB2-05":1425.9372920605417,"GB2-06":1294.4032197580957,"GB2-07":1360.9291793752632,"GB2-08":1406.99372259192},"medium":{"GB2-01":1352.724974415417,"GB2-04":1410.5828918591815,"GB2-05":1376.8202676606927,"GB2-06":1357.7494699631518,"GB2-07":1559.47109857469,"GB2-08":1374.0188407720661},"none":{"GB2-01":1355.9500612082281,"GB2-02":1417.7094752557712,"GB2-03":1366.398078926526,"GB2-04":1434.5531221880658,"GB2-05":1456.5466660236063,"GB2-06":1396.798521197171,"GB2-07":1314.5051285578213,"GB2-08":1229.695315780491}},"per_game_tracks":{"highest":{"GB2-01":60.8205075514987,"GB2-03":35.65183214213093,"GB2-05":48.901739943330185,"GB2-06":41.3521692574829,"GB2-07":43.0589829732501,"GB2-08":46.89528780008164},"medium":{"GB2-01":37.714378352125756,"GB2-04":41.30089972848673,"GB2-05":44.951329299796704,"GB2-06":45.5079637460376,"GB2-07":58.66898009922765,"GB2-08":47.1534585632366},"none":{"GB2-01":38.04070860479989,"GB2-02":42.61423590854792,"GB2-03":42.44672377419938,"GB2-04":44.38565083284622,"GB2-05":51.34743548974502,"GB2-06":48.04625952225212,"GB2-07":39.21797577246691,"GB2-08":33.2861170011128}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:12:27Z","reasoning":{"highest":31.858956674754452,"medium":34.41212622361388,"none":42.42313836324628},"reasoning_agg":{"highest":{"max":48.901739943330185,"mean":31.858956674754452,"min":0.0},"medium":{"max":58.66898009922765,"mean":34.41212622361388,"min":0.0},"none":{"max":51.34743548974502,"mean":42.42313836324628,"min":33.2861170011128}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.564181688491828}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:e66ff3c382888215","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":0.40577},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.428104},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.16760900000000004}},"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":0.428104},"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":0.16760899999999998},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40576999999999996}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.001483},"codegen_latency_ms":{"attempt_count":34,"max_ms":395404,"mean_ms":199903.16666666666,"min_ms":55601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":395404,"mean_ms":251379.375,"min_ms":180439,"run_count":8},"medium":{"attempt_count":14,"max_ms":353826,"mean_ms":258198.75,"min_ms":158866,"run_count":8},"none":{"attempt_count":9,"max_ms":131809,"mean_ms":90131.375,"min_ms":55601,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22808,"output_mean":12018.333333333334,"output_min":2752,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":22808,"output_mean":15068.125,"output_min":11085,"run_count":8},"medium":{"attempt_count":14,"output_max":21381,"output_mean":15556.75,"output_min":10057,"run_count":8},"none":{"attempt_count":9,"output_max":8609,"output_mean":5430.125,"output_min":2752,"run_count":8}},"display_name":"Seed 2.0 Code","economics":{"all":39.4690448156712,"highest":42.043159041407925,"medium":45.766634676578626,"none":29.64228437811501},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":38.23479876495882,"score":38.23479876495882},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":39.790007926051565,"score":26.526671950701044},"GB2-03":{"attempts":3,"playable":42.42516018003982,"score":42.42516018003982},"GB2-04":{"attempts":3,"playable":40.51379738986375,"score":40.51379738986375},"GB2-05":{"attempts":3,"playable":38.63637730894513,"score":38.63637730894513},"GB2-06":{"attempts":3,"playable":17.25382639402203,"score":17.25382639402203},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":37.09244158996715,"score":24.728294393311433},"GB2-08":{"attempts":3,"playable":59.75030885619761,"score":59.75030885619761}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":40.950766421087735,"score":40.950766421087735},"GB2-02":{"attempts":1,"playable":40.203320809376095,"score":40.203320809376095},"GB2-03":{"attempts":1,"playable":42.01719193515508,"score":42.01719193515508},"GB2-04":{"attempts":1,"playable":38.799966620939344,"score":38.799966620939344},"GB2-05":{"attempts":1,"playable":50.60744833477242,"score":50.60744833477242},"GB2-06":{"attempts":1,"playable":19.6037439182415,"score":19.6037439182415},"GB2-07":{"attempts":1,"playable":45.44097431764102,"score":45.44097431764102},"GB2-08":{"attempts":1,"playable":58.72185997405024,"score":58.72185997405024}},"medium":{"GB2-01":{"attempts":1,"playable":50.411814754967054,"score":50.411814754967054},"GB2-02":{"attempts":1,"playable":39.376695042727036,"score":39.376695042727036},"GB2-03":{"attempts":1,"playable":39.70641861518519,"score":39.70641861518519},"GB2-04":{"attempts":1,"playable":40.560587758157226,"score":40.560587758157226},"GB2-05":{"attempts":1,"playable":48.6308282546792,"score":48.6308282546792},"GB2-06":{"attempts":1,"playable":14.38119710788823,"score":14.38119710788823},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":87.29890120244643,"score":87.29890120244643}},"none":{"GB2-01":{"attempts":1,"playable":23.341815118821664,"score":23.341815118821664},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":45.551869989779156,"score":45.551869989779156},"GB2-04":{"attempts":1,"playable":42.180837790494664,"score":42.180837790494664},"GB2-05":{"attempts":1,"playable":16.670855337383752,"score":16.670855337383752},"GB2-06":{"attempts":1,"playable":17.77653815593636,"score":17.77653815593636},"GB2-07":{"attempts":1,"playable":28.74390886229328,"score":28.74390886229328},"GB2-08":{"attempts":1,"playable":33.23016539209617,"score":33.23016539209617}}},"id":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-10-22T10:37:00Z","match_totals_all":{"draws":2816,"losses":5243,"wins":2597},"match_totals_tracks":{"highest":{"draws":1191,"losses":1718,"wins":963},"medium":{"draws":797,"losses":1473,"wins":1106},"none":{"draws":828,"losses":2052,"wins":528}},"model_slug":"bytedance-seed-seed-2-0-code","overall":{"max":87.29890120244643,"mean":36.00865440475496,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":40.950766421087735,"GB2-02":40.203320809376095,"GB2-03":42.01719193515508,"GB2-04":38.799966620939344,"GB2-05":50.60744833477242,"GB2-06":19.6037439182415,"GB2-07":45.44097431764102,"GB2-08":58.72185997405024},"per_game_all":{"GB2-01":38.23479876495882,"GB2-03":42.42516018003982,"GB2-04":40.51379738986375,"GB2-05":38.63637730894513,"GB2-06":17.25382639402203,"GB2-08":59.75030885619761},"per_game_match_totals_all":{"GB2-01":{"draws":372,"losses":742,"wins":350},"GB2-02":{"draws":678,"losses":223,"wins":11},"GB2-03":{"draws":321,"losses":698,"wins":385},"GB2-04":{"draws":938,"losses":387,"wins":87},"GB2-05":{"draws":0,"losses":950,"wins":572},"GB2-06":{"draws":7,"losses":1215,"wins":212},"GB2-07":{"draws":0,"losses":647,"wins":343},"GB2-08":{"draws":500,"losses":381,"wins":637}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":198,"losses":196,"wins":94},"GB2-02":{"draws":343,"losses":108,"wins":5},"GB2-03":{"draws":126,"losses":225,"wins":117},"GB2-04":{"draws":303,"losses":142,"wins":25},"GB2-05":{"draws":0,"losses":255,"wins":251},"GB2-06":{"draws":2,"losses":395,"wins":81},"GB2-07":{"draws":0,"losses":285,"wins":213},"GB2-08":{"draws":219,"losses":112,"wins":177}},"medium":{"GB2-01":{"draws":64,"losses":220,"wins":204},"GB2-02":{"draws":335,"losses":115,"wins":6},"GB2-03":{"draws":97,"losses":250,"wins":121},"GB2-04":{"draws":299,"losses":136,"wins":37},"GB2-05":{"draws":0,"losses":268,"wins":240},"GB2-06":{"draws":1,"losses":418,"wins":59},"GB2-08":{"draws":1,"losses":66,"wins":439}},"none":{"GB2-01":{"draws":110,"losses":326,"wins":52},"GB2-03":{"draws":98,"losses":223,"wins":147},"GB2-04":{"draws":336,"losses":109,"wins":25},"GB2-05":{"draws":0,"losses":427,"wins":81},"GB2-06":{"draws":4,"losses":402,"wins":72},"GB2-07":{"draws":0,"losses":362,"wins":130},"GB2-08":{"draws":280,"losses":203,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1352.0625726173569,"GB2-03":1366.1780149761569,"GB2-04":1404.3768709626775,"GB2-05":1272.6926708423782,"GB2-06":918.9604723114159,"GB2-08":1598.8728539864733},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1384.3984902495647,"GB2-02":1398.9194075235487,"GB2-03":1362.6613465631103,"GB2-04":1390.8976910541594,"GB2-05":1447.3201903994598,"GB2-06":960.1701799068456,"GB2-07":1392.0605286890836,"GB2-08":1510.9776786173682},"medium":{"GB2-01":1474.896796230556,"GB2-02":1392.4221804958875,"GB2-03":1342.491948626952,"GB2-04":1404.7852326691805,"GB2-05":1422.7254253596175,"GB2-06":867.5110224910902,"GB2-08":2056.525170261555},"none":{"GB2-01":1196.89243137195,"GB2-03":1393.380749738408,"GB2-04":1417.447689164693,"GB2-05":948.0323967680579,"GB2-06":929.2002145363116,"GB2-07":1177.1658908114123,"GB2-08":1229.1157130804963}},"per_game_tracks":{"highest":{"GB2-01":40.950766421087735,"GB2-02":40.203320809376095,"GB2-03":42.01719193515508,"GB2-04":38.799966620939344,"GB2-05":50.60744833477242,"GB2-06":19.6037439182415,"GB2-07":45.44097431764102,"GB2-08":58.72185997405024},"medium":{"GB2-01":50.411814754967054,"GB2-02":39.376695042727036,"GB2-03":39.70641861518519,"GB2-04":40.560587758157226,"GB2-05":48.6308282546792,"GB2-06":14.38119710788823,"GB2-08":87.29890120244643},"none":{"GB2-01":23.341815118821664,"GB2-03":45.551869989779156,"GB2-04":42.180837790494664,"GB2-05":16.670855337383752,"GB2-06":17.77653815593636,"GB2-07":28.74390886229328,"GB2-08":33.23016539209617}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:22:36Z","reasoning":{"highest":42.043159041407925,"medium":40.0458053420063,"none":25.936998830850634},"reasoning_agg":{"highest":{"max":58.72185997405024,"mean":42.043159041407925,"min":19.6037439182415},"medium":{"max":87.29890120244643,"mean":40.0458053420063,"min":0.0},"none":{"max":45.551869989779156,"mean":25.936998830850634,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":16.10616021055729}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:6c1249aa2f6759fd","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":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.06623293499999999,"mean":0.04480870625,"median":0.0402421875,"min":0.0205156,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.35846965},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.028626384999999997,"mean":0.021101813124999997,"median":0.024224999999999997,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.16881450499999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.06623293499999999,"mean":0.04480870625,"median":0.0402421875,"min":0.0205156,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.35846965000000003},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.028626384999999997,"mean":0.021101813124999997,"median":0.024224999999999997,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.16881450499999998},"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":17,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.3521656,"mean":0.08720021666666666,"median":0.0402421875,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":38,"run_count":24,"total":2.0928052000000004},"codegen_latency_ms":{"attempt_count":38,"max_ms":2128037,"mean_ms":537328.375,"min_ms":33625,"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":13,"max_ms":394009,"mean_ms":249918.25,"min_ms":106640,"run_count":8},"none":{"attempt_count":14,"max_ms":139550,"mean_ms":102175.0,"min_ms":33625,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":142524,"output_mean":33293.458333333336,"output_min":2177,"run_count":24},"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":13,"output_max":24263,"output_mean":15845.5,"output_min":6781,"run_count":8},"none":{"attempt_count":14,"output_max":9194,"output_mean":6162.875,"output_min":2177,"run_count":8}},"display_name":"Qwen3.8 27B","economics":{"all":45.51421159814498,"highest":59.946240339342616,"medium":46.62728173061038,"none":35.044229850437645},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[131072],"finish_reason_observations":38,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":41,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"reconciliation_get_attempts":53,"requested_max_output_token_observations":27,"requested_max_output_tokens":[131072],"total_output_tokens":799043,"total_reasoning_output_tokens":636129,"total_visible_output_tokens":162914,"visible_token_observations":38},"generation_policy":{"generation_policy":"quality_generation_policy","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/qwen3.8-27b","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":["GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"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},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.5,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":50.701496866177145,"score":50.701496866177145},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.42563987976783,"score":28.28375991984522},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":45.79782404708458,"score":30.53188269805639},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":55.71923246140132,"score":37.146154974267546},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.33532037839802,"score":39.55688025226535},"GB2-06":{"attempts":3,"playable":40.326926330112826,"score":40.326926330112826},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":49.47625477951735,"score":32.984169853011565},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":47.65152087087082,"score":15.883840290290273}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":75.0305069857446,"score":75.0305069857446},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":71.26442352015377,"score":71.26442352015377},"GB2-05":{"attempts":1,"playable":59.247648242762516,"score":59.247648242762516},"GB2-06":{"attempts":1,"playable":28.254283266674413,"score":28.254283266674413},"GB2-07":{"attempts":1,"playable":78.2290591498496,"score":78.2290591498496},"GB2-08":{"attempts":1,"playable":47.65152087087082,"score":47.65152087087082}},"medium":{"GB2-01":{"attempts":1,"playable":52.756925688799186,"score":52.756925688799186},"GB2-02":{"attempts":1,"playable":42.291725234605046,"score":42.291725234605046},"GB2-03":{"attempts":1,"playable":48.8677686864839,"score":48.8677686864839},"GB2-04":{"attempts":1,"playable":40.17404140264886,"score":40.17404140264886},"GB2-05":{"attempts":1,"playable":59.42299251403354,"score":59.42299251403354},"GB2-06":{"attempts":1,"playable":62.15406817851705,"score":62.15406817851705},"GB2-07":{"attempts":1,"playable":20.723450409185098,"score":20.723450409185098},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"playable":24.317057923987672,"score":24.317057923987672},"GB2-02":{"attempts":1,"playable":42.55955452493062,"score":42.55955452493062},"GB2-03":{"attempts":1,"playable":42.727879407685265,"score":42.727879407685265},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":30.572427545147008,"score":30.572427545147008},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.8-27b","is_recent_addition":false,"last_measured_at":"2026-10-22T10:30:30Z","match_totals_all":{"draws":1881,"losses":3412,"wins":2899},"match_totals_tracks":{"highest":{"draws":307,"losses":1075,"wins":1570},"medium":{"draws":965,"losses":1369,"wins":1018},"none":{"draws":609,"losses":968,"wins":311}},"model_slug":"qwen-qwen3-8-27b","overall":{"max":78.2290591498496,"mean":34.42688889800329,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":52,"overall_ranking_status":"partial","per_game":{"GB2-01":75.0305069857446,"GB2-04":71.26442352015377,"GB2-05":59.247648242762516,"GB2-06":28.254283266674413,"GB2-07":78.2290591498496,"GB2-08":47.65152087087082},"per_game_all":{"GB2-01":50.701496866177145,"GB2-06":40.326926330112826},"per_game_match_totals_all":{"GB2-01":{"draws":254,"losses":614,"wins":596},"GB2-02":{"draws":727,"losses":172,"wins":9},"GB2-03":{"draws":267,"losses":407,"wins":264},"GB2-04":{"draws":443,"losses":205,"wins":292},"GB2-05":{"draws":0,"losses":418,"wins":592},"GB2-06":{"draws":54,"losses":870,"wins":508},"GB2-07":{"draws":0,"losses":512,"wins":476},"GB2-08":{"draws":136,"losses":214,"wins":162}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":123,"wins":355},"GB2-04":{"draws":142,"losses":69,"wins":259},"GB2-05":{"draws":0,"losses":209,"wins":297},"GB2-06":{"draws":19,"losses":350,"wins":111},"GB2-07":{"draws":0,"losses":110,"wins":386},"GB2-08":{"draws":136,"losses":214,"wins":162}},"medium":{"GB2-01":{"draws":110,"losses":183,"wins":195},"GB2-02":{"draws":363,"losses":87,"wins":4},"GB2-03":{"draws":169,"losses":171,"wins":128},"GB2-04":{"draws":301,"losses":136,"wins":33},"GB2-05":{"draws":0,"losses":209,"wins":295},"GB2-06":{"draws":22,"losses":181,"wins":273},"GB2-07":{"draws":0,"losses":402,"wins":90}},"none":{"GB2-01":{"draws":134,"losses":308,"wins":46},"GB2-02":{"draws":364,"losses":85,"wins":5},"GB2-03":{"draws":98,"losses":236,"wins":136},"GB2-06":{"draws":13,"losses":339,"wins":124}}},"per_game_raw_elo_all":{"GB2-01":1479.980211288711,"GB2-06":1283.9468216761734},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1733.8478915079072,"GB2-04":1658.852672696586,"GB2-05":1557.5883113534878,"GB2-06":1096.4175724605948,"GB2-07":1859.0281697501619,"GB2-08":1379.435862497781},"medium":{"GB2-01":1497.3237199341686,"GB2-02":1415.2072999348557,"GB2-03":1422.323494718069,"GB2-04":1401.7489487055493,"GB2-05":1559.9196716122365,"GB2-06":1623.8407799152092,"GB2-07":1056.4230906585867},"none":{"GB2-01":1208.7690224240566,"GB2-02":1417.2854407653294,"GB2-03":1368.8427095012364,"GB2-06":1131.5821126527162}},"per_game_tracks":{"highest":{"GB2-01":75.0305069857446,"GB2-04":71.26442352015377,"GB2-05":59.247648242762516,"GB2-06":28.254283266674413,"GB2-07":78.2290591498496,"GB2-08":47.65152087087082},"medium":{"GB2-01":52.756925688799186,"GB2-02":42.291725234605046,"GB2-03":48.8677686864839,"GB2-04":40.17404140264886,"GB2-05":59.42299251403354,"GB2-06":62.15406817851705,"GB2-07":20.723450409185098},"none":{"GB2-01":24.317057923987672,"GB2-02":42.55955452493062,"GB2-03":42.727879407685265,"GB2-06":30.572427545147008}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.959680254506964,"medium":40.79887151428408,"none":17.522114925218823},"reasoning_agg":{"highest":{"max":78.2290591498496,"mean":44.959680254506964,"min":0.0},"medium":{"max":62.15406817851705,"mean":40.79887151428408,"min":0.0},"none":{"max":42.727879407685265,"mean":17.522114925218823,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":27.43756532928814}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:058c03a7b2f80826","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":0.0584754711},"medium":{"admitted_cell_count":22,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","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":0.010671596919999998}},"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","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":0.058475471099999995}},"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":2,"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":37.56834219906097,"highest":41.68094838247326,"medium":36.97031177327528,"none":35.46644587871767},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":22,"evaluated_cells":22,"first_pass_admitted":15,"first_pass_rate":0.6818181818181818,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":2,"infra_failures_excluded":1},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"infra_excluded_game_aliases":["GB2-03","GB2-04"],"infra_failures_excluded":2,"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":0.3181818181818182},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":24.81083917902185,"score":24.81083917902185},"GB2-02":{"attempts":5,"playable":41.548598118129526,"score":41.548598118129526},"GB2-03":{"attempts":4,"playable":37.727396959381956,"score":37.727396959381956},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.44758554246114,"score":27.631723694974095},"GB2-05":{"attempts":5,"failed_attempts":1,"playable":35.21036006082169,"score":23.473573373881127},"GB2-06":{"attempts":5,"playable":55.38727427637497,"score":55.38727427637497},"GB2-07":{"attempts":5,"playable":28.103130907705445,"score":28.103130907705445},"GB2-08":{"attempts":5,"playable":33.79921935805197,"score":33.79921935805197}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":15.776596121738628,"score":15.776596121738628},"GB2-02":{"attempts":1,"playable":43.050438176333934,"score":43.050438176333934},"GB2-03":{"attempts":1,"playable":34.665221552137155,"score":34.665221552137155},"GB2-04":{"attempts":1,"playable":42.21659117460939,"score":42.21659117460939},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":82.57875581898149,"score":82.57875581898149},"GB2-07":{"attempts":1,"playable":39.138613088693965,"score":39.138613088693965},"GB2-08":{"attempts":1,"playable":34.34042274481828,"score":34.34042274481828}},"medium":{"GB2-01":{"attempts":3,"playable":38.326187663053844,"score":38.326187663053844},"GB2-02":{"attempts":3,"playable":39.81243126358752,"score":39.81243126358752},"GB2-03":{"attempts":2,"playable":43.72222815494095,"score":43.72222815494095},"GB2-04":{"attempts":2,"playable":40.67857991031289,"score":40.67857991031289},"GB2-05":{"attempts":3,"playable":25.930970235547836,"score":25.930970235547836},"GB2-06":{"attempts":3,"playable":26.119454075981483,"score":26.119454075981483},"GB2-07":{"attempts":3,"playable":25.618690763625803,"score":25.618690763625803},"GB2-08":{"attempts":3,"playable":37.20496570717597,"score":37.20496570717597}},"none":{"GB2-01":{"attempts":1,"playable":20.32973375227308,"score":20.32973375227308},"GB2-02":{"attempts":1,"playable":41.78292491446713,"score":41.78292491446713},"GB2-03":{"attempts":1,"playable":34.79474117106777,"score":34.79474117106777},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":44.489749886095545,"score":44.489749886095545},"GB2-06":{"attempts":1,"playable":57.463612934161944,"score":57.463612934161944},"GB2-07":{"attempts":1,"playable":19.552088870796563,"score":19.552088870796563},"GB2-08":{"attempts":1,"playable":29.852269622161653,"score":29.852269622161653}}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:17:35Z","match_totals_all":{"draws":4603,"losses":9226,"wins":3601},"match_totals_tracks":{"highest":{"draws":1147,"losses":1449,"wins":764},"medium":{"draws":2656,"losses":5917,"wins":2099},"none":{"draws":800,"losses":1860,"wins":738}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":82.57875581898149,"mean":34.060219483440115,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":53,"overall_ranking_status":"ranked","per_game":{"GB2-01":15.776596121738628,"GB2-02":43.050438176333934,"GB2-03":34.665221552137155,"GB2-04":42.21659117460939,"GB2-06":82.57875581898149,"GB2-07":39.138613088693965,"GB2-08":34.34042274481828},"per_game_all":{"GB2-01":24.400647087104876,"GB2-02":41.70447883264011,"GB2-03":37.727396959381956,"GB2-06":57.347039817648884,"GB2-07":29.02316482976244,"GB2-08":35.20732566782758},"per_game_match_totals_all":{"GB2-01":{"draws":384,"losses":1543,"wins":515},"GB2-02":{"draws":1718,"losses":520,"wins":42},"GB2-03":{"draws":548,"losses":922,"wins":402},"GB2-04":{"draws":941,"losses":375,"wins":94},"GB2-05":{"draws":0,"losses":1426,"wins":600},"GB2-06":{"draws":59,"losses":1367,"wins":964},"GB2-07":{"draws":0,"losses":1863,"wins":615},"GB2-08":{"draws":953,"losses":1210,"wins":369}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":102,"losses":366,"wins":20},"GB2-02":{"draws":338,"losses":98,"wins":20},"GB2-03":{"draws":140,"losses":249,"wins":79},"GB2-04":{"draws":284,"losses":135,"wins":51},"GB2-06":{"draws":33,"losses":71,"wins":374},"GB2-07":{"draws":0,"losses":314,"wins":180},"GB2-08":{"draws":250,"losses":216,"wins":40}},"medium":{"GB2-01":{"draws":179,"losses":834,"wins":453},"GB2-02":{"draws":1013,"losses":335,"wins":20},"GB2-03":{"draws":272,"losses":422,"wins":242},"GB2-04":{"draws":657,"losses":240,"wins":43},"GB2-05":{"draws":0,"losses":1139,"wins":381},"GB2-06":{"draws":14,"losses":1085,"wins":335},"GB2-07":{"draws":0,"losses":1141,"wins":349},"GB2-08":{"draws":521,"losses":721,"wins":276}},"none":{"GB2-01":{"draws":103,"losses":343,"wins":42},"GB2-02":{"draws":367,"losses":87,"wins":2},"GB2-03":{"draws":136,"losses":251,"wins":81},"GB2-05":{"draws":0,"losses":287,"wins":219},"GB2-06":{"draws":12,"losses":211,"wins":255},"GB2-07":{"draws":0,"losses":408,"wins":86},"GB2-08":{"draws":182,"losses":273,"wins":53}}},"per_game_raw_elo_all":{"GB2-01":1195.3209274807607,"GB2-02":1410.5463794466023,"GB2-03":1324.6749607185159,"GB2-06":1563.6329387642115,"GB2-07":1167.660252842056,"GB2-08":1250.602798863611},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1091.9818397021772,"GB2-02":1421.0892283861301,"GB2-03":1297.6896150223681,"GB2-04":1417.726077183337,"GB2-06":2003.3019185527248,"GB2-07":1313.506647691721,"GB2-08":1240.589423296724},"medium":{"GB2-01":1335.760743279101,"GB2-02":1399.2964610399663,"GB2-03":1377.4738180591712,"GB2-04":1405.6818952807876,"GB2-05":1165.3200731015509,"GB2-06":1141.767237907809,"GB2-07":1152.757229492454,"GB2-08":1317.492042151744},"none":{"GB2-01":1158.220199461004,"GB2-02":1411.2534489137108,"GB2-03":1298.8614490740085,"GB2-05":1371.023223665772,"GB2-06":1545.8296598321006,"GB2-07":1036.7168813419933,"GB2-08":1193.7269311423652}},"per_game_tracks":{"highest":{"GB2-01":15.776596121738628,"GB2-02":43.050438176333934,"GB2-03":34.665221552137155,"GB2-04":42.21659117460939,"GB2-06":82.57875581898149,"GB2-07":39.138613088693965,"GB2-08":34.34042274481828},"medium":{"GB2-01":37.09561138730293,"GB2-02":40.28007340711927,"GB2-03":43.72222815494095,"GB2-04":40.67857991031289,"GB2-05":32.17917346042339,"GB2-06":31.998750699803203,"GB2-07":28.378792529796783,"GB2-08":41.42928463650282},"none":{"GB2-01":20.32973375227308,"GB2-02":41.78292491446713,"GB2-03":34.79474117106777,"GB2-05":44.489749886095545,"GB2-06":57.463612934161944,"GB2-07":19.552088870796563,"GB2-08":29.852269622161653}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:29:56Z","reasoning":{"highest":36.4708298346641,"medium":34.67668847177829,"none":31.03314014387796},"reasoning_agg":{"highest":{"max":82.57875581898149,"mean":36.4708298346641,"min":0.0},"medium":{"max":43.72222815494095,"mean":34.67668847177829,"min":25.618690763625803},"none":{"max":57.463612934161944,"mean":31.03314014387796,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":5.43768969078614}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:85ad0786a0c95cba","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":15},"recorded_attempt_count":15,"run_count":8,"total":0.0},"medium":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16},"recorded_attempt_count":16,"run_count":8,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16},"recorded_attempt_count":16,"run_count":8,"total":0.0},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":15},"recorded_attempt_count":15,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":42},"recorded_attempt_count":42,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":42,"max_ms":537122,"mean_ms":137533.5,"min_ms":13879,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":537122,"mean_ms":335588.75,"min_ms":221492,"run_count":8},"medium":{"attempt_count":11,"max_ms":84351,"mean_ms":41299.125,"min_ms":13879,"run_count":8},"none":{"attempt_count":16,"max_ms":68645,"mean_ms":35712.625,"min_ms":19448,"run_count":8}},"codegen_output_tokens":{"attempt_count":42,"output_max":39424,"output_mean":14219.625,"output_min":2263,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":39424,"output_mean":32529.75,"output_min":24807,"run_count":8},"medium":{"attempt_count":11,"output_max":9849,"output_mean":5340.25,"output_min":2263,"run_count":8},"none":{"attempt_count":16,"output_max":8167,"output_mean":4788.875,"output_min":2672,"run_count":8}},"display_name":"Space Bunny Alpha","economics":{"all":40.533848571130214,"highest":47.67157861632984,"medium":41.18214433445938,"none":37.725384497492506},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":42,"effective_max_output_tokens":[262144],"finish_reason_observations":42,"finish_reasons":["stop"],"indexed_attempts":42,"output_token_observations":42,"provider_post_attempt_observations":42,"provider_post_attempts":42,"reasoning_token_observations":42,"reconciliation_get_attempt_observations":42,"requested_max_output_token_observations":42,"requested_max_output_tokens":[262144],"total_output_tokens":341271,"total_visible_output_tokens":341271,"visible_token_observations":42},"generation_policy":{"generation_policy":"quality_generation_policy","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":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":["GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"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},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":56.21580345136561,"score":37.477202300910406},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.29051736667194,"score":28.193678244447963},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":41.25509782058089,"score":27.50339854705393},"GB2-04":{"attempts":3,"playable":41.5940522745631,"score":41.5940522745631},"GB2-05":{"attempts":3,"playable":33.9483087599314,"score":33.9483087599314},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":49.1713463123547,"score":32.7808975415698},"GB2-07":{"attempts":3,"playable":46.05918467889614,"score":46.05918467889614},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":28.993310991015772,"score":19.328873994010515}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.298147419750414,"score":63.298147419750414},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.029039770043696,"score":39.029039770043696},"GB2-05":{"attempts":1,"playable":45.23510433956989,"score":45.23510433956989},"GB2-06":{"attempts":1,"playable":39.79871275069954,"score":39.79871275069954},"GB2-07":{"attempts":1,"playable":74.6823363704155,"score":74.6823363704155},"GB2-08":{"attempts":1,"playable":23.98613104750001,"score":23.98613104750001}},"medium":{"GB2-01":{"attempts":1,"playable":49.133459482980804,"score":49.133459482980804},"GB2-02":{"attempts":1,"playable":42.986667969615034,"score":42.986667969615034},"GB2-03":{"attempts":1,"playable":46.16034034041906,"score":46.16034034041906},"GB2-04":{"attempts":1,"playable":41.862165351779765,"score":41.862165351779765},"GB2-05":{"attempts":1,"playable":13.117468260770659,"score":13.117468260770659},"GB2-06":{"attempts":1,"playable":58.54397987400986,"score":58.54397987400986},"GB2-07":{"attempts":1,"playable":36.47092906164046,"score":36.47092906164046},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.59436676372885,"score":41.59436676372885},"GB2-03":{"attempts":1,"playable":36.349855300742725,"score":36.349855300742725},"GB2-04":{"attempts":1,"playable":43.89095170186583,"score":43.89095170186583},"GB2-05":{"attempts":1,"playable":43.49235367945367,"score":43.49235367945367},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":27.02428860463244,"score":27.02428860463244},"GB2-08":{"attempts":1,"playable":34.000490934531534,"score":34.000490934531534}}},"id":"stealth/space-bunny-alpha","is_recent_addition":false,"last_measured_at":"2026-10-22T10:59:02Z","match_totals_all":{"draws":2581,"losses":4192,"wins":2413},"match_totals_tracks":{"highest":{"draws":646,"losses":1260,"wins":1028},"medium":{"draws":877,"losses":1603,"wins":876},"none":{"draws":1058,"losses":1329,"wins":509}},"model_slug":"stealth-space-bunny-alpha","overall":{"max":74.6823363704155,"mean":33.360699542672904,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":54,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.298147419750414,"GB2-04":39.029039770043696,"GB2-05":45.23510433956989,"GB2-06":39.79871275069954,"GB2-07":74.6823363704155,"GB2-08":23.98613104750001},"per_game_all":{"GB2-04":41.5940522745631,"GB2-05":33.9483087599314,"GB2-07":46.05918467889614},"per_game_match_totals_all":{"GB2-01":{"draws":230,"losses":325,"wins":421},"GB2-02":{"draws":723,"losses":174,"wins":11},"GB2-03":{"draws":217,"losses":474,"wins":247},"GB2-04":{"draws":917,"losses":385,"wins":110},"GB2-05":{"draws":0,"losses":1011,"wins":501},"GB2-06":{"draws":12,"losses":507,"wins":433},"GB2-07":{"draws":0,"losses":828,"wins":650},"GB2-08":{"draws":482,"losses":488,"wins":40}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":146,"losses":114,"wins":228},"GB2-04":{"draws":282,"losses":152,"wins":36},"GB2-05":{"draws":0,"losses":280,"wins":224},"GB2-06":{"draws":7,"losses":299,"wins":170},"GB2-07":{"draws":0,"losses":131,"wins":361},"GB2-08":{"draws":211,"losses":284,"wins":9}},"medium":{"GB2-01":{"draws":84,"losses":211,"wins":193},"GB2-02":{"draws":367,"losses":80,"wins":7},"GB2-03":{"draws":102,"losses":218,"wins":150},"GB2-04":{"draws":319,"losses":120,"wins":31},"GB2-05":{"draws":0,"losses":441,"wins":63},"GB2-06":{"draws":5,"losses":208,"wins":263},"GB2-07":{"draws":0,"losses":325,"wins":169}},"none":{"GB2-02":{"draws":356,"losses":94,"wins":4},"GB2-03":{"draws":115,"losses":256,"wins":97},"GB2-04":{"draws":316,"losses":113,"wins":43},"GB2-05":{"draws":0,"losses":290,"wins":214},"GB2-07":{"draws":0,"losses":372,"wins":120},"GB2-08":{"draws":271,"losses":204,"wins":31}}},"per_game_raw_elo_all":{"GB2-04":1412.8008753916056,"GB2-05":1203.6810135591286,"GB2-07":1409.0539065152636},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1601.5302839174165,"GB2-04":1392.713516073111,"GB2-05":1380.3783410660512,"GB2-06":1270.8423637489066,"GB2-07":1794.5689654660655,"GB2-08":1128.9867100202578},"medium":{"GB2-01":1462.7122023821519,"GB2-02":1420.5954315562858,"GB2-03":1398.6739514865012,"GB2-04":1414.9646069374792,"GB2-05":872.2142755267188,"GB2-06":1563.5280478963803,"GB2-07":1279.692085295147},"none":{"GB2-02":1409.7860420068369,"GB2-03":1312.8316313342802,"GB2-04":1430.7245031642274,"GB2-05":1358.450424084616,"GB2-07":1152.9006687845786,"GB2-08":1237.0821843948493}},"per_game_tracks":{"highest":{"GB2-01":63.298147419750414,"GB2-04":39.029039770043696,"GB2-05":45.23510433956989,"GB2-06":39.79871275069954,"GB2-07":74.6823363704155,"GB2-08":23.98613104750001},"medium":{"GB2-01":49.133459482980804,"GB2-02":42.986667969615034,"GB2-03":46.16034034041906,"GB2-04":41.862165351779765,"GB2-05":13.117468260770659,"GB2-06":58.54397987400986,"GB2-07":36.47092906164046},"none":{"GB2-02":41.59436676372885,"GB2-03":36.349855300742725,"GB2-04":43.89095170186583,"GB2-05":43.49235367945367,"GB2-07":27.02428860463244,"GB2-08":34.000490934531534}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":-2,"rank_movement_baseline_at":"2026-10-20T11:30:53Z","reasoning":{"highest":35.75368396224738,"medium":36.034376292651956,"none":28.29403837311938},"reasoning_agg":{"highest":{"max":74.6823363704155,"mean":35.75368396224738,"min":0.0},"medium":{"max":58.54397987400986,"mean":36.034376292651956,"min":0.0},"none":{"max":43.89095170186583,"mean":28.29403837311938,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":7.740337919532575}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:86cc87b0caaecf5b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000001},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.27157109999999995}},"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":1.8519749000000003},"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":37.441208061011764,"highest":38.45556867780423,"medium":31.21426623284735,"none":42.653789272383726},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":2}},"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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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}},"headline_games_all":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":37.790629878001106,"score":31.864294220270892},"GB2-02":{"attempts":6,"failed_attempts":2,"playable":43.23517950201647,"score":28.390709176694628},"GB2-03":{"attempts":6,"failed_attempts":1,"playable":47.92586417601083,"score":38.78011424934299},"GB2-04":{"attempts":6,"playable":43.26670270479725,"score":43.26670270479725},"GB2-05":{"attempts":6,"playable":15.351144473881149,"score":15.351144473881149},"GB2-06":{"attempts":6,"playable":37.71495446145075,"score":37.71495446145075},"GB2-07":{"attempts":6,"failed_attempts":1,"playable":42.59121467425032,"score":39.174870400787604},"GB2-08":{"attempts":6,"playable":31.65397461768626,"score":31.65397461768626}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":35.5580139463813,"score":17.77900697319065},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":45.1104027666528,"score":22.5552013833264},"GB2-03":{"attempts":2,"playable":47.72531267025522,"score":47.72531267025522},"GB2-04":{"attempts":2,"playable":39.85283322803161,"score":39.85283322803161},"GB2-05":{"attempts":2,"playable":18.2200862406468,"score":18.2200862406468},"GB2-06":{"attempts":2,"playable":43.11785708510108,"score":43.11785708510108},"GB2-07":{"attempts":2,"playable":45.12363358810948,"score":45.12363358810948},"GB2-08":{"attempts":2,"playable":32.93640989725552,"score":32.93640989725552}},"medium":{"GB2-01":{"attempts":2,"playable":40.95851748576041,"score":40.95851748576041},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.956419185278236,"score":21.978209592639118},"GB2-03":{"attempts":2,"playable":41.17778029777021,"score":41.17778029777021},"GB2-04":{"attempts":2,"playable":42.695455543709556,"score":42.695455543709556},"GB2-05":{"attempts":2,"playable":15.986261477999701,"score":15.986261477999701},"GB2-06":{"attempts":2,"playable":13.775747877551384,"score":13.775747877551384},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.498065640776254,"score":10.249032820388127},"GB2-08":{"attempts":2,"playable":30.665882353933032,"score":30.665882353933032}},"none":{"GB2-01":{"attempts":2,"playable":36.85535820186162,"score":36.85535820186162},"GB2-02":{"attempts":2,"playable":40.63871655411837,"score":40.63871655411837},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":54.87449956000706,"score":27.43724978000353},"GB2-04":{"attempts":2,"playable":47.25181934265058,"score":47.25181934265058},"GB2-05":{"attempts":2,"playable":11.847085702996953,"score":11.847085702996953},"GB2-06":{"attempts":2,"playable":56.2512584216998,"score":56.2512584216998},"GB2-07":{"attempts":2,"playable":62.15194479386521,"score":62.15194479386521},"GB2-08":{"attempts":2,"playable":31.359631601870227,"score":31.359631601870227}}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-22T10:33:29Z","match_totals_all":{"draws":5232,"losses":10542,"wins":4557},"match_totals_tracks":{"highest":{"draws":1441,"losses":3274,"wins":1571},"medium":{"draws":1846,"losses":3882,"wins":1052},"none":{"draws":1945,"losses":3386,"wins":1934}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":62.15194479386521,"mean":33.27459553811394,"min":10.249032820388127},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":55,"overall_ranking_status":"ranked","per_game":{"GB2-01":35.5580139463813,"GB2-02":45.1104027666528,"GB2-03":47.72531267025522,"GB2-04":39.85283322803161,"GB2-05":18.2200862406468,"GB2-06":43.11785708510108,"GB2-07":45.12363358810948,"GB2-08":32.93640989725552},"per_game_all":{"GB2-01":37.790629878001106,"GB2-02":43.23517950201647,"GB2-03":47.92586417601083,"GB2-04":43.26670270479725,"GB2-05":15.351144473881149,"GB2-06":37.71495446145075,"GB2-07":42.59121467425032,"GB2-08":31.65397461768626},"per_game_match_totals_all":{"GB2-01":{"draws":435,"losses":1328,"wins":679},"GB2-02":{"draws":1437,"losses":354,"wins":36},"GB2-03":{"draws":519,"losses":1074,"wins":751},"GB2-04":{"draws":1757,"losses":756,"wins":309},"GB2-05":{"draws":0,"losses":2583,"wins":445},"GB2-06":{"draws":44,"losses":1834,"wins":990},"GB2-07":{"draws":0,"losses":1351,"wins":1113},"GB2-08":{"draws":1040,"losses":1262,"wins":234}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":95,"losses":274,"wins":119},"GB2-02":{"draws":343,"losses":85,"wins":30},"GB2-03":{"draws":137,"losses":455,"wins":346},"GB2-04":{"draws":561,"losses":296,"wins":83},"GB2-05":{"draws":0,"losses":830,"wins":178},"GB2-06":{"draws":30,"losses":553,"wins":373},"GB2-07":{"draws":0,"losses":566,"wins":420},"GB2-08":{"draws":275,"losses":215,"wins":22}},"medium":{"GB2-01":{"draws":157,"losses":515,"wins":304},"GB2-02":{"draws":383,"losses":70,"wins":3},"GB2-03":{"draws":298,"losses":432,"wins":206},"GB2-04":{"draws":629,"losses":236,"wins":75},"GB2-05":{"draws":0,"losses":856,"wins":154},"GB2-06":{"draws":4,"losses":840,"wins":112},"GB2-07":{"draws":0,"losses":402,"wins":92},"GB2-08":{"draws":375,"losses":531,"wins":106}},"none":{"GB2-01":{"draws":183,"losses":539,"wins":256},"GB2-02":{"draws":711,"losses":199,"wins":3},"GB2-03":{"draws":84,"losses":187,"wins":199},"GB2-04":{"draws":567,"losses":224,"wins":151},"GB2-05":{"draws":0,"losses":897,"wins":113},"GB2-06":{"draws":10,"losses":441,"wins":505},"GB2-07":{"draws":0,"losses":383,"wins":601},"GB2-08":{"draws":390,"losses":516,"wins":106}}},"per_game_raw_elo_all":{"GB2-01":1353.0497968775405,"GB2-02":1422.461728170325,"GB2-03":1415.0754790534568,"GB2-04":1425.7564168036395,"GB2-05":917.2642875653223,"GB2-06":1237.3751598370566,"GB2-07":1351.5990458328931,"GB2-08":1212.5818601002063},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1331.1944597406516,"GB2-02":1436.9968309883384,"GB2-03":1413.8765901128697,"GB2-04":1399.1647486883899,"GB2-05":978.2130695901091,"GB2-06":1329.9897612015488,"GB2-07":1388.1206140473962,"GB2-08":1226.069957477825},"medium":{"GB2-01":1384.473292361055,"GB2-02":1428.0947099292284,"GB2-03":1355.3473537584414,"GB2-04":1421.4196135278132,"GB2-05":934.1716164121358,"GB2-06":855.5323464574884,"GB2-07":1052.684430126098,"GB2-08":1202.184964556031},"none":{"GB2-01":1343.4816385309155,"GB2-02":1402.293643593408,"GB2-03":1476.0024932890594,"GB2-04":1456.6848881947158,"GB2-05":839.408176693722,"GB2-06":1526.6033718521326,"GB2-07":1613.9920933251851,"GB2-08":1209.490658266763}},"per_game_tracks":{"highest":{"GB2-01":35.5580139463813,"GB2-02":45.1104027666528,"GB2-03":47.72531267025522,"GB2-04":39.85283322803161,"GB2-05":18.2200862406468,"GB2-06":43.11785708510108,"GB2-07":45.12363358810948,"GB2-08":32.93640989725552},"medium":{"GB2-01":40.95851748576041,"GB2-02":43.956419185278236,"GB2-03":41.17778029777021,"GB2-04":42.695455543709556,"GB2-05":15.986261477999701,"GB2-06":13.775747877551384,"GB2-07":20.498065640776254,"GB2-08":30.665882353933032},"none":{"GB2-01":36.85535820186162,"GB2-02":40.63871655411837,"GB2-03":54.87449956000706,"GB2-04":47.25181934265058,"GB2-05":11.847085702996953,"GB2-06":56.2512584216998,"GB2-07":62.15194479386521,"GB2-08":31.359631601870227}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-4,"rank_movement_baseline_at":"2026-10-20T11:45:46Z","reasoning":{"highest":33.413792633239595,"medium":27.185860931218944,"none":39.224133049883285},"reasoning_agg":{"highest":{"max":47.72531267025522,"mean":33.413792633239595,"min":17.77900697319065},"medium":{"max":42.695455543709556,"mean":27.185860931218944,"min":10.249032820388127},"none":{"max":62.15194479386521,"mean":39.224133049883285,"min":11.847085702996953}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":12.038272118664342}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:6ecbaafa67ed937a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761484999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"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":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"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":true,"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":true,"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":33.882713732057084,"highest":39.03843790618069,"medium":31.366278766573874,"none":31.243424523416685},"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":"thinkingmachines","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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"],"first_pass_admitted":6,"first_pass_rate":0.6666666666666666,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":21.484328707252462,"score":21.484328707252462},"GB2-02":{"attempts":3,"playable":41.784099928372186,"score":41.784099928372186},"GB2-03":{"attempts":3,"playable":47.445498570801625,"score":47.445498570801625},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":43.96190843910521,"score":36.89549164164793},"GB2-05":{"attempts":3,"playable":19.00948527201577,"score":19.00948527201577},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":29.461332655542787,"score":23.826633670961485},"GB2-07":{"attempts":3,"playable":35.53037285729743,"score":35.53037285729743},"GB2-08":{"attempts":3,"playable":32.38468342606921,"score":32.38468342606921}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":32.931782227689844,"score":32.931782227689844},"GB2-02":{"attempts":1,"playable":42.03561822542847,"score":42.03561822542847},"GB2-03":{"attempts":1,"playable":46.0477291401826,"score":46.0477291401826},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.39850078474362,"score":21.19925039237181},"GB2-05":{"attempts":1,"playable":41.73159909525078,"score":41.73159909525078},"GB2-06":{"attempts":1,"playable":54.57580405914055,"score":54.57580405914055},"GB2-07":{"attempts":1,"playable":18.879467958678035,"score":18.879467958678035},"GB2-08":{"attempts":1,"playable":33.707001758331614,"score":33.707001758331614}},"medium":{"GB2-01":{"attempts":1,"playable":9.186764058697836,"score":9.186764058697836},"GB2-02":{"attempts":1,"playable":41.943466591265654,"score":41.943466591265654},"GB2-03":{"attempts":1,"playable":39.82235897202978,"score":39.82235897202978},"GB2-04":{"attempts":1,"playable":45.2370419502296,"score":45.2370419502296},"GB2-05":{"attempts":1,"playable":9.895830738265554,"score":9.895830738265554},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.25773470922283,"score":8.628867354611415},"GB2-07":{"attempts":1,"playable":55.61179006126211,"score":55.61179006126211},"GB2-08":{"attempts":1,"playable":31.975243051617642,"score":31.975243051617642}},"none":{"GB2-01":{"attempts":1,"playable":22.33443983536971,"score":22.33443983536971},"GB2-02":{"attempts":1,"playable":41.37321496842243,"score":41.37321496842243},"GB2-03":{"attempts":1,"playable":56.46640760019249,"score":56.46640760019249},"GB2-04":{"attempts":1,"playable":44.25018258234239,"score":44.25018258234239},"GB2-05":{"attempts":1,"playable":5.40102598253098,"score":5.40102598253098},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.550459198264974,"score":8.275229599132487},"GB2-07":{"attempts":1,"playable":32.09986055195214,"score":32.09986055195214},"GB2-08":{"attempts":1,"playable":31.471805468258374,"score":31.471805468258374}}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-10-22T10:56:26Z","match_totals_all":{"draws":3473,"losses":6173,"wins":1964},"match_totals_tracks":{"highest":{"draws":1185,"losses":1846,"wins":839},"medium":{"draws":1087,"losses":2182,"wins":599},"none":{"draws":1201,"losses":2145,"wins":526}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":56.46640760019249,"mean":32.29507425930226,"min":5.40102598253098},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":56,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.931782227689844,"GB2-02":42.03561822542847,"GB2-03":46.0477291401826,"GB2-04":42.39850078474362,"GB2-05":41.73159909525078,"GB2-06":54.57580405914055,"GB2-07":18.879467958678035,"GB2-08":33.707001758331614},"per_game_all":{"GB2-01":21.484328707252462,"GB2-02":41.784099928372186,"GB2-03":47.445498570801625,"GB2-04":43.96190843910521,"GB2-05":19.00948527201577,"GB2-06":29.461332655542787,"GB2-07":35.53037285729743,"GB2-08":32.38468342606921},"per_game_match_totals_all":{"GB2-01":{"draws":254,"losses":1041,"wins":171},"GB2-02":{"draws":1103,"losses":264,"wins":3},"GB2-03":{"draws":411,"losses":585,"wins":412},"GB2-04":{"draws":913,"losses":351,"wins":148},"GB2-05":{"draws":0,"losses":1239,"wins":277},"GB2-06":{"draws":18,"losses":1038,"wins":378},"GB2-07":{"draws":0,"losses":990,"wins":494},"GB2-08":{"draws":774,"losses":665,"wins":81}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":135,"losses":266,"wins":87},"GB2-02":{"draws":373,"losses":85,"wins":0},"GB2-03":{"draws":88,"losses":227,"wins":155},"GB2-04":{"draws":297,"losses":129,"wins":46},"GB2-05":{"draws":0,"losses":298,"wins":206},"GB2-06":{"draws":14,"losses":225,"wins":239},"GB2-07":{"draws":0,"losses":410,"wins":82},"GB2-08":{"draws":278,"losses":206,"wins":24}},"medium":{"GB2-01":{"draws":57,"losses":420,"wins":13},"GB2-02":{"draws":368,"losses":87,"wins":1},"GB2-03":{"draws":121,"losses":238,"wins":109},"GB2-04":{"draws":288,"losses":119,"wins":63},"GB2-05":{"draws":0,"losses":459,"wins":47},"GB2-06":{"draws":2,"losses":405,"wins":71},"GB2-07":{"draws":0,"losses":227,"wins":267},"GB2-08":{"draws":251,"losses":227,"wins":28}},"none":{"GB2-01":{"draws":62,"losses":355,"wins":71},"GB2-02":{"draws":362,"losses":92,"wins":2},"GB2-03":{"draws":202,"losses":120,"wins":148},"GB2-04":{"draws":328,"losses":103,"wins":39},"GB2-05":{"draws":0,"losses":482,"wins":24},"GB2-06":{"draws":2,"losses":408,"wins":68},"GB2-07":{"draws":0,"losses":353,"wins":145},"GB2-08":{"draws":245,"losses":232,"wins":29}}},"per_game_raw_elo_all":{"GB2-01":1151.2883847739902,"GB2-02":1411.2611442446603,"GB2-03":1410.6280870422295,"GB2-04":1431.2601605878679,"GB2-05":923.0351000131428,"GB2-06":1109.0137967183914,"GB2-07":1255.8717045723624,"GB2-08":1220.307689403555},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1304.3522507456676,"GB2-02":1413.2181277200207,"GB2-03":1397.6939230781543,"GB2-04":1419.1418843983956,"GB2-05":1336.0648942951098,"GB2-06":1499.2248144298771,"GB2-07":1025.0742162748913,"GB2-08":1234.0502634632344},"medium":{"GB2-01":965.1972635964004,"GB2-02":1412.5018915916216,"GB2-03":1343.507516317972,"GB2-04":1441.133476366214,"GB2-05":791.9936393354548,"GB2-06":920.1665893818175,"GB2-07":1519.7605443117131,"GB2-08":1216.0682943988731},"none":{"GB2-01":1184.3156399799022,"GB2-02":1408.0634134223387,"GB2-03":1490.6828217305615,"GB2-04":1433.5051209989938,"GB2-05":641.0467664088641,"GB2-06":907.6499863434798,"GB2-07":1222.7803531304826,"GB2-08":1210.804510348558}},"per_game_tracks":{"highest":{"GB2-01":32.931782227689844,"GB2-02":42.03561822542847,"GB2-03":46.0477291401826,"GB2-04":42.39850078474362,"GB2-05":41.73159909525078,"GB2-06":54.57580405914055,"GB2-07":18.879467958678035,"GB2-08":33.707001758331614},"medium":{"GB2-01":9.186764058697836,"GB2-02":41.943466591265654,"GB2-03":39.82235897202978,"GB2-04":45.2370419502296,"GB2-05":9.895830738265554,"GB2-06":17.25773470922283,"GB2-07":55.61179006126211,"GB2-08":31.975243051617642},"none":{"GB2-01":22.33443983536971,"GB2-02":41.37321496842243,"GB2-03":56.46640760019249,"GB2-04":44.25018258234239,"GB2-05":5.40102598253098,"GB2-06":16.550459198264974,"GB2-07":32.09986055195214,"GB2-08":31.471805468258374}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:42:18Z","reasoning":{"highest":36.38853160713421,"medium":30.287670347247452,"none":30.209020823525123},"reasoning_agg":{"highest":{"max":54.57580405914055,"mean":36.38853160713421,"min":18.879467958678035},"medium":{"max":55.61179006126211,"mean":30.287670347247452,"min":8.628867354611415},"none":{"max":56.46640760019249,"mean":30.209020823525123,"min":5.40102598253098}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.179510783609089}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:190691b385f34011","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.05850166000000001}},"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":0.05850166},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539},"codegen_latency_ms":{"attempt_count":34,"max_ms":380009,"mean_ms":93239.75,"min_ms":17041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":380009,"mean_ms":168796.875,"min_ms":74942,"run_count":8},"medium":{"attempt_count":10,"max_ms":111336,"mean_ms":66228.375,"min_ms":28934,"run_count":8},"none":{"attempt_count":13,"max_ms":72200,"mean_ms":44694.0,"min_ms":17041,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":16539,"output_mean":6423.083333333333,"output_min":1715,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":16539,"output_mean":12718.0,"output_min":9279,"run_count":8},"medium":{"attempt_count":10,"output_max":6754,"output_mean":3630.75,"output_min":2165,"run_count":8},"none":{"attempt_count":13,"output_max":4210,"output_mean":2920.5,"output_min":1715,"run_count":8}},"display_name":"Muse Glimmer 30B","economics":{"all":35.03803453512848,"highest":41.26066899836071,"medium":31.696992202191463,"none":31.946111879406853},"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":"meta","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":30.108529223339577,"score":30.108529223339577},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.140878152491695,"score":28.760585434994464},"GB2-03":{"attempts":3,"playable":40.10939657923976,"score":40.10939657923976},"GB2-04":{"attempts":3,"playable":46.1039053995922,"score":46.1039053995922},"GB2-05":{"attempts":3,"playable":23.172482388398123,"score":23.172482388398123},"GB2-06":{"attempts":3,"failed_attempts":2,"playable":17.1109139452018,"score":5.703637981733934},"GB2-07":{"attempts":3,"playable":37.75095775887422,"score":37.75095775887422},"GB2-08":{"attempts":3,"playable":32.982935861327,"score":32.982935861327}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":31.496289204929067,"score":31.496289204929067},"GB2-02":{"attempts":1,"playable":42.96080472671972,"score":42.96080472671972},"GB2-03":{"attempts":1,"playable":36.87411609184499,"score":36.87411609184499},"GB2-04":{"attempts":1,"playable":49.52676363647947,"score":49.52676363647947},"GB2-05":{"attempts":1,"playable":46.58698120693764,"score":46.58698120693764},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":48.16894783702535,"score":48.16894783702535},"GB2-08":{"attempts":1,"playable":33.21078028458873,"score":33.21078028458873}},"medium":{"GB2-01":{"attempts":1,"playable":22.349127743802097,"score":22.349127743802097},"GB2-02":{"attempts":1,"playable":43.32095157826366,"score":43.32095157826366},"GB2-03":{"attempts":1,"playable":39.21802044731769,"score":39.21802044731769},"GB2-04":{"attempts":1,"playable":45.5440817336835,"score":45.5440817336835},"GB2-05":{"attempts":1,"playable":15.105360130327302,"score":15.105360130327302},"GB2-06":{"attempts":1,"playable":17.1109139452018,"score":17.1109139452018},"GB2-07":{"attempts":1,"playable":37.79731114274407,"score":37.79731114274407},"GB2-08":{"attempts":1,"playable":33.1301708961916,"score":33.1301708961916}},"none":{"GB2-01":{"attempts":1,"playable":36.480170721287564,"score":36.480170721287564},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":44.2360531985566,"score":44.2360531985566},"GB2-04":{"attempts":1,"playable":43.24087082861362,"score":43.24087082861362},"GB2-05":{"attempts":1,"playable":7.825105827929428,"score":7.825105827929428},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":27.28661429685324,"score":27.28661429685324},"GB2-08":{"attempts":1,"playable":32.60785640320065,"score":32.60785640320065}}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-10-22T10:20:51Z","match_totals_all":{"draws":3165,"losses":5242,"wins":1784},"match_totals_tracks":{"highest":{"draws":1169,"losses":1464,"wins":756},"medium":{"draws":1181,"losses":2133,"wins":560},"none":{"draws":815,"losses":1645,"wins":468}},"model_slug":"meta-muse-glimmer-30b","overall":{"max":49.52676363647947,"mean":30.586553828437406,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":57,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.496289204929067,"GB2-02":42.96080472671972,"GB2-03":36.87411609184499,"GB2-04":49.52676363647947,"GB2-05":46.58698120693764,"GB2-07":48.16894783702535,"GB2-08":33.21078028458873},"per_game_all":{"GB2-01":30.108529223339577,"GB2-03":40.10939657923976,"GB2-04":46.1039053995922,"GB2-05":23.172482388398123,"GB2-07":37.75095775887422,"GB2-08":32.982935861327},"per_game_match_totals_all":{"GB2-01":{"draws":307,"losses":894,"wins":270},"GB2-02":{"draws":750,"losses":156,"wins":6},"GB2-03":{"draws":416,"losses":679,"wins":309},"GB2-04":{"draws":934,"losses":312,"wins":164},"GB2-05":{"draws":0,"losses":1177,"wins":341},"GB2-06":{"draws":2,"losses":406,"wins":70},"GB2-07":{"draws":0,"losses":955,"wins":525},"GB2-08":{"draws":756,"losses":663,"wins":99}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":129,"losses":278,"wins":82},"GB2-02":{"draws":368,"losses":83,"wins":5},"GB2-03":{"draws":149,"losses":235,"wins":84},"GB2-04":{"draws":274,"losses":107,"wins":89},"GB2-05":{"draws":0,"losses":274,"wins":232},"GB2-07":{"draws":0,"losses":267,"wins":229},"GB2-08":{"draws":249,"losses":220,"wins":35}},"medium":{"GB2-01":{"draws":89,"losses":344,"wins":61},"GB2-02":{"draws":382,"losses":73,"wins":1},"GB2-03":{"draws":118,"losses":241,"wins":109},"GB2-04":{"draws":325,"losses":100,"wins":45},"GB2-05":{"draws":0,"losses":433,"wins":73},"GB2-06":{"draws":2,"losses":406,"wins":70},"GB2-07":{"draws":0,"losses":318,"wins":174},"GB2-08":{"draws":265,"losses":218,"wins":27}},"none":{"GB2-01":{"draws":89,"losses":272,"wins":127},"GB2-03":{"draws":149,"losses":203,"wins":116},"GB2-04":{"draws":335,"losses":105,"wins":30},"GB2-05":{"draws":0,"losses":470,"wins":36},"GB2-07":{"draws":0,"losses":370,"wins":122},"GB2-08":{"draws":242,"losses":225,"wins":37}}},"per_game_raw_elo_all":{"GB2-01":1271.4262942767434,"GB2-03":1345.8862955661423,"GB2-04":1447.8143757833768,"GB2-05":1014.6005709055784,"GB2-07":1293.0531241045771,"GB2-08":1226.550648105496},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1289.3261963631771,"GB2-02":1420.395134010576,"GB2-03":1317.5037909982154,"GB2-04":1474.252666037493,"GB2-05":1397.277584830111,"GB2-07":1425.9407613714784,"GB2-08":1228.9148647088653},"medium":{"GB2-01":1184.501418140811,"GB2-02":1423.1828346523823,"GB2-03":1338.2085574916623,"GB2-04":1443.5044771113642,"GB2-05":915.8617527643884,"GB2-06":917.5880948989326,"GB2-07":1296.570710435931,"GB2-08":1228.0794609139834},"none":{"GB2-01":1340.4512683262424,"GB2-03":1381.946538208549,"GB2-04":1425.6859842012732,"GB2-05":730.6623751222355,"GB2-07":1156.6479005063225,"GB2-08":1222.6576186936395}},"per_game_tracks":{"highest":{"GB2-01":31.496289204929067,"GB2-02":42.96080472671972,"GB2-03":36.87411609184499,"GB2-04":49.52676363647947,"GB2-05":46.58698120693764,"GB2-07":48.16894783702535,"GB2-08":33.21078028458873},"medium":{"GB2-01":22.349127743802097,"GB2-02":43.32095157826366,"GB2-03":39.21802044731769,"GB2-04":45.5440817336835,"GB2-05":15.105360130327302,"GB2-06":17.1109139452018,"GB2-07":37.79731114274407,"GB2-08":33.1301708961916},"none":{"GB2-01":36.480170721287564,"GB2-03":44.2360531985566,"GB2-04":43.24087082861362,"GB2-05":7.825105827929428,"GB2-07":27.28661429685324,"GB2-08":32.60785640320065}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:17:08Z","reasoning":{"highest":36.10308537356562,"medium":31.696992202191463,"none":23.95958390955514},"reasoning_agg":{"highest":{"max":49.52676363647947,"mean":36.10308537356562,"min":0.0},"medium":{"max":45.5440817336835,"mean":31.696992202191463,"min":15.105360130327302},"none":{"max":44.2360531985566,"mean":23.95958390955514,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.14350146401048}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:2f879edb92e42f6f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"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":0.009855890999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855890999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.05953976200000001}},"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":0.07848132599999999},"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":34.54736929212315,"highest":40.03454073251237,"medium":31.249231280671864,"none":32.52854686669692},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":38.518554336947076,"score":25.679036224631385},"GB2-02":{"attempts":3,"playable":43.295516288724116,"score":43.295516288724116},"GB2-03":{"attempts":3,"playable":39.17098613473041,"score":39.17098613473041},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":40.57324048108904,"score":27.04882698739269},"GB2-05":{"attempts":3,"playable":29.637330045949934,"score":29.637330045949934},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":24.50639377761182,"score":16.337595851741213},"GB2-07":{"attempts":3,"playable":28.141685923910135,"score":28.141685923910135},"GB2-08":{"attempts":3,"playable":32.49132806730114,"score":32.49132806730114}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.98715218426001,"score":43.98715218426001},"GB2-03":{"attempts":1,"playable":45.85314717149013,"score":45.85314717149013},"GB2-04":{"attempts":1,"playable":42.468974401998935,"score":42.468974401998935},"GB2-05":{"attempts":1,"playable":57.99267569312063,"score":57.99267569312063},"GB2-06":{"attempts":1,"playable":21.998205557059805,"score":21.998205557059805},"GB2-07":{"attempts":1,"playable":34.297944527282844,"score":34.297944527282844},"GB2-08":{"attempts":1,"playable":33.64368559237425,"score":33.64368559237425}},"medium":{"GB2-01":{"attempts":1,"playable":36.010795071147186,"score":36.010795071147186},"GB2-02":{"attempts":1,"playable":42.52786348873232,"score":42.52786348873232},"GB2-03":{"attempts":1,"playable":35.451056149995566,"score":35.451056149995566},"GB2-04":{"attempts":1,"playable":38.67750656017914,"score":38.67750656017914},"GB2-05":{"attempts":1,"playable":15.317225907395295,"score":15.317225907395295},"GB2-06":{"attempts":1,"playable":27.014581998163834,"score":27.014581998163834},"GB2-07":{"attempts":1,"playable":21.227860632402066,"score":21.227860632402066},"GB2-08":{"attempts":1,"playable":33.76696043735952,"score":33.76696043735952}},"none":{"GB2-01":{"attempts":1,"playable":41.026313602746974,"score":41.026313602746974},"GB2-02":{"attempts":1,"playable":43.37153319318001,"score":43.37153319318001},"GB2-03":{"attempts":1,"playable":36.208755082705544,"score":36.208755082705544},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":15.60208853733387,"score":15.60208853733387},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":28.899252612045505,"score":28.899252612045505},"GB2-08":{"attempts":1,"playable":30.06333817216965,"score":30.06333817216965}}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-10-22T10:35:23Z","match_totals_all":{"draws":2885,"losses":5411,"wins":1862},"match_totals_tracks":{"highest":{"draws":912,"losses":1632,"wins":832},"medium":{"draws":1157,"losses":2157,"wins":550},"none":{"draws":816,"losses":1622,"wins":480}},"model_slug":"openai-gpt-oss-120b","overall":{"max":57.99267569312063,"mean":30.225288190547626,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":58,"overall_ranking_status":"ranked","per_game":{"GB2-02":43.98715218426001,"GB2-03":45.85314717149013,"GB2-04":42.468974401998935,"GB2-05":57.99267569312063,"GB2-06":21.998205557059805,"GB2-07":34.297944527282844,"GB2-08":33.64368559237425},"per_game_all":{"GB2-02":43.295516288724116,"GB2-03":39.17098613473041,"GB2-05":29.637330045949934,"GB2-07":28.141685923910135,"GB2-08":32.49132806730114},"per_game_match_totals_all":{"GB2-01":{"draws":169,"losses":532,"wins":275},"GB2-02":{"draws":1112,"losses":241,"wins":17},"GB2-03":{"draws":350,"losses":724,"wins":332},"GB2-04":{"draws":622,"losses":259,"wins":59},"GB2-05":{"draws":0,"losses":1079,"wins":437},"GB2-06":{"draws":11,"losses":743,"wins":202},"GB2-07":{"draws":0,"losses":1096,"wins":384},"GB2-08":{"draws":621,"losses":737,"wins":156}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":366,"losses":80,"wins":12},"GB2-03":{"draws":117,"losses":209,"wins":142},"GB2-04":{"draws":308,"losses":122,"wins":40},"GB2-05":{"draws":0,"losses":217,"wins":287},"GB2-06":{"draws":3,"losses":384,"wins":91},"GB2-07":{"draws":0,"losses":334,"wins":158},"GB2-08":{"draws":118,"losses":286,"wins":102}},"medium":{"GB2-01":{"draws":90,"losses":275,"wins":123},"GB2-02":{"draws":367,"losses":85,"wins":4},"GB2-03":{"draws":119,"losses":257,"wins":92},"GB2-04":{"draws":314,"losses":137,"wins":19},"GB2-05":{"draws":0,"losses":430,"wins":74},"GB2-06":{"draws":8,"losses":359,"wins":111},"GB2-07":{"draws":0,"losses":402,"wins":94},"GB2-08":{"draws":259,"losses":212,"wins":33}},"none":{"GB2-01":{"draws":79,"losses":257,"wins":152},"GB2-02":{"draws":379,"losses":76,"wins":1},"GB2-03":{"draws":114,"losses":258,"wins":98},"GB2-05":{"draws":0,"losses":432,"wins":76},"GB2-07":{"draws":0,"losses":360,"wins":132},"GB2-08":{"draws":244,"losses":239,"wins":21}}},"per_game_raw_elo_all":{"GB2-02":1422.9819431810813,"GB2-03":1337.4503922735648,"GB2-05":1129.2089729035904,"GB2-07":1165.2376310585719,"GB2-08":1221.3440730746122},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1428.332061374252,"GB2-03":1396.0009757182136,"GB2-04":1419.6901174683958,"GB2-05":1541.0522549072273,"GB2-06":999.1997616002567,"GB2-07":1251.6841733111405,"GB2-08":1233.3956652011034},"medium":{"GB2-01":1335.7493808162249,"GB2-02":1417.0396502227234,"GB2-03":1304.7790496517155,"GB2-04":1389.925770244573,"GB2-05":920.3179659296449,"GB2-06":1077.490231693792,"GB2-07":1064.70376976354,"GB2-08":1234.6699813205714},"none":{"GB2-01":1385.130600558821,"GB2-02":1423.5741179462686,"GB2-03":1311.571151450766,"GB2-05":926.2566978738988,"GB2-07":1179.324950101035,"GB2-08":1195.9665727021616}},"per_game_tracks":{"highest":{"GB2-02":43.98715218426001,"GB2-03":45.85314717149013,"GB2-04":42.468974401998935,"GB2-05":57.99267569312063,"GB2-06":21.998205557059805,"GB2-07":34.297944527282844,"GB2-08":33.64368559237425},"medium":{"GB2-01":36.010795071147186,"GB2-02":42.52786348873232,"GB2-03":35.451056149995566,"GB2-04":38.67750656017914,"GB2-05":15.317225907395295,"GB2-06":27.014581998163834,"GB2-07":21.227860632402066,"GB2-08":33.76696043735952},"none":{"GB2-01":41.026313602746974,"GB2-02":43.37153319318001,"GB2-03":36.208755082705544,"GB2-05":15.60208853733387,"GB2-07":28.899252612045505,"GB2-08":30.06333817216965}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:17:40Z","reasoning":{"highest":35.03022314094832,"medium":31.249231280671864,"none":24.39641015002269},"reasoning_agg":{"highest":{"max":57.99267569312063,"mean":35.03022314094832,"min":0.0},"medium":{"max":42.52786348873232,"mean":31.249231280671864,"min":15.317225907395295},"none":{"max":43.37153319318001,"mean":24.39641015002269,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.633812990925634}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:0fa7262b1701e6da","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":5,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.50472065},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005}},"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":2,"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":5,"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":9,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.2116408500000002},"codegen_latency_ms":{"attempt_count":56,"max_ms":622714,"mean_ms":85345.36,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":35,"max_ms":622714,"mean_ms":94544.1875,"min_ms":23604,"run_count":16},"medium":{"attempt_count":21,"max_ms":124322,"mean_ms":68991.88888888889,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":56,"output_max":17712,"output_mean":7782.6,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":35,"output_max":17712,"output_mean":7793.4375,"output_min":2728,"run_count":16},"medium":{"attempt_count":21,"output_max":13873,"output_mean":7763.333333333333,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":38.44170031842211,"highest":34.32599276133404,"medium":39.31911833565414,"none":35.3716785886969},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":["GB2-03","GB2-04"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"infra_failures_excluded":2},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":2,"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":5,"repaired_rate":0.7142857142857143},"baseline":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":1}},"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":14,"failed_game_aliases":["GB2-01","GB2-03","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.14285714285714285,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":2},"GB2-03":{"model_code_failures":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"model_code_failures":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.35714285714285715,"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":7,"repaired_rate":0.5}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":45.7170065189998,"score":41.42725391968638},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.94117274810037,"score":27.294115165400246},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":31.512041976438525,"score":10.504013992146175},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.7326907952977,"score":27.8217938635318},"GB2-05":{"attempts":3,"playable":46.173964036799845,"score":46.173964036799845},"GB2-06":{"attempts":3,"playable":35.83713834322841,"score":35.83713834322841},"GB2-07":{"attempts":5,"failed_attempts":3,"playable":7.4851491822599465,"score":4.199720763311013},"GB2-08":{"attempts":4,"playable":33.7709560930381,"score":33.7709560930381}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":25.73851559588054,"score":12.86925779794027},"GB2-02":{"attempts":2,"playable":40.90958704236034,"score":40.90958704236034},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":1,"playable":41.00342528027053,"score":41.00342528027053},"GB2-05":{"attempts":2,"playable":30.29074551209937,"score":30.29074551209937},"GB2-06":{"attempts":1,"playable":34.07145696679683,"score":34.07145696679683},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":33.94222617059661,"score":33.94222617059661}},"medium":{"GB2-01":{"attempts":1,"playable":56.37149617351933,"score":56.37149617351933},"GB2-02":{"attempts":1,"playable":40.97275845384039,"score":40.97275845384039},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":57.44456342635759,"score":57.44456342635759},"GB2-07":{"attempts":1,"playable":10.228026215346182,"score":10.228026215346182},"GB2-08":{"attempts":1,"playable":31.578747409207203,"score":31.578747409207203}},"none":{"GB2-01":{"attempts":1,"playable":55.04100778759954,"score":55.04100778759954},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.512041976438525,"score":31.512041976438525},"GB2-04":{"attempts":1,"playable":42.461956310324865,"score":42.461956310324865},"GB2-05":{"attempts":1,"playable":62.057182561500326,"score":62.057182561500326},"GB2-06":{"attempts":1,"playable":15.995394636530808,"score":15.995394636530808},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":4.742272149173711,"score":2.3711360745868557},"GB2-08":{"attempts":1,"playable":35.791894699310504,"score":35.791894699310504}}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-10-22T09:37:09Z","match_totals_all":{"draws":3214,"losses":5116,"wins":1890},"match_totals_tracks":{"highest":{"draws":1670,"losses":2098,"wins":600},"medium":{"draws":702,"losses":1178,"wins":554},"none":{"draws":842,"losses":1840,"wins":736}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":62.057182561500326,"mean":27.624916209170554,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":59,"overall_ranking_status":"partial","per_game":{"GB2-01":25.73851559588054,"GB2-02":40.90958704236034,"GB2-04":41.00342528027053,"GB2-05":30.29074551209937,"GB2-06":34.07145696679683,"GB2-08":33.94222617059661},"per_game_all":{"GB2-01":45.7170065189998,"GB2-06":35.83713834322841,"GB2-08":33.7709560930381},"per_game_match_totals_all":{"GB2-01":{"draws":267,"losses":682,"wins":515},"GB2-02":{"draws":1063,"losses":293,"wins":12},"GB2-03":{"draws":180,"losses":243,"wins":45},"GB2-04":{"draws":662,"losses":230,"wins":50},"GB2-05":{"draws":0,"losses":913,"wins":603},"GB2-06":{"draws":42,"losses":939,"wins":453},"GB2-07":{"draws":0,"losses":938,"wins":62},"GB2-08":{"draws":1000,"losses":878,"wins":150}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":99,"losses":320,"wins":69},"GB2-02":{"draws":703,"losses":198,"wins":11},"GB2-04":{"draws":335,"losses":115,"wins":20},"GB2-05":{"draws":0,"losses":714,"wins":296},"GB2-06":{"draws":27,"losses":318,"wins":133},"GB2-08":{"draws":506,"losses":433,"wins":71}},"medium":{"GB2-01":{"draws":97,"losses":172,"wins":219},"GB2-02":{"draws":360,"losses":95,"wins":1},"GB2-06":{"draws":10,"losses":212,"wins":256},"GB2-07":{"draws":0,"losses":461,"wins":43},"GB2-08":{"draws":235,"losses":238,"wins":35}},"none":{"GB2-01":{"draws":71,"losses":190,"wins":227},"GB2-03":{"draws":180,"losses":243,"wins":45},"GB2-04":{"draws":327,"losses":115,"wins":30},"GB2-05":{"draws":0,"losses":199,"wins":307},"GB2-06":{"draws":5,"losses":409,"wins":64},"GB2-07":{"draws":0,"losses":477,"wins":19},"GB2-08":{"draws":259,"losses":207,"wins":44}}},"per_game_raw_elo_all":{"GB2-01":1425.7289814138994,"GB2-06":1209.1833423133546,"GB2-08":1234.642080173425},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1225.6072490080685,"GB2-02":1404.4185096840918,"GB2-04":1408.2558762645335,"GB2-05":1171.2456565606553,"GB2-06":1184.3830798966387,"GB2-08":1236.4788808279723},"medium":{"GB2-01":1532.2514838418726,"GB2-02":1404.9395637285616,"GB2-06":1545.5189493541693,"GB2-07":841.9931759055481,"GB2-08":1211.924250103736},"none":{"GB2-01":1519.3282113917573,"GB2-03":1268.675993644367,"GB2-04":1419.635528368134,"GB2-05":1595.6707729367158,"GB2-06":897.647997689256,"GB2-07":650.4435648546603,"GB2-08":1255.523109588567}},"per_game_tracks":{"highest":{"GB2-01":25.73851559588054,"GB2-02":40.90958704236034,"GB2-04":41.00342528027053,"GB2-05":30.29074551209937,"GB2-06":34.07145696679683,"GB2-08":33.94222617059661},"medium":{"GB2-01":56.37149617351933,"GB2-02":40.97275845384039,"GB2-06":57.44456342635759,"GB2-07":10.228026215346182,"GB2-08":31.578747409207203},"none":{"GB2-01":55.04100778759954,"GB2-03":31.512041976438525,"GB2-04":42.461956310324865,"GB2-05":62.057182561500326,"GB2-06":15.995394636530808,"GB2-07":4.742272149173711,"GB2-08":35.791894699310504}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.135837346257993,"medium":28.085084525467245,"none":30.653826755786422},"reasoning_agg":{"highest":{"max":41.00342528027053,"mean":24.135837346257993,"min":0.0},"medium":{"max":57.44456342635759,"mean":28.085084525467245,"min":0.0},"none":{"max":62.057182561500326,"mean":30.653826755786422,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.517989409528429}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:18b88d4d37d49f67","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":60},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.261503015,"mean":0.224623670625,"median":0.22750746833333335,"min":0.17735088333333335,"recorded_attempt_count":60,"run_count":22,"total":4.90638056},"medium":{"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":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164},"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":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164000000002},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":60},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.261503015,"mean":0.224623670625,"median":0.22750746833333335,"min":0.17735088333333335,"recorded_attempt_count":60,"run_count":22,"total":4.90638056}},"codegen_cost_usd":{"admitted_cell_count":32,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.261503015,"mean":0.09751241583333332,"median":0.042993304999999996,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":112,"run_count":46,"total":5.7439161499999996},"codegen_latency_ms":{"attempt_count":112,"max_ms":712912,"mean_ms":234938.63043478262,"min_ms":16322,"run_count":46},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":60,"max_ms":712912,"mean_ms":442344.0909090909,"min_ms":125659,"run_count":22},"medium":{"attempt_count":13,"max_ms":52676,"mean_ms":32623.625,"min_ms":16322,"run_count":8},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":112,"output_max":80000,"output_mean":26608.978260869564,"output_min":1372,"run_count":46},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":60,"output_max":80000,"output_mean":50498.318181818184,"output_min":12059,"run_count":22},"medium":{"attempt_count":13,"output_max":9117,"output_mean":4863.875,"output_min":2632,"run_count":8},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":31.82968179896862,"highest":39.44951434198323,"medium":25.53878302295008,"none":38.12560552822659},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":20,"effective_max_output_tokens":[262144],"finish_reason_observations":112,"finish_reasons":["length","stop"],"indexed_attempts":112,"output_token_observations":112,"provider_post_attempt_observations":20,"provider_post_attempts":23,"reasoning_token_observations":85,"reconciliation_get_attempt_observations":20,"reconciliation_get_attempts":33,"requested_max_output_token_observations":20,"requested_max_output_tokens":[262144],"total_output_tokens":1224013,"total_reasoning_output_tokens":793927,"total_visible_output_tokens":126602,"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":"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":"thinkingmachines","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"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},"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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":1,"model_code_failures":1}},"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":14,"evaluated_cells":16,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"admitted":2,"infra_failures_excluded":1},"GB2-02":{"admitted":2,"infra_failures_excluded":1},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":2,"infra_failures_excluded":1},"GB2-08":{"admitted":2,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-07","GB2-08"],"infra_failures_excluded":6,"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":5,"repaired_rate":0.3125}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":25.810405222944137,"score":25.810405222944137},"GB2-02":{"attempts":5,"failed_attempts":2,"playable":43.05230405818659,"score":21.376984529105272},"GB2-03":{"attempts":5,"playable":44.520265043135446,"score":44.520265043135446},"GB2-04":{"attempts":5,"failed_attempts":1,"playable":42.17699952321043,"score":34.83596162224667},"GB2-05":{"attempts":5,"playable":19.360909293959736,"score":19.360909293959736},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":35.24109131258391,"score":21.6326349903717},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":23.868420397978028,"score":19.91260495044948},"GB2-08":{"attempts":5,"failed_attempts":2,"playable":57.39738830078541,"score":26.179456703163243}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":39.89999200799664,"score":39.89999200799664},"GB2-02":{"attempts":2,"playable":42.15729905825845,"score":42.15729905825845},"GB2-03":{"attempts":2,"playable":47.98531733416969,"score":47.98531733416969},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.04622740578256,"score":22.02311370289128},"GB2-05":{"attempts":2,"playable":16.242409847765835,"score":16.242409847765835},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":54.00582859161591,"score":27.002914295807955},"GB2-07":{"attempts":2,"playable":28.977076872868132,"score":28.977076872868132},"GB2-08":{"attempts":2,"playable":42.281963617408636,"score":42.281963617408636}},"medium":{"GB2-01":{"attempts":1,"playable":17.606292175427395,"score":17.606292175427395},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.812816488634326,"score":36.812816488634326},"GB2-04":{"attempts":1,"playable":41.733142959644496,"score":41.733142959644496},"GB2-05":{"attempts":1,"playable":14.11461887362114,"score":14.11461887362114},"GB2-06":{"attempts":1,"playable":24.072536004478458,"score":24.072536004478458},"GB2-07":{"attempts":1,"playable":18.893291635894656,"score":18.893291635894656},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":2,"playable":19.924931485408386,"score":19.924931485408386},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.94730905811474,"score":21.97365452905737},"GB2-03":{"attempts":2,"playable":48.76266130660231,"score":48.76266130660231},"GB2-04":{"attempts":2,"playable":40.75162820420424,"score":40.75162820420424},"GB2-05":{"attempts":2,"playable":27.725699160492237,"score":27.725699160492237},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":27.644909341657364,"score":13.822454670828682},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":23.7348926851713,"score":11.86744634258565},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":72.51281298416218,"score":36.25640649208109}}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-10-22T10:42:34Z","match_totals_all":{"draws":4051,"losses":8307,"wins":3131},"match_totals_tracks":{"highest":{"draws":1860,"losses":3409,"wins":1513},"medium":{"draws":654,"losses":1893,"wins":355},"none":{"draws":1537,"losses":3005,"wins":1263}},"model_slug":"thinkingmachines-inkling","overall":{"max":48.76266130660231,"mean":26.70365279442196,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":60,"overall_ranking_status":"ranked","per_game":{"GB2-01":39.89999200799664,"GB2-02":42.15729905825845,"GB2-03":47.98531733416969,"GB2-04":44.04622740578256,"GB2-05":16.242409847765835,"GB2-06":54.00582859161591,"GB2-07":28.977076872868132,"GB2-08":42.281963617408636},"per_game_all":{"GB2-01":25.810405222944137,"GB2-03":44.520265043135446,"GB2-04":42.17699952321043,"GB2-05":19.360909293959736,"GB2-06":35.24109131258391,"GB2-07":23.868420397978028},"per_game_match_totals_all":{"GB2-01":{"draws":595,"losses":1508,"wins":341},"GB2-02":{"draws":1104,"losses":247,"wins":15},"GB2-03":{"draws":741,"losses":973,"wins":628},"GB2-04":{"draws":1202,"losses":519,"wins":163},"GB2-05":{"draws":0,"losses":2030,"wins":500},"GB2-06":{"draws":29,"losses":954,"wins":450},"GB2-07":{"draws":0,"losses":1514,"wins":456},"GB2-08":{"draws":380,"losses":562,"wins":578}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":266,"losses":471,"wins":239},"GB2-02":{"draws":724,"losses":176,"wins":10},"GB2-03":{"draws":198,"losses":421,"wins":317},"GB2-04":{"draws":301,"losses":120,"wins":51},"GB2-05":{"draws":0,"losses":855,"wins":159},"GB2-06":{"draws":12,"losses":226,"wins":240},"GB2-07":{"draws":0,"losses":720,"wins":266},"GB2-08":{"draws":359,"losses":420,"wins":231}},"medium":{"GB2-01":{"draws":55,"losses":382,"wins":55},"GB2-03":{"draws":286,"losses":168,"wins":14},"GB2-04":{"draws":310,"losses":126,"wins":34},"GB2-05":{"draws":0,"losses":436,"wins":68},"GB2-06":{"draws":3,"losses":373,"wins":100},"GB2-07":{"draws":0,"losses":408,"wins":84}},"none":{"GB2-01":{"draws":274,"losses":655,"wins":47},"GB2-02":{"draws":380,"losses":71,"wins":5},"GB2-03":{"draws":257,"losses":384,"wins":297},"GB2-04":{"draws":591,"losses":273,"wins":78},"GB2-05":{"draws":0,"losses":739,"wins":273},"GB2-06":{"draws":14,"losses":355,"wins":110},"GB2-07":{"draws":0,"losses":386,"wins":106},"GB2-08":{"draws":21,"losses":142,"wins":347}}},"per_game_raw_elo_all":{"GB2-01":1213.973299601703,"GB2-03":1385.4541967192197,"GB2-04":1417.3639567115076,"GB2-05":990.4917145329413,"GB2-06":1203.0887894350947,"GB2-07":1103.3238684042642},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1370.8449287113272,"GB2-02":1414.1634669366035,"GB2-03":1414.5950930765653,"GB2-04":1431.9267004270282,"GB2-05":939.3657767267725,"GB2-06":1490.1360488330274,"GB2-07":1180.3868226045927,"GB2-08":1329.4617887360935},"medium":{"GB2-01":1119.9796181736215,"GB2-03":1316.9583771116781,"GB2-04":1413.9583218094774,"GB2-05":894.5472254844507,"GB2-06":1032.0030236363154,"GB2-07":1025.3160564345958},"none":{"GB2-01":1151.0953519201603,"GB2-02":1428.0243489689835,"GB2-03":1424.8091199694154,"GB2-04":1406.2068478980173,"GB2-05":1137.5621413876006,"GB2-06":1087.127295835941,"GB2-07":1104.2687261736035,"GB2-08":1726.070920534729}},"per_game_tracks":{"highest":{"GB2-01":39.89999200799664,"GB2-02":42.15729905825845,"GB2-03":47.98531733416969,"GB2-04":44.04622740578256,"GB2-05":16.242409847765835,"GB2-06":54.00582859161591,"GB2-07":28.977076872868132,"GB2-08":42.281963617408636},"medium":{"GB2-01":17.606292175427395,"GB2-03":36.812816488634326,"GB2-04":41.733142959644496,"GB2-05":14.11461887362114,"GB2-06":24.072536004478458,"GB2-07":18.893291635894656},"none":{"GB2-01":19.924931485408386,"GB2-02":43.94730905811474,"GB2-03":48.76266130660231,"GB2-04":40.75162820420424,"GB2-05":27.725699160492237,"GB2-06":27.644909341657364,"GB2-07":23.7348926851713,"GB2-08":72.51281298416218}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:13:27Z","reasoning":{"highest":33.32126084214583,"medium":19.15408726721256,"none":27.635610273907492},"reasoning_agg":{"highest":{"max":47.98531733416969,"mean":33.32126084214583,"min":16.242409847765835},"medium":{"max":41.733142959644496,"mean":19.15408726721256,"min":0.0},"none":{"max":48.76266130660231,"mean":27.635610273907492,"min":11.86744634258565}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":14.167173574933273}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:150ac88b4f9078a9","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":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0442025,"mean":0.017142385,"median":0.01322286,"min":0.01037917,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.13713908},"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":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.11342239999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.0442025,"mean":0.017142385,"median":0.01322286,"min":0.01037917,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.13713908000000002},"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":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.11342239999999998},"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":17,"cell_count":24,"cost_basis_counts":{"provider_reported":46},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.11219570000000001,"mean":0.030692482499999996,"median":0.01928415,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":46,"run_count":24,"total":0.73661958},"codegen_latency_ms":{"attempt_count":46,"max_ms":511905,"mean_ms":147013.95833333334,"min_ms":23584,"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":13,"max_ms":348782,"mean_ms":92838.875,"min_ms":39705,"run_count":8},"none":{"attempt_count":13,"max_ms":194018,"mean_ms":63357.25,"min_ms":23584,"run_count":8}},"codegen_output_tokens":{"attempt_count":46,"output_max":93362,"output_mean":24067.583333333332,"output_min":4359,"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":13,"output_max":33638,"output_mean":12726.0,"output_min":7627,"run_count":8},"none":{"attempt_count":13,"output_max":17245,"output_mean":10160.0,"output_min":4359,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":31.86327376587251,"highest":24.73047220992625,"medium":35.18204653801823,"none":40.88628321843269},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[230400],"finish_reason_observations":46,"finish_reasons":["stop"],"indexed_attempts":46,"output_token_observations":46,"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":[230400],"total_output_tokens":577622,"total_visible_output_tokens":183088,"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":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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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","GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-05","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"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":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":17.747461025214818,"score":17.747461025214818},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":43.95274525081541,"score":14.650915083605137},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":36.045910505730745,"score":24.030607003820496},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":39.7186759621747,"score":13.239558654058234},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":44.76872779268852,"score":29.845818528459017},"GB2-06":{"attempts":3,"playable":42.5754707422667,"score":42.5754707422667},"GB2-07":{"attempts":3,"playable":35.26688953013602,"score":35.26688953013602},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":23.99608894282776,"score":15.997392628551841}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":9.725333877010327,"score":9.725333877010327},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":38.6730291604042,"score":38.6730291604042},"GB2-06":{"attempts":1,"playable":33.25905645600859,"score":33.25905645600859},"GB2-07":{"attempts":1,"playable":24.435774216165505,"score":24.435774216165505},"GB2-08":{"attempts":1,"playable":17.55916734004265,"score":17.55916734004265}},"medium":{"GB2-01":{"attempts":1,"playable":10.411011880202157,"score":10.411011880202157},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":34.48060894376731,"score":34.48060894376731},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":50.86442642497284,"score":50.86442642497284},"GB2-06":{"attempts":1,"playable":45.31865289339318,"score":45.31865289339318},"GB2-07":{"attempts":1,"playable":39.58456854016102,"score":39.58456854016102},"GB2-08":{"attempts":1,"playable":30.43301054561287,"score":30.43301054561287}},"none":{"GB2-01":{"attempts":1,"playable":33.10603731843197,"score":33.10603731843197},"GB2-02":{"attempts":1,"playable":43.95274525081541,"score":43.95274525081541},"GB2-03":{"attempts":1,"playable":37.611212067694176,"score":37.611212067694176},"GB2-04":{"attempts":1,"playable":39.7186759621747,"score":39.7186759621747},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":49.148702877398335,"score":49.148702877398335},"GB2-07":{"attempts":1,"playable":41.78032583408154,"score":41.78032583408154},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T09:45:32Z","match_totals_all":{"draws":1570,"losses":4840,"wins":1874},"match_totals_tracks":{"highest":{"draws":153,"losses":1828,"wins":497},"medium":{"draws":482,"losses":1725,"wins":737},"none":{"draws":935,"losses":1287,"wins":640}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":50.86442642497284,"mean":24.16926414951403,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":61,"overall_ranking_status":"ranked","per_game":{"GB2-01":9.725333877010327,"GB2-05":38.6730291604042,"GB2-06":33.25905645600859,"GB2-07":24.435774216165505,"GB2-08":17.55916734004265},"per_game_all":{"GB2-01":17.747461025214818,"GB2-06":42.5754707422667,"GB2-07":35.26688953013602},"per_game_match_totals_all":{"GB2-01":{"draws":183,"losses":1136,"wins":155},"GB2-02":{"draws":366,"losses":78,"wins":10},"GB2-03":{"draws":275,"losses":490,"wins":171},"GB2-04":{"draws":306,"losses":135,"wins":29},"GB2-05":{"draws":0,"losses":569,"wins":443},"GB2-06":{"draws":52,"losses":841,"wins":537},"GB2-07":{"draws":0,"losses":1002,"wins":492},"GB2-08":{"draws":388,"losses":589,"wins":37}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":25,"losses":432,"wins":31},"GB2-05":{"draws":0,"losses":316,"wins":192},"GB2-06":{"draws":10,"losses":330,"wins":138},"GB2-07":{"draws":0,"losses":387,"wins":111},"GB2-08":{"draws":118,"losses":363,"wins":25}},"medium":{"GB2-01":{"draws":66,"losses":410,"wins":14},"GB2-03":{"draws":134,"losses":253,"wins":81},"GB2-05":{"draws":0,"losses":253,"wins":251},"GB2-06":{"draws":12,"losses":269,"wins":195},"GB2-07":{"draws":0,"losses":314,"wins":184},"GB2-08":{"draws":270,"losses":226,"wins":12}},"none":{"GB2-01":{"draws":92,"losses":294,"wins":110},"GB2-02":{"draws":366,"losses":78,"wins":10},"GB2-03":{"draws":141,"losses":237,"wins":90},"GB2-04":{"draws":306,"losses":135,"wins":29},"GB2-06":{"draws":30,"losses":242,"wins":204},"GB2-07":{"draws":0,"losses":301,"wins":197}}},"per_game_raw_elo_all":{"GB2-01":1092.3836063450071,"GB2-06":1313.6179734710597,"GB2-07":1260.199384833848},"per_game_raw_elo_tracks":{"highest":{"GB2-01":977.8407848187859,"GB2-05":1296.408986637452,"GB2-06":1172.1364824537154,"GB2-07":1114.910683704113,"GB2-08":1048.2911313768766},"medium":{"GB2-01":993.1521596643628,"GB2-03":1296.016928184212,"GB2-05":1450.522453535539,"GB2-06":1354.8493686485563,"GB2-07":1319.1126431019388,"GB2-08":1199.8784529964478},"none":{"GB2-01":1306.1578745518727,"GB2-02":1428.0663349252402,"GB2-03":1324.0449911348298,"GB2-04":1398.1633454613514,"GB2-06":1413.8680693109072,"GB2-07":1346.5748276954919}},"per_game_tracks":{"highest":{"GB2-01":9.725333877010327,"GB2-05":38.6730291604042,"GB2-06":33.25905645600859,"GB2-07":24.435774216165505,"GB2-08":17.55916734004265},"medium":{"GB2-01":10.411011880202157,"GB2-03":34.48060894376731,"GB2-05":50.86442642497284,"GB2-06":45.31865289339318,"GB2-07":39.58456854016102,"GB2-08":30.43301054561287},"none":{"GB2-01":33.10603731843197,"GB2-02":43.95274525081541,"GB2-03":37.611212067694176,"GB2-04":39.7186759621747,"GB2-06":49.148702877398335,"GB2-07":41.78032583408154}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:06:29Z","reasoning":{"highest":15.456545131203907,"medium":26.386534903513667,"none":30.664712413824518},"reasoning_agg":{"highest":{"max":38.6730291604042,"mean":15.456545131203907,"min":0.0},"medium":{"max":50.86442642497284,"mean":26.386534903513667,"min":0.0},"none":{"max":49.148702877398335,"mean":30.664712413824518,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":15.208167282620611}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:449789a3e6a0c569","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.007612510000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"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":0.028312969999999993},"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":34.21623452486893,"highest":28.202348752569183,"medium":27.34293360665821,"none":38.88599293828971},"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":"inception","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":27.796050012590833,"score":9.265350004196945},"GB2-02":{"attempts":3,"playable":42.56983950607546,"score":42.56983950607546},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":46.03905847000343,"score":15.346352823334477},"GB2-04":{"attempts":3,"playable":41.132442183306274,"score":41.132442183306274},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":28.329481665738104,"score":18.88632111049207},"GB2-06":{"attempts":3,"playable":18.946421885225053,"score":18.946421885225053},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":12.532687078248841,"score":8.355124718832561},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.098051076212194,"score":21.398700717474796}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.796050012590833,"score":27.796050012590833},"GB2-02":{"attempts":1,"playable":42.16651957593997,"score":42.16651957593997},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.08483647804285,"score":39.08483647804285},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":16.008193514076144,"score":16.008193514076144},"GB2-07":{"attempts":1,"playable":14.347636428599724,"score":14.347636428599724},"GB2-08":{"attempts":1,"playable":29.810856506165578,"score":29.810856506165578}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.17062916899501,"score":43.17062916899501},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.48148971412053,"score":40.48148971412053},"GB2-05":{"attempts":1,"playable":16.854093868907924,"score":16.854093868907924},"GB2-06":{"attempts":1,"playable":18.448405513769035,"score":18.448405513769035},"GB2-07":{"attempts":1,"playable":10.71773772789796,"score":10.71773772789796},"GB2-08":{"attempts":1,"playable":34.38524564625881,"score":34.38524564625881}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.372369773291396,"score":42.372369773291396},"GB2-03":{"attempts":1,"playable":46.03905847000343,"score":46.03905847000343},"GB2-04":{"attempts":1,"playable":43.83100035775544,"score":43.83100035775544},"GB2-05":{"attempts":1,"playable":39.804869462568284,"score":39.804869462568284},"GB2-06":{"attempts":1,"playable":22.382666627829977,"score":22.382666627829977},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"inception/mercury-2.5-preview","is_recent_addition":false,"last_measured_at":"2026-10-22T09:50:59Z","match_totals_all":{"draws":2879,"losses":4369,"wins":954},"match_totals_tracks":{"highest":{"draws":1040,"losses":1614,"wins":248},"medium":{"draws":999,"losses":1665,"wins":246},"none":{"draws":840,"losses":1090,"wins":460}},"model_slug":"inception-mercury-2-5-preview","overall":{"max":46.03905847000343,"mean":21.987569118617206,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":62,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.796050012590833,"GB2-02":42.16651957593997,"GB2-04":39.08483647804285,"GB2-06":16.008193514076144,"GB2-07":14.347636428599724,"GB2-08":29.810856506165578},"per_game_all":{"GB2-02":42.56983950607546,"GB2-04":41.132442183306274,"GB2-06":18.946421885225053},"per_game_match_totals_all":{"GB2-01":{"draws":112,"losses":306,"wins":74},"GB2-02":{"draws":1122,"losses":243,"wins":3},"GB2-03":{"draws":111,"losses":219,"wins":146},"GB2-04":{"draws":1009,"losses":342,"wins":61},"GB2-05":{"draws":0,"losses":733,"wins":279},"GB2-06":{"draws":10,"losses":1191,"wins":233},"GB2-07":{"draws":0,"losses":885,"wins":107},"GB2-08":{"draws":515,"losses":450,"wins":51}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":112,"losses":306,"wins":74},"GB2-02":{"draws":370,"losses":84,"wins":2},"GB2-04":{"draws":335,"losses":123,"wins":12},"GB2-06":{"draws":3,"losses":410,"wins":65},"GB2-07":{"draws":0,"losses":436,"wins":62},"GB2-08":{"draws":220,"losses":255,"wins":33}},"medium":{"GB2-02":{"draws":379,"losses":76,"wins":1},"GB2-04":{"draws":321,"losses":124,"wins":25},"GB2-05":{"draws":0,"losses":422,"wins":82},"GB2-06":{"draws":4,"losses":399,"wins":75},"GB2-07":{"draws":0,"losses":449,"wins":45},"GB2-08":{"draws":295,"losses":195,"wins":18}},"none":{"GB2-02":{"draws":373,"losses":83,"wins":0},"GB2-03":{"draws":111,"losses":219,"wins":146},"GB2-04":{"draws":353,"losses":95,"wins":24},"GB2-05":{"draws":0,"losses":311,"wins":197},"GB2-06":{"draws":3,"losses":382,"wins":93}}},"per_game_raw_elo_all":{"GB2-02":1417.362660741921,"GB2-04":1409.193348562483,"GB2-06":947.9837856271982},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1249.1163574502532,"GB2-02":1414.2350831286121,"GB2-04":1393.155372743056,"GB2-06":897.8805242560857,"GB2-07":938.6842084892398,"GB2-08":1193.286958550435},"medium":{"GB2-02":1422.0196445189376,"GB2-04":1404.164457383502,"GB2-05":951.6905261175319,"GB2-06":940.731460252817,"GB2-07":854.8059290224148,"GB2-08":1241.051551498205},"none":{"GB2-02":1415.833254578213,"GB2-03":1397.6184725258688,"GB2-04":1430.2602155608909,"GB2-05":1311.215956170791,"GB2-06":1005.339372372692}},"per_game_tracks":{"highest":{"GB2-01":27.796050012590833,"GB2-02":42.16651957593997,"GB2-04":39.08483647804285,"GB2-06":16.008193514076144,"GB2-07":14.347636428599724,"GB2-08":29.810856506165578},"medium":{"GB2-02":43.17062916899501,"GB2-04":40.48148971412053,"GB2-05":16.854093868907924,"GB2-06":18.448405513769035,"GB2-07":10.71773772789796,"GB2-08":34.38524564625881},"none":{"GB2-02":42.372369773291396,"GB2-03":46.03905847000343,"GB2-04":43.83100035775544,"GB2-05":39.804869462568284,"GB2-06":22.382666627829977}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":-3,"rank_movement_baseline_at":"2026-10-20T11:13:32Z","reasoning":{"highest":21.151761564426888,"medium":20.50720020499366,"none":24.30374558643107},"reasoning_agg":{"highest":{"max":42.16651957593997,"mean":21.151761564426888,"min":0.0},"medium":{"max":43.17062916899501,"mean":20.50720020499366,"min":0.0},"none":{"max":46.03905847000343,"mean":24.30374558643107,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":3.7965453814374115}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:ba04af9c02fb7b99","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":0.21994025000000003},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.081084},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.081084},"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":15.921520641607705,"highest":28.091746633560366,"medium":26.962676515684507,"none":18.171534229348687},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"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"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":24.227224982759907,"score":16.151483321839937},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":42.90800475997001,"score":14.302668253323338},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":44.034689579104445,"score":29.356459719402963},"GB2-05":{"attempts":3,"playable":11.376896465709464,"score":11.376896465709464},"GB2-06":{"attempts":3,"playable":22.29104009842459,"score":22.29104009842459},"GB2-07":{"attempts":3,"playable":14.096625360689062,"score":14.096625360689062},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":35.183471875242105,"score":23.45564791682807}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.38848321030736,"score":43.38848321030736},"GB2-05":{"attempts":1,"playable":10.73068794572349,"score":10.73068794572349},"GB2-06":{"attempts":1,"playable":19.187086144447825,"score":19.187086144447825},"GB2-07":{"attempts":1,"playable":33.48127686427242,"score":33.48127686427242},"GB2-08":{"attempts":1,"playable":33.671199003050724,"score":33.671199003050724}},"medium":{"GB2-01":{"attempts":1,"playable":34.16802719128088,"score":34.16802719128088},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":44.680895947901526,"score":44.680895947901526},"GB2-05":{"attempts":1,"playable":17.23742395337964,"score":17.23742395337964},"GB2-06":{"attempts":1,"playable":22.961880382734787,"score":22.961880382734787},"GB2-07":{"attempts":1,"playable":6.032086871376703,"score":6.032086871376703},"GB2-08":{"attempts":1,"playable":36.69574474743348,"score":36.69574474743348}},"none":{"GB2-01":{"attempts":1,"playable":14.286422774238932,"score":14.286422774238932},"GB2-02":{"attempts":1,"playable":42.90800475997001,"score":42.90800475997001},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":6.162577498025268,"score":6.162577498025268},"GB2-06":{"attempts":1,"playable":24.72415376809117,"score":24.72415376809117},"GB2-07":{"attempts":1,"playable":2.7765123464180648,"score":2.7765123464180648},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-22T10:56:58Z","match_totals_all":{"draws":1782,"losses":5140,"wins":898},"match_totals_tracks":{"highest":{"draws":613,"losses":1506,"wins":339},"medium":{"draws":705,"losses":1841,"wins":394},"none":{"draws":464,"losses":1793,"wins":165}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":44.680895947901526,"mean":16.37885264202718,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":63,"overall_ranking_status":"partial","per_game":{"GB2-04":43.38848321030736,"GB2-05":10.73068794572349,"GB2-06":19.187086144447825,"GB2-07":33.48127686427242,"GB2-08":33.671199003050724},"per_game_all":{"GB2-05":11.376896465709464,"GB2-06":22.29104009842459,"GB2-07":14.096625360689062},"per_game_match_totals_all":{"GB2-01":{"draws":327,"losses":586,"wins":63},"GB2-02":{"draws":365,"losses":84,"wins":7},"GB2-04":{"draws":649,"losses":213,"wins":78},"GB2-05":{"draws":0,"losses":1357,"wins":163},"GB2-06":{"draws":10,"losses":1148,"wins":276},"GB2-07":{"draws":0,"losses":1296,"wins":188},"GB2-08":{"draws":431,"losses":456,"wins":123}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":341,"losses":101,"wins":28},"GB2-05":{"draws":0,"losses":457,"wins":51},"GB2-06":{"draws":0,"losses":398,"wins":80},"GB2-07":{"draws":0,"losses":344,"wins":154},"GB2-08":{"draws":272,"losses":206,"wins":26}},"medium":{"GB2-01":{"draws":235,"losses":209,"wins":44},"GB2-04":{"draws":308,"losses":112,"wins":50},"GB2-05":{"draws":0,"losses":422,"wins":84},"GB2-06":{"draws":3,"losses":380,"wins":95},"GB2-07":{"draws":0,"losses":468,"wins":24},"GB2-08":{"draws":159,"losses":250,"wins":97}},"none":{"GB2-01":{"draws":92,"losses":377,"wins":19},"GB2-02":{"draws":365,"losses":84,"wins":7},"GB2-05":{"draws":0,"losses":478,"wins":28},"GB2-06":{"draws":7,"losses":370,"wins":101},"GB2-07":{"draws":0,"losses":484,"wins":10}}},"per_game_raw_elo_all":{"GB2-05":815.1930307431059,"GB2-06":1003.30403169722,"GB2-07":826.8266617982894},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1426.8308846555572,"GB2-05":814.2178804590366,"GB2-06":953.2125547805034,"GB2-07":1241.0206393259998,"GB2-08":1233.6801370838489},"medium":{"GB2-01":1317.083159878683,"GB2-04":1436.8361750129336,"GB2-05":959.2764174044934,"GB2-06":1014.5343947544335,"GB2-07":707.0744840614924,"GB2-08":1264.8006698155662},"none":{"GB2-01":1067.43011790085,"GB2-02":1419.986173309112,"GB2-05":672.0847943657878,"GB2-06":1042.165145556723,"GB2-07":532.3848620073758}},"per_game_tracks":{"highest":{"GB2-04":43.38848321030736,"GB2-05":10.73068794572349,"GB2-06":19.187086144447825,"GB2-07":33.48127686427242,"GB2-08":33.671199003050724},"medium":{"GB2-01":34.16802719128088,"GB2-04":44.680895947901526,"GB2-05":17.23742395337964,"GB2-06":22.961880382734787,"GB2-07":6.032086871376703,"GB2-08":36.69574474743348},"none":{"GB2-01":14.286422774238932,"GB2-02":42.90800475997001,"GB2-05":6.162577498025268,"GB2-06":24.72415376809117,"GB2-07":2.7765123464180648}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.557341645975228,"medium":20.22200738676338,"none":11.35720889334293},"reasoning_agg":{"highest":{"max":43.38848321030736,"mean":17.557341645975228,"min":0.0},"medium":{"max":44.680895947901526,"mean":20.22200738676338,"min":0.0},"none":{"max":42.90800475997001,"mean":11.35720889334293,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":8.86479849342045}},{"canonical_public_row_identity":"publication-row.v1:overall:upstage-solar-mini4:c2d1550765ed5b85","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.02342595,"mean":0.01633628125,"median":0.016221199999999998,"min":0.011361950000000001,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.13069024999999998},"medium":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.012110200000000002,"mean":0.0072751125,"median":0.0080226,"min":0.00114085,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.0582009},"none":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0023752,"mean":0.0015195812500000002,"median":0.00138595,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":0.01215665}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.012110200000000002,"mean":0.0072751125,"median":0.0080226,"min":0.00114085,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.0582009},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0023752,"mean":0.0015195812500000002,"median":0.00138595,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":0.012156650000000001},"historical-provider-setting-intensive":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.02342595,"mean":0.01633628125,"median":0.016221199999999998,"min":0.011361950000000001,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.13069025}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":24,"cost_basis_counts":{"provider_reported":49},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":17,"max":0.02342595,"mean":0.008376991666666668,"median":0.0080226,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":48},"recorded_attempt_count":49,"run_count":24,"total":0.20104779999999997},"codegen_latency_ms":{"attempt_count":48,"max_ms":1854161,"mean_ms":628655.8260869565,"min_ms":24176,"run_count":23},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":1854161,"mean_ms":1241203.5,"min_ms":669527,"run_count":8},"medium":{"attempt_count":14,"max_ms":912503,"mean_ms":578415.5714285715,"min_ms":208280,"run_count":7},"none":{"attempt_count":16,"max_ms":108436,"mean_ms":60068.375,"min_ms":24176,"run_count":8}},"codegen_output_tokens":{"attempt_count":49,"output_max":112315,"output_mean":38073.333333333336,"output_min":1354,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":112315,"output_mean":77461.75,"output_min":52895,"run_count":8},"medium":{"attempt_count":15,"output_max":54994,"output_mean":32804.625,"output_min":3815,"run_count":8},"none":{"attempt_count":16,"output_max":7089,"output_mean":3953.625,"output_min":1354,"run_count":8}},"display_name":"Solar Mini 4","economics":{"highest":36.935734245678894,"medium":19.926003442003516,"none":40.78389519984609},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":49,"effective_max_output_tokens":[131072],"finish_reason_observations":48,"finish_reasons":["stop"],"indexed_attempts":49,"output_token_observations":49,"provider_post_attempt_observations":49,"provider_post_attempts":51,"reasoning_token_observations":49,"reconciliation_get_attempt_observations":49,"requested_max_output_token_observations":49,"requested_max_output_tokens":[131072],"total_output_tokens":913760,"total_reasoning_output_tokens":808441,"total_visible_output_tokens":105319,"visible_token_observations":49},"generation_policy":{"generation_policy":"quality_generation_policy","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":"upstage","provider_model":"upstage/solar-mini4","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":7,"failed_game_aliases":["GB2-03","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"model_code_failure_rate":0.7142857142857143,"model_code_failures":5,"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},"baseline":{"admitted_plugins":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"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}},"intensive":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":19.47212403158535,"score":6.49070801052845},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.78389519984609,"score":13.59463173328203},"GB2-05":{"attempts":3,"failed_attempts":2,"playable":46.59197845396087,"score":15.530659484653624},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":25.880993784595027,"score":17.253995856396685},"GB2-07":{"attempts":3,"failed_attempts":2,"playable":32.833119566307424,"score":10.944373188769141},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":46.59197845396087,"score":46.59197845396087},"GB2-06":{"attempts":1,"playable":31.38210471676837,"score":31.38210471676837},"GB2-07":{"attempts":1,"playable":32.833119566307424,"score":32.833119566307424},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":19.47212403158535,"score":19.47212403158535},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":20.379882852421684,"score":20.379882852421684},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.78389519984609,"score":40.78389519984609},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"upstage/solar-mini4","is_recent_addition":false,"last_measured_at":"2026-10-22T09:44:58Z","match_totals_all":{"draws":423,"losses":1834,"wins":669},"match_totals_tracks":{"highest":{"draws":7,"losses":963,"wins":514},"medium":{"draws":84,"losses":748,"wins":134},"none":{"draws":332,"losses":123,"wins":21}},"model_slug":"upstage-solar-mini4","overall":{"max":46.59197845396087,"mean":8.214010360894259,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":64,"overall_ranking_status":"partial","per_game":{"GB2-05":46.59197845396087,"GB2-06":31.38210471676837,"GB2-07":32.833119566307424},"per_game_match_totals_all":{"GB2-01":{"draws":79,"losses":360,"wins":51},"GB2-04":{"draws":332,"losses":123,"wins":21},"GB2-05":{"draws":0,"losses":274,"wins":232},"GB2-06":{"draws":12,"losses":728,"wins":214},"GB2-07":{"draws":0,"losses":349,"wins":151}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":274,"wins":232},"GB2-06":{"draws":7,"losses":340,"wins":131},"GB2-07":{"draws":0,"losses":349,"wins":151}},"medium":{"GB2-01":{"draws":79,"losses":360,"wins":51},"GB2-06":{"draws":5,"losses":388,"wins":83}},"none":{"GB2-04":{"draws":332,"losses":123,"wins":21}}},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1397.339922216162,"GB2-06":1143.8184854780104,"GB2-07":1232.4958202640992},"medium":{"GB2-01":1146.5611709250215,"GB2-06":972.987829532291},"none":{"GB2-04":1406.5363614203554}},"per_game_tracks":{"highest":{"GB2-05":46.59197845396087,"GB2-06":31.38210471676837,"GB2-07":32.833119566307424},"medium":{"GB2-01":19.47212403158535,"GB2-06":20.379882852421684},"none":{"GB2-04":40.78389519984609}},"provider_color":"#805CFB","provider_company":"Upstage","provider_key":"upstage","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":13.850900342129584,"medium":5.693143840572433,"none":5.097986899980762},"reasoning_agg":{"highest":{"max":46.59197845396087,"mean":13.850900342129584,"min":0.0},"medium":{"max":20.379882852421684,"mean":5.693143840572433,"min":0.0},"none":{"max":40.78389519984609,"mean":5.097986899980762,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.752913442148824}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:be67b64b0b6e292f","codegen_cost_by_reasoning":{"highest":{"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.01113168,"mean":0.0083819225,"median":0.007854965,"min":0.00635193,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.06705538000000001},"medium":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.00328117,"mean":0.0022631475,"median":0.0021966650000000004,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":19},"recorded_attempt_count":19,"run_count":8,"total":0.01810518},"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":1,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.00328117,"mean":0.0022631475,"median":0.0021966650000000004,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":19},"recorded_attempt_count":19,"run_count":8,"total":0.018105180000000002},"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":0.022539919999999995},"historical-provider-setting-intensive":{"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.01113168,"mean":0.0083819225,"median":0.007854965,"min":0.00635193,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.06705538}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":24,"cost_basis_counts":{"provider_reported":56},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":23,"max":0.01113168,"mean":0.00448752,"median":0.002935335,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":37},"recorded_attempt_count":56,"run_count":24,"total":0.10770048},"codegen_latency_ms":{"attempt_count":56,"max_ms":643052,"mean_ms":207186.875,"min_ms":45308,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":643052,"mean_ms":466285.75,"min_ms":257629,"run_count":8},"medium":{"attempt_count":19,"max_ms":129121,"mean_ms":76432.5,"min_ms":45308,"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":56,"output_max":39360,"output_mean":13818.666666666666,"output_min":3954,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":39360,"output_mean":29587.25,"output_min":21705,"run_count":8},"medium":{"attempt_count":19,"output_max":7321,"output_mean":5310.0,"output_min":3954,"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":{"medium":38.72118165069343},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":37,"effective_max_output_tokens":[117964],"finish_reason_observations":56,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":56,"provider_post_attempt_observations":56,"provider_post_attempts":56,"reasoning_token_observations":56,"reconciliation_get_attempt_observations":56,"reconciliation_get_attempts":88,"requested_max_output_token_observations":37,"requested_max_output_tokens":[117964],"total_output_tokens":331648,"total_reasoning_output_tokens":194609,"total_visible_output_tokens":137039,"visible_token_observations":56},"generation_policy":{"generation_policy":"quality_generation_policy","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":"ibm","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"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},"baseline":{"admitted_plugins":0,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":1.0,"model_code_failures":8,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"under_tested","grouped_stable":false,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":0,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":1.0,"model_code_failures":8,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"under_tested","grouped_stable":false,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-02":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":38.72118165069343,"score":12.907060550231144},"GB2-05":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-06":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-07":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.72118165069343,"score":38.72118165069343},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"ibm-granite/granite-4.2-8b","is_recent_addition":false,"last_measured_at":"2026-10-22T03:22:21Z","match_totals_all":{"draws":300,"losses":144,"wins":26},"match_totals_tracks":{"medium":{"draws":300,"losses":144,"wins":26}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":38.72118165069343,"mean":1.613382568778893,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","grouped_stability_incomplete"],"overall_official_rank":65,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-04":{"draws":300,"losses":144,"wins":26}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":300,"losses":144,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1390.2725008237048}},"per_game_tracks":{"medium":{"GB2-04":38.72118165069343}},"provider_color":"#0F62FE","provider_company":"IBM","provider_key":"ibm","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":0.0,"medium":4.840147706336679,"none":0.0},"reasoning_agg":{"highest":{"max":0.0,"mean":0.0,"min":0.0},"medium":{"max":38.72118165069343,"mean":4.840147706336679,"min":0.0},"none":{"max":0.0,"mean":0.0,"min":0.0}},"reasoning_labels":{"highest":"Full","medium":"Low","none":"Non-thinking"},"reasoning_settings":{"balanced":"low"},"score_diagnostics":{"reasoning_variance":4.840147706336679}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10:732b2f0caf422303","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128}},"codegen_cost_by_setting":{"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":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.23661279999999998}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128},"codegen_latency_ms":{"attempt_count":8,"max_ms":215199,"mean_ms":151362.125,"min_ms":97625,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":8,"max_ms":215199,"mean_ms":151362.125,"min_ms":97625,"run_count":8}},"codegen_output_tokens":{"attempt_count":8,"output_max":11980,"output_mean":7218.375,"output_min":3411,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":8,"output_max":11980,"output_mean":7218.375,"output_min":3411,"run_count":8}},"display_name":"Pareto 26.10","economics":{"none":90.70669293332905},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":8,"effective_max_output_tokens":[131072],"finish_reason_observations":8,"finish_reasons":["stop"],"indexed_attempts":8,"output_token_observations":8,"provider_post_attempt_observations":8,"provider_post_attempts":8,"reasoning_token_observations":8,"reconciliation_get_attempt_observations":8,"requested_max_output_token_observations":8,"requested_max_output_tokens":[131072],"total_output_tokens":57747,"total_visible_output_tokens":57747,"visible_token_observations":8},"generation_policy":{"generation_policy":"quality_generation_policy","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":"unbiased","provider_model":"unbiased/pareto-26.10","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":92.43345241035907,"score":92.43345241035907},"GB2-02":{"attempts":1,"playable":79.67294953657564,"score":79.67294953657564},"GB2-03":{"attempts":1,"playable":96.70746479373689,"score":96.70746479373689},"GB2-04":{"attempts":1,"playable":85.19139285420269,"score":85.19139285420269},"GB2-05":{"attempts":1,"playable":91.83844401917078,"score":91.83844401917078},"GB2-06":{"attempts":1,"playable":94.02588347412058,"score":94.02588347412058},"GB2-07":{"attempts":1,"playable":94.46576118806253,"score":94.46576118806253},"GB2-08":{"attempts":1,"playable":91.31819519040427,"score":91.31819519040427}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":92.43345241035907,"score":92.43345241035907},"GB2-02":{"attempts":1,"playable":79.67294953657564,"score":79.67294953657564},"GB2-03":{"attempts":1,"playable":96.70746479373689,"score":96.70746479373689},"GB2-04":{"attempts":1,"playable":85.19139285420269,"score":85.19139285420269},"GB2-05":{"attempts":1,"playable":91.83844401917078,"score":91.83844401917078},"GB2-06":{"attempts":1,"playable":94.02588347412058,"score":94.02588347412058},"GB2-07":{"attempts":1,"playable":94.46576118806253,"score":94.46576118806253},"GB2-08":{"attempts":1,"playable":91.31819519040427,"score":91.31819519040427}}},"id":"unbiased/pareto-26.10","is_recent_addition":false,"last_measured_at":"2026-10-22T10:56:24Z","match_totals_all":{"draws":223,"losses":158,"wins":2275},"match_totals_tracks":{"none":{"draws":223,"losses":158,"wins":2275}},"model_slug":"unbiased-pareto-26-10","overall":{"max":96.70746479373689,"mean":90.70669293332905,"min":79.67294953657564},"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":23,"wins":257},"GB2-02":{"draws":177,"losses":11,"wins":280},"GB2-03":{"draws":1,"losses":4,"wins":261},"GB2-04":{"draws":35,"losses":23,"wins":196},"GB2-05":{"draws":0,"losses":43,"wins":477},"GB2-06":{"draws":10,"losses":15,"wins":263},"GB2-07":{"draws":0,"losses":12,"wins":264},"GB2-08":{"draws":0,"losses":27,"wins":277}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":0,"losses":23,"wins":257},"GB2-02":{"draws":177,"losses":11,"wins":280},"GB2-03":{"draws":1,"losses":4,"wins":261},"GB2-04":{"draws":35,"losses":23,"wins":196},"GB2-05":{"draws":0,"losses":43,"wins":477},"GB2-06":{"draws":10,"losses":15,"wins":263},"GB2-07":{"draws":0,"losses":12,"wins":264},"GB2-08":{"draws":0,"losses":27,"wins":277}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":2053.895244981297,"GB2-02":1752.0368876236644,"GB2-03":2336.3761180338392,"GB2-04":1832.7481515121049,"GB2-05":2345.5427905371525,"GB2-06":2312.012446761293,"GB2-07":2406.8287435457596,"GB2-08":2182.0519180967385}},"per_game_tracks":{"none":{"GB2-01":92.43345241035907,"GB2-02":79.67294953657564,"GB2-03":96.70746479373689,"GB2-04":85.19139285420269,"GB2-05":91.83844401917078,"GB2-06":94.02588347412058,"GB2-07":94.46576118806253,"GB2-08":91.31819519040427}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":90.70669293332905},"reasoning_agg":{"none":{"max":96.70746479373689,"mean":90.70669293332905,"min":79.67294953657564}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10-preview:5bf9476febd0847c","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998}},"codegen_cost_by_setting":{"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":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998},"codegen_latency_ms":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8}},"codegen_output_tokens":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8}},"display_name":"Pareto 26.10 Preview","economics":{"none":89.81375813482263},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[131072],"finish_reason_observations":9,"finish_reasons":["stop"],"indexed_attempts":9,"output_token_observations":9,"provider_post_attempt_observations":9,"provider_post_attempts":9,"reasoning_token_observations":9,"reconciliation_get_attempt_observations":9,"requested_max_output_token_observations":9,"requested_max_output_tokens":[131072],"total_output_tokens":57710,"total_visible_output_tokens":57710,"visible_token_observations":9},"generation_policy":{"generation_policy":"quality_generation_policy","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":"unbiased","provider_model":"unbiased/pareto-26.10-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":74.37041761688418,"score":74.37041761688418},"GB2-02":{"attempts":1,"playable":91.48260814275451,"score":91.48260814275451},"GB2-03":{"attempts":1,"playable":94.0806560303095,"score":94.0806560303095},"GB2-04":{"attempts":1,"playable":86.14842377728753,"score":86.14842377728753},"GB2-05":{"attempts":1,"playable":94.70157304966443,"score":94.70157304966443},"GB2-06":{"attempts":1,"playable":87.60006938940906,"score":87.60006938940906},"GB2-07":{"attempts":1,"playable":95.82835370603625,"score":95.82835370603625},"GB2-08":{"attempts":1,"playable":94.29796336623556,"score":94.29796336623556}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":74.37041761688418,"score":74.37041761688418},"GB2-02":{"attempts":1,"playable":91.48260814275451,"score":91.48260814275451},"GB2-03":{"attempts":1,"playable":94.0806560303095,"score":94.0806560303095},"GB2-04":{"attempts":1,"playable":86.14842377728753,"score":86.14842377728753},"GB2-05":{"attempts":1,"playable":94.70157304966443,"score":94.70157304966443},"GB2-06":{"attempts":1,"playable":87.60006938940906,"score":87.60006938940906},"GB2-07":{"attempts":1,"playable":95.82835370603625,"score":95.82835370603625},"GB2-08":{"attempts":1,"playable":94.29796336623556,"score":94.29796336623556}}},"id":"unbiased/pareto-26.10-preview","is_recent_addition":false,"last_measured_at":"2026-10-22T07:31:03Z","match_totals_all":{"draws":129,"losses":335,"wins":3428},"match_totals_tracks":{"none":{"draws":129,"losses":335,"wins":3428}},"model_slug":"unbiased-pareto-26-10-preview","overall":{"max":95.82835370603625,"mean":89.81375813482263,"min":74.37041761688418},"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":124,"wins":352},"GB2-02":{"draws":36,"losses":21,"wins":399},"GB2-03":{"draws":5,"losses":27,"wins":442},"GB2-04":{"draws":39,"losses":49,"wins":384},"GB2-05":{"draws":0,"losses":25,"wins":487},"GB2-06":{"draws":37,"losses":43,"wins":400},"GB2-07":{"draws":0,"losses":18,"wins":486},"GB2-08":{"draws":0,"losses":28,"wins":478}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":12,"losses":124,"wins":352},"GB2-02":{"draws":36,"losses":21,"wins":399},"GB2-03":{"draws":5,"losses":27,"wins":442},"GB2-04":{"draws":39,"losses":49,"wins":384},"GB2-05":{"draws":0,"losses":25,"wins":487},"GB2-06":{"draws":37,"losses":43,"wins":400},"GB2-07":{"draws":0,"losses":18,"wins":486},"GB2-08":{"draws":0,"losses":28,"wins":478}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1725.5928605092597,"GB2-02":1969.8918892291117,"GB2-03":2172.665744946371,"GB2-04":1848.8939242747488,"GB2-05":2504.886865625316,"GB2-06":2115.717077496899,"GB2-07":2495.0000804948736,"GB2-08":2303.8853793366975}},"per_game_tracks":{"none":{"GB2-01":74.37041761688418,"GB2-02":91.48260814275451,"GB2-03":94.0806560303095,"GB2-04":86.14842377728753,"GB2-05":94.70157304966443,"GB2-06":87.60006938940906,"GB2-07":95.82835370603625,"GB2-08":94.29796336623556}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":89.81375813482263},"reasoning_agg":{"none":{"max":95.82835370603625,"mean":89.81375813482263,"min":74.37041761688418}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:821a160a66db4312","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.056915889375,"median":0.0447982575,"min":0.02822715,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.455327115},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.05751309}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.056915889375,"median":0.0447982575,"min":0.02822715,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.45532711500000006},"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":0.05751309}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.032052512812499996,"median":0.0201057,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":19,"run_count":16,"total":0.512840205},"codegen_latency_ms":{"attempt_count":19,"max_ms":3172586,"mean_ms":488857.125,"min_ms":33029,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":9,"max_ms":3172586,"mean_ms":924271.75,"min_ms":388744,"run_count":8},"none":{"attempt_count":10,"max_ms":84396,"mean_ms":53442.5,"min_ms":33029,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":171951,"output_mean":32110.125,"output_min":2214,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":9,"output_max":171951,"output_mean":60792.125,"output_min":28781,"run_count":8},"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":73.21018196925738,"none":50.905786978836225},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":19,"effective_max_output_tokens":[131072],"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"provider_post_attempt_observations":19,"provider_post_attempts":20,"reasoning_token_observations":19,"reconciliation_get_attempt_observations":19,"requested_max_output_token_observations":19,"requested_max_output_tokens":[131072],"total_output_tokens":513762,"total_reasoning_output_tokens":447944,"total_visible_output_tokens":65818,"visible_token_observations":19},"generation_policy":{"generation_policy":"quality_generation_policy","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":46.9205885495434,"score":46.9205885495434},"GB2-02":{"attempts":2,"playable":60.78311136580862,"score":60.78311136580862},"GB2-03":{"attempts":2,"playable":65.57044889639158,"score":65.57044889639158},"GB2-04":{"attempts":2,"playable":50.469620261654484,"score":50.469620261654484},"GB2-05":{"attempts":2,"playable":65.09183353901189,"score":65.09183353901189},"GB2-06":{"attempts":2,"playable":56.46201758009731,"score":56.46201758009731},"GB2-07":{"attempts":2,"playable":66.67978153901939,"score":66.67978153901939},"GB2-08":{"attempts":2,"playable":84.48647406084768,"score":84.48647406084768}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":54.047219023956735,"score":54.047219023956735},"GB2-02":{"attempts":1,"playable":81.00428939825213,"score":81.00428939825213},"GB2-03":{"attempts":1,"playable":85.60384809432335,"score":85.60384809432335},"GB2-04":{"attempts":1,"playable":45.79057905850182,"score":45.79057905850182},"GB2-05":{"attempts":1,"playable":84.67143416047293,"score":84.67143416047293},"GB2-06":{"attempts":1,"playable":57.427715517084465,"score":57.427715517084465},"GB2-07":{"attempts":1,"playable":90.09727670869583,"score":90.09727670869583},"GB2-08":{"attempts":1,"playable":87.03909379277167,"score":87.03909379277167}},"none":{"GB2-01":{"attempts":1,"playable":39.79395807513007,"score":39.79395807513007},"GB2-02":{"attempts":1,"playable":40.56193333336511,"score":40.56193333336511},"GB2-03":{"attempts":1,"playable":45.53704969845981,"score":45.53704969845981},"GB2-04":{"attempts":1,"playable":55.148661464807155,"score":55.148661464807155},"GB2-05":{"attempts":1,"playable":45.51223291755084,"score":45.51223291755084},"GB2-06":{"attempts":1,"playable":55.49631964311016,"score":55.49631964311016},"GB2-07":{"attempts":1,"playable":43.26228636934293,"score":43.26228636934293},"GB2-08":{"attempts":1,"playable":81.93385432892372,"score":81.93385432892372}}},"id":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-10-22T11:01:23Z","match_totals_all":{"draws":1337,"losses":2363,"wins":4022},"match_totals_tracks":{"medium":{"draws":355,"losses":887,"wins":2616},"none":{"draws":982,"losses":1476,"wins":1406}},"model_slug":"xiaomi-mimo-v2-6-pro","overall":{"max":90.09727670869583,"mean":62.057984474046805,"min":39.79395807513007},"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":292,"losses":387,"wins":297},"GB2-02":{"draws":421,"losses":154,"wins":333},"GB2-03":{"draws":95,"losses":297,"wins":544},"GB2-04":{"draws":476,"losses":240,"wins":224},"GB2-05":{"draws":0,"losses":362,"wins":648},"GB2-06":{"draws":53,"losses":415,"wins":486},"GB2-07":{"draws":0,"losses":342,"wins":648},"GB2-08":{"draws":0,"losses":166,"wins":842}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":75,"losses":194,"wins":219},"GB2-02":{"draws":78,"losses":50,"wins":326},"GB2-03":{"draws":2,"losses":72,"wins":394},"GB2-04":{"draws":170,"losses":176,"wins":124},"GB2-05":{"draws":0,"losses":80,"wins":426},"GB2-06":{"draws":30,"losses":200,"wins":246},"GB2-07":{"draws":0,"losses":46,"wins":446},"GB2-08":{"draws":0,"losses":69,"wins":435}},"none":{"GB2-01":{"draws":217,"losses":193,"wins":78},"GB2-02":{"draws":343,"losses":104,"wins":7},"GB2-03":{"draws":93,"losses":225,"wins":150},"GB2-04":{"draws":306,"losses":64,"wins":100},"GB2-05":{"draws":0,"losses":282,"wins":222},"GB2-06":{"draws":23,"losses":215,"wins":240},"GB2-07":{"draws":0,"losses":296,"wins":202},"GB2-08":{"draws":0,"losses":97,"wins":407}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1509.7294721087792,"GB2-02":1769.9973798063147,"GB2-03":1884.3059877046267,"GB2-04":1445.4073656899527,"GB2-05":2055.491612490211,"GB2-06":1545.2441868349347,"GB2-07":2187.208620652736,"GB2-08":2049.304007055444},"none":{"GB2-01":1373.1508292434382,"GB2-02":1401.7283176957076,"GB2-03":1393.2518855553908,"GB2-04":1518.2033459272259,"GB2-05":1383.8491058941884,"GB2-06":1513.9762060922374,"GB2-07":1365.0153039043594,"GB2-08":1920.7801204436523}},"per_game_tracks":{"medium":{"GB2-01":54.047219023956735,"GB2-02":81.00428939825213,"GB2-03":85.60384809432335,"GB2-04":45.79057905850182,"GB2-05":84.67143416047293,"GB2-06":57.427715517084465,"GB2-07":90.09727670869583,"GB2-08":87.03909379277167},"none":{"GB2-01":39.79395807513007,"GB2-02":40.56193333336511,"GB2-03":45.53704969845981,"GB2-04":55.148661464807155,"GB2-05":45.51223291755084,"GB2-06":55.49631964311016,"GB2-07":43.26228636934293,"GB2-08":81.93385432892372}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":73.21018196925738,"none":50.905786978836225},"reasoning_agg":{"medium":{"max":90.09727670869583,"mean":73.21018196925738,"min":45.79057905850182},"none":{"max":81.93385432892372,"mean":50.905786978836225,"min":39.79395807513007}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":22.30439499042115}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-5-preview:acd288b5e05bf9f7","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419},"medium":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419}},"codegen_cost_usd":{"admitted_cell_count":2,"cell_count":3,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1851245,"median":0.183419,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":5,"run_count":3,"total":0.5553735},"codegen_latency_ms":{"attempt_count":4,"max_ms":724394,"mean_ms":700552.5,"min_ms":676711,"run_count":2},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":2,"max_ms":724394,"mean_ms":724394.0,"min_ms":724394,"run_count":1},"none":{"attempt_count":2,"max_ms":676711,"mean_ms":676711.0,"min_ms":676711,"run_count":1}},"codegen_output_tokens":{"attempt_count":5,"output_max":64000,"output_mean":62025.0,"output_min":59586,"run_count":3},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":1,"output_max":64000,"output_mean":64000.0,"output_min":64000,"run_count":1},"medium":{"attempt_count":2,"output_max":59586,"output_mean":59586.0,"output_min":59586,"run_count":1},"none":{"attempt_count":2,"output_max":62489,"output_mean":62489.0,"output_min":62489,"run_count":1}},"display_name":"Step 5 Preview","economics":{"medium":83.15587622700995,"none":34.96926267501448},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":5,"effective_max_output_tokens":[64000],"finish_reason_observations":4,"finish_reasons":["stop"],"indexed_attempts":5,"output_token_observations":5,"provider_post_attempt_observations":5,"provider_post_attempts":5,"reasoning_token_observations":5,"reconciliation_get_attempt_observations":5,"requested_max_output_token_observations":5,"requested_max_output_tokens":[64000],"total_output_tokens":186075,"total_reasoning_output_tokens":53683,"total_visible_output_tokens":132392,"visible_token_observations":5},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"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":64000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":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":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-08":{"attempts":2,"playable":59.062569451012216,"score":59.062569451012216}},"headline_games_tracks":{"medium":{"GB2-08":{"attempts":1,"playable":83.15587622700995,"score":83.15587622700995}},"none":{"GB2-08":{"attempts":1,"playable":34.96926267501448,"score":34.96926267501448}}},"id":"stepfun/step-5-preview","is_recent_addition":false,"last_measured_at":"2026-10-22T08:39:55Z","match_totals_all":{"draws":277,"losses":287,"wins":450},"match_totals_tracks":{"medium":{"draws":2,"losses":89,"wins":419},"none":{"draws":275,"losses":198,"wins":31}},"model_slug":"stepfun-step-5-preview","overall":{"max":83.15587622700995,"mean":59.062569451012216,"min":34.96926267501448},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":277,"losses":287,"wins":450}},"per_game_match_totals_tracks":{"medium":{"GB2-08":{"draws":2,"losses":89,"wins":419}},"none":{"GB2-08":{"draws":275,"losses":198,"wins":31}}},"per_game_raw_elo_tracks":{"medium":{"GB2-08":1949.6162021345651},"none":{"GB2-08":1247.0665610677875}},"per_game_tracks":{"medium":{"GB2-08":83.15587622700995},"none":{"GB2-08":34.96926267501448}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":83.15587622700995,"none":34.96926267501448},"reasoning_agg":{"medium":{"max":83.15587622700995,"mean":83.15587622700995,"min":83.15587622700995},"none":{"max":34.96926267501448,"mean":34.96926267501448,"min":34.96926267501448}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":48.18661355199548}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:bf28c36bffb0fdb4","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02304638,"mean":0.0178225775,"median":0.01816367,"min":0.01029504,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.14258062000000002},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.0234374}},"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":0.14258062},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.023437399999999997}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02304638,"mean":0.01037612625,"median":0.0072198,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":23},"recorded_attempt_count":23,"run_count":16,"total":0.16601802},"codegen_latency_ms":{"attempt_count":23,"max_ms":1374551,"mean_ms":491530.125,"min_ms":35032,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1374551,"mean_ms":925316.625,"min_ms":428464,"run_count":8},"none":{"attempt_count":12,"max_ms":114099,"mean_ms":57743.625,"min_ms":35032,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":78655,"output_mean":31302.375,"output_min":3072,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":78655,"output_mean":57997.125,"output_min":33074,"run_count":8},"none":{"attempt_count":12,"output_max":6869,"output_mean":4607.625,"output_min":3072,"run_count":8}},"display_name":"MiMo-V2.6-Flash","economics":{"medium":60.16000699865019,"none":46.32408877772629},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":61.19049683836702,"score":61.19049683836702},"GB2-02":{"attempts":2,"playable":54.57878147844953,"score":54.57878147844953},"GB2-03":{"attempts":2,"playable":51.73353598192166,"score":51.73353598192166},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":58.230351482034514,"score":29.115175741017257},"GB2-05":{"attempts":2,"playable":56.510363689393856,"score":56.510363689393856},"GB2-06":{"attempts":2,"playable":60.08463953844536,"score":60.08463953844536},"GB2-07":{"attempts":2,"playable":61.94881638449445,"score":61.94881638449445},"GB2-08":{"attempts":2,"playable":27.61252906455364,"score":27.61252906455364}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":53.86716917657206,"score":53.86716917657206},"GB2-02":{"attempts":1,"playable":67.11648505489401,"score":67.11648505489401},"GB2-03":{"attempts":1,"playable":63.153626157453715,"score":63.153626157453715},"GB2-04":{"attempts":1,"playable":58.230351482034514,"score":58.230351482034514},"GB2-05":{"attempts":1,"playable":60.20788754426244,"score":60.20788754426244},"GB2-06":{"attempts":1,"playable":66.8945051471949,"score":66.8945051471949},"GB2-07":{"attempts":1,"playable":83.19763669580782,"score":83.19763669580782},"GB2-08":{"attempts":1,"playable":28.612394730981975,"score":28.612394730981975}},"none":{"GB2-01":{"attempts":1,"playable":68.51382450016197,"score":68.51382450016197},"GB2-02":{"attempts":1,"playable":42.041077902005036,"score":42.041077902005036},"GB2-03":{"attempts":1,"playable":40.3134458063896,"score":40.3134458063896},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":52.81283983452527,"score":52.81283983452527},"GB2-06":{"attempts":1,"playable":53.274773929695804,"score":53.274773929695804},"GB2-07":{"attempts":1,"playable":40.699996073181076,"score":40.699996073181076},"GB2-08":{"attempts":1,"playable":26.612663398125303,"score":26.612663398125303}}},"id":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:32:10Z","match_totals_all":{"draws":1433,"losses":2786,"wins":3049},"match_totals_tracks":{"medium":{"draws":553,"losses":1331,"wins":1980},"none":{"draws":880,"losses":1455,"wins":1069}},"model_slug":"xiaomi-mimo-v2-6-flash","overall":{"max":83.19763669580782,"mean":50.34679233958035,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":175,"losses":306,"wins":497},"GB2-02":{"draws":537,"losses":156,"wins":215},"GB2-03":{"draws":172,"losses":403,"wins":365},"GB2-04":{"draws":54,"losses":177,"wins":243},"GB2-05":{"draws":0,"losses":448,"wins":564},"GB2-06":{"draws":46,"losses":384,"wins":526},"GB2-07":{"draws":0,"losses":388,"wins":598},"GB2-08":{"draws":449,"losses":524,"wins":41}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":20,"losses":222,"wins":246},"GB2-02":{"draws":197,"losses":56,"wins":201},"GB2-03":{"draws":29,"losses":176,"wins":263},"GB2-04":{"draws":54,"losses":177,"wins":243},"GB2-05":{"draws":0,"losses":205,"wins":299},"GB2-06":{"draws":15,"losses":162,"wins":301},"GB2-07":{"draws":0,"losses":83,"wins":409},"GB2-08":{"draws":238,"losses":250,"wins":18}},"none":{"GB2-01":{"draws":155,"losses":84,"wins":251},"GB2-02":{"draws":340,"losses":100,"wins":14},"GB2-03":{"draws":143,"losses":227,"wins":102},"GB2-05":{"draws":0,"losses":243,"wins":265},"GB2-06":{"draws":31,"losses":222,"wins":225},"GB2-07":{"draws":0,"losses":305,"wins":189},"GB2-08":{"draws":211,"losses":274,"wins":23}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1507.9947602447207,"GB2-02":1616.1751765360357,"GB2-03":1555.7343433398644,"GB2-04":1542.939907740029,"GB2-05":1570.424389007406,"GB2-06":1705.9925915670103,"GB2-07":1966.8513908856726,"GB2-08":1180.4716540265517},"none":{"GB2-01":1657.1722445437465,"GB2-02":1413.2605538869723,"GB2-03":1347.8042315424168,"GB2-05":1474.8819532059465,"GB2-06":1478.5265257726164,"GB2-07":1333.0891186160645,"GB2-08":1158.668076099446}},"per_game_tracks":{"medium":{"GB2-01":53.86716917657206,"GB2-02":67.11648505489401,"GB2-03":63.153626157453715,"GB2-04":58.230351482034514,"GB2-05":60.20788754426244,"GB2-06":66.8945051471949,"GB2-07":83.19763669580782,"GB2-08":28.612394730981975},"none":{"GB2-01":68.51382450016197,"GB2-02":42.041077902005036,"GB2-03":40.3134458063896,"GB2-05":52.81283983452527,"GB2-06":53.274773929695804,"GB2-07":40.699996073181076,"GB2-08":26.612663398125303}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":60.16000699865019,"none":40.533577680510504},"reasoning_agg":{"medium":{"max":83.19763669580782,"mean":60.16000699865019,"min":28.612394730981975},"none":{"max":68.51382450016197,"mean":40.533577680510504,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":19.626429318139685}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:f1e12e0e8e8a182b","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":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.30150960000000004},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"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_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":0.061982706,"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":true,"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":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.020562389374999997,"median":0.015992453,"min":0.0021123,"recorded_attempt_count":22,"run_count":16,"total":0.32899823000000006},"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":61.49707000105604,"none":34.277219106640516},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.88504463263037,"score":42.88504463263037},"GB2-02":{"attempts":2,"playable":51.086922225284084,"score":51.086922225284084},"GB2-03":{"attempts":2,"playable":55.16886576416567,"score":55.16886576416567},"GB2-04":{"attempts":2,"playable":44.31421298853343,"score":44.31421298853343},"GB2-05":{"attempts":2,"playable":44.101994990790644,"score":44.101994990790644},"GB2-06":{"attempts":2,"playable":67.42447726571997,"score":67.42447726571997},"GB2-07":{"attempts":2,"playable":42.67624715436922,"score":42.67624715436922},"GB2-08":{"attempts":2,"playable":35.439391409292824,"score":35.439391409292824}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":51.13530675785991,"score":51.13530675785991},"GB2-02":{"attempts":1,"playable":58.72448839076711,"score":58.72448839076711},"GB2-03":{"attempts":1,"playable":65.51490652430594,"score":65.51490652430594},"GB2-04":{"attempts":1,"playable":47.91352990004999,"score":47.91352990004999},"GB2-05":{"attempts":1,"playable":71.37558639602382,"score":71.37558639602382},"GB2-06":{"attempts":1,"playable":80.07339356989996,"score":80.07339356989996},"GB2-07":{"attempts":1,"playable":75.14298542924794,"score":75.14298542924794},"GB2-08":{"attempts":1,"playable":42.09636304029364,"score":42.09636304029364}},"none":{"GB2-01":{"attempts":1,"playable":34.63478250740082,"score":34.63478250740082},"GB2-02":{"attempts":1,"playable":43.44935605980107,"score":43.44935605980107},"GB2-03":{"attempts":1,"playable":44.822825004025404,"score":44.822825004025404},"GB2-04":{"attempts":1,"playable":40.714896077016874,"score":40.714896077016874},"GB2-05":{"attempts":1,"playable":16.82840358555747,"score":16.82840358555747},"GB2-06":{"attempts":1,"playable":54.77556096153998,"score":54.77556096153998},"GB2-07":{"attempts":1,"playable":10.209508879490494,"score":10.209508879490494},"GB2-08":{"attempts":1,"playable":28.782419778292013,"score":28.782419778292013}}},"id":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:37:07Z","match_totals_all":{"draws":2264,"losses":3035,"wins":2435},"match_totals_tracks":{"medium":{"draws":1116,"losses":987,"wins":1765},"none":{"draws":1148,"losses":2048,"wins":670}},"model_slug":"qwen-qwen3-8-flash","overall":{"max":80.07339356989996,"mean":47.88714455384827,"min":10.209508879490494},"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":282,"losses":431,"wins":263},"GB2-02":{"draws":612,"losses":152,"wins":148},"GB2-03":{"draws":239,"losses":330,"wins":369},"GB2-04":{"draws":595,"losses":236,"wins":109},"GB2-05":{"draws":0,"losses":578,"wins":434},"GB2-06":{"draws":53,"losses":303,"wins":600},"GB2-07":{"draws":0,"losses":576,"wins":412},"GB2-08":{"draws":483,"losses":429,"wins":100}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":176,"losses":159,"wins":153},"GB2-02":{"draws":254,"losses":67,"wins":135},"GB2-03":{"draws":116,"losses":118,"wins":236},"GB2-04":{"draws":277,"losses":111,"wins":82},"GB2-05":{"draws":0,"losses":153,"wins":353},"GB2-06":{"draws":44,"losses":77,"wins":357},"GB2-07":{"draws":0,"losses":125,"wins":369},"GB2-08":{"draws":249,"losses":177,"wins":80}},"none":{"GB2-01":{"draws":106,"losses":272,"wins":110},"GB2-02":{"draws":358,"losses":85,"wins":13},"GB2-03":{"draws":123,"losses":212,"wins":133},"GB2-04":{"draws":318,"losses":125,"wins":27},"GB2-05":{"draws":0,"losses":425,"wins":81},"GB2-06":{"draws":9,"losses":226,"wins":243},"GB2-07":{"draws":0,"losses":451,"wins":43},"GB2-08":{"draws":234,"losses":252,"wins":20}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1481.8028986468082,"GB2-02":1543.688946933821,"GB2-03":1580.4775611755103,"GB2-04":1461.7883673386298,"GB2-05":1739.363017840444,"GB2-06":1952.2645096791323,"GB2-07":1802.5281017377201,"GB2-08":1320.42981207426},"none":{"GB2-01":1321.8443132120765,"GB2-02":1424.1760203204701,"GB2-03":1387.0441300426314,"GB2-04":1405.995507165992,"GB2-05":951.1789161958077,"GB2-06":1502.4181463408333,"GB2-07":841.4999568059983,"GB2-08":1182.3000546050505}},"per_game_tracks":{"medium":{"GB2-01":51.13530675785991,"GB2-02":58.72448839076711,"GB2-03":65.51490652430594,"GB2-04":47.91352990004999,"GB2-05":71.37558639602382,"GB2-06":80.07339356989996,"GB2-07":75.14298542924794,"GB2-08":42.09636304029364},"none":{"GB2-01":34.63478250740082,"GB2-02":43.44935605980107,"GB2-03":44.822825004025404,"GB2-04":40.714896077016874,"GB2-05":16.82840358555747,"GB2-06":54.77556096153998,"GB2-07":10.209508879490494,"GB2-08":28.782419778292013}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":61.49707000105604,"none":34.277219106640516},"reasoning_agg":{"medium":{"max":80.07339356989996,"mean":61.49707000105604,"min":42.09636304029364},"none":{"max":54.77556096153998,"mean":34.277219106640516,"min":10.209508879490494}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":27.219850894415522}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-large-4-0:ef7199f81f1139d9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414000000001},"none":{"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":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"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":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.33846634,"mean":0.10613685812499998,"median":0.05239252,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.6981897300000002},"codegen_latency_ms":{"attempt_count":23,"max_ms":2372746,"mean_ms":755436.1875,"min_ms":27078,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2372746,"mean_ms":1420193.375,"min_ms":412995,"run_count":8},"none":{"attempt_count":13,"max_ms":165291,"mean_ms":90679.0,"min_ms":27078,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":159550,"output_mean":46908.8125,"output_min":3069,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":159550,"output_mean":88125.0,"output_min":32501,"run_count":8},"none":{"attempt_count":13,"output_max":9287,"output_mean":5692.625,"output_min":3069,"run_count":8}},"display_name":"Mistral Large 4","economics":{"highest":57.841358407878914,"none":40.81686237533449},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[262144],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":25,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[262144],"total_output_tokens":750541,"total_reasoning_output_tokens":655796,"total_visible_output_tokens":94745,"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":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":47.23089979362314,"score":47.23089979362314},"GB2-02":{"attempts":2,"playable":54.18113829421843,"score":54.18113829421843},"GB2-03":{"attempts":2,"playable":36.854622629259154,"score":36.854622629259154},"GB2-04":{"attempts":2,"playable":52.18355732223087,"score":52.18355732223087},"GB2-05":{"attempts":2,"playable":56.879443183738346,"score":56.879443183738346},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":80.08408298067621,"score":40.04204149033811},"GB2-07":{"attempts":2,"playable":44.59531884707436,"score":44.59531884707436},"GB2-08":{"attempts":2,"playable":42.25743038470395,"score":42.25743038470395}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":34.6685875088884,"score":34.6685875088884},"GB2-02":{"attempts":1,"playable":65.30872126557126,"score":65.30872126557126},"GB2-03":{"attempts":1,"playable":43.172142648199575,"score":43.172142648199575},"GB2-04":{"attempts":1,"playable":65.44799547997252,"score":65.44799547997252},"GB2-05":{"attempts":1,"playable":50.175873740183604,"score":50.175873740183604},"GB2-06":{"attempts":1,"playable":80.08408298067621,"score":80.08408298067621},"GB2-07":{"attempts":1,"playable":79.52353910104367,"score":79.52353910104367},"GB2-08":{"attempts":1,"playable":44.3499245384961,"score":44.3499245384961}},"none":{"GB2-01":{"attempts":1,"playable":59.79321207835787,"score":59.79321207835787},"GB2-02":{"attempts":1,"playable":43.05355532286559,"score":43.05355532286559},"GB2-03":{"attempts":1,"playable":30.53710261031873,"score":30.53710261031873},"GB2-04":{"attempts":1,"playable":38.91911916448922,"score":38.91911916448922},"GB2-05":{"attempts":1,"playable":63.58301262729309,"score":63.58301262729309},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":9.667098593105054,"score":9.667098593105054},"GB2-08":{"attempts":1,"playable":40.16493623091181,"score":40.16493623091181}}},"id":"mistralai/mistral-large-4-0","is_recent_addition":false,"last_measured_at":"2026-10-22T10:44:36Z","match_totals_all":{"draws":2128,"losses":2682,"wins":2450},"match_totals_tracks":{"highest":{"draws":952,"losses":1213,"wins":1699},"none":{"draws":1176,"losses":1469,"wins":751}},"model_slug":"mistralai-mistral-large-4-0","overall":{"max":80.08408298067621,"mean":46.7780564931483,"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":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":34.6685875088884,"GB2-02":65.30872126557126,"GB2-03":43.172142648199575,"GB2-04":65.44799547997252,"GB2-05":50.175873740183604,"GB2-06":80.08408298067621,"GB2-07":79.52353910104367,"GB2-08":44.3499245384961},"per_game_match_totals_all":{"GB2-01":{"draws":122,"losses":467,"wins":387},"GB2-02":{"draws":622,"losses":116,"wins":172},"GB2-03":{"draws":329,"losses":458,"wins":149},"GB2-04":{"draws":505,"losses":211,"wins":228},"GB2-05":{"draws":0,"losses":444,"wins":570},"GB2-06":{"draws":35,"losses":81,"wins":360},"GB2-07":{"draws":0,"losses":554,"wins":430},"GB2-08":{"draws":515,"losses":351,"wins":154}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":22,"losses":315,"wins":151},"GB2-02":{"draws":247,"losses":38,"wins":169},"GB2-03":{"draws":170,"losses":198,"wins":100},"GB2-04":{"draws":222,"losses":58,"wins":192},"GB2-05":{"draws":0,"losses":255,"wins":249},"GB2-06":{"draws":35,"losses":81,"wins":360},"GB2-07":{"draws":0,"losses":102,"wins":390},"GB2-08":{"draws":256,"losses":166,"wins":88}},"none":{"GB2-01":{"draws":100,"losses":152,"wins":236},"GB2-02":{"draws":375,"losses":78,"wins":3},"GB2-03":{"draws":159,"losses":260,"wins":49},"GB2-04":{"draws":283,"losses":153,"wins":36},"GB2-05":{"draws":0,"losses":189,"wins":321},"GB2-07":{"draws":0,"losses":452,"wins":40},"GB2-08":{"draws":259,"losses":185,"wins":66}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1322.188227982663,"GB2-02":1599.7732135694462,"GB2-03":1372.7039504433058,"GB2-04":1604.155315197628,"GB2-05":1441.9458059936458,"GB2-06":1952.4777368051978,"GB2-07":1884.7314743530935,"GB2-08":1344.035186235791},"none":{"GB2-01":1565.9805749263687,"GB2-02":1421.1133630739055,"GB2-03":1259.4824521669404,"GB2-04":1391.8425545564633,"GB2-05":1617.1120942303528,"GB2-07":826.7509142411009,"GB2-08":1300.4380522593685}},"per_game_tracks":{"highest":{"GB2-01":34.6685875088884,"GB2-02":65.30872126557126,"GB2-03":43.172142648199575,"GB2-04":65.44799547997252,"GB2-05":50.175873740183604,"GB2-06":80.08408298067621,"GB2-07":79.52353910104367,"GB2-08":44.3499245384961},"none":{"GB2-01":59.79321207835787,"GB2-02":43.05355532286559,"GB2-03":30.53710261031873,"GB2-04":38.91911916448922,"GB2-05":63.58301262729309,"GB2-07":9.667098593105054,"GB2-08":40.16493623091181}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":57.841358407878914,"none":35.714754578417676},"reasoning_agg":{"highest":{"max":80.08408298067621,"mean":57.841358407878914,"min":34.6685875088884},"none":{"max":63.58301262729309,"mean":35.714754578417676,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":22.12660382946124}},{"canonical_public_row_identity":"publication-row.v1:overall:elorian-glimpse:824fb74331f77be3","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.224169,"mean":0.1412031,"median":0.16102650000000002,"min":0.0567792,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.1296248000000002},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0395322,"mean":0.023054325,"median":0.0214521,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1844346}},"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":0.224169,"mean":0.1412031,"median":0.16102650000000002,"min":0.0567792,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.1296248},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0395322,"mean":0.023054325,"median":0.0214521,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1844346}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.224169,"mean":0.0821287125,"median":0.0481557,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.3140593999999999},"codegen_latency_ms":{"attempt_count":23,"max_ms":561371,"mean_ms":157083.3125,"min_ms":8331,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":10,"max_ms":561371,"mean_ms":286804.25,"min_ms":88263,"run_count":8},"none":{"attempt_count":13,"max_ms":43454,"mean_ms":27362.375,"min_ms":8331,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":73204,"output_mean":25017.0625,"output_min":2066,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":10,"output_max":73204,"output_mean":44953.5,"output_min":17269,"run_count":8},"none":{"attempt_count":13,"output_max":8678,"output_mean":5080.625,"output_min":2066,"run_count":8}},"display_name":"Glimpse","economics":{"medium":66.49238001648483,"none":31.131802771613174},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[235929],"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":[235929],"total_output_tokens":400273,"total_reasoning_output_tokens":316594,"total_visible_output_tokens":83679,"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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"elorian/glimpse","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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},"baseline":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-05","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":48.41968107090535,"score":48.41968107090535},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.481004076825855,"score":21.740502038412927},"GB2-03":{"attempts":2,"playable":45.462442657324274,"score":45.462442657324274},"GB2-04":{"attempts":2,"playable":47.81748643401262,"score":47.81748643401262},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":61.84290339910371,"score":30.921451699551856},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":86.23234211916532,"score":43.11617105958266},"GB2-07":{"attempts":2,"playable":46.50325171398081,"score":46.50325171398081},"GB2-08":{"attempts":2,"playable":59.81804032120176,"score":59.81804032120176}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":82.8523946777341,"score":82.8523946777341},"GB2-02":{"attempts":1,"playable":43.481004076825855,"score":43.481004076825855},"GB2-03":{"attempts":1,"playable":36.24947180443738,"score":36.24947180443738},"GB2-04":{"attempts":1,"playable":54.8790540693121,"score":54.8790540693121},"GB2-05":{"attempts":1,"playable":61.84290339910371,"score":61.84290339910371},"GB2-06":{"attempts":1,"playable":86.23234211916532,"score":86.23234211916532},"GB2-07":{"attempts":1,"playable":77.09587653777574,"score":77.09587653777574},"GB2-08":{"attempts":1,"playable":89.30599344752443,"score":89.30599344752443}},"none":{"GB2-01":{"attempts":1,"playable":13.986967464076603,"score":13.986967464076603},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":54.67541351021117,"score":54.67541351021117},"GB2-04":{"attempts":1,"playable":40.75591879871314,"score":40.75591879871314},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":15.910626890185881,"score":15.910626890185881},"GB2-08":{"attempts":1,"playable":30.33008719487908,"score":30.33008719487908}}},"id":"elorian/glimpse","is_recent_addition":false,"last_measured_at":"2026-10-22T11:01:23Z","match_totals_all":{"draws":754,"losses":1414,"wins":1374},"match_totals_tracks":{"medium":{"draws":536,"losses":479,"wins":1095},"none":{"draws":218,"losses":935,"wins":279}},"model_slug":"elorian-glimpse","overall":{"max":89.30599344752443,"mean":42.97487837437153,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":34,"losses":267,"wins":225},"GB2-02":{"draws":234,"losses":51,"wins":7},"GB2-03":{"draws":141,"losses":226,"wins":135},"GB2-04":{"draws":331,"losses":104,"wins":77},"GB2-05":{"draws":0,"losses":114,"wins":174},"GB2-06":{"draws":14,"losses":42,"wins":236},"GB2-07":{"draws":0,"losses":406,"wins":244},"GB2-08":{"draws":0,"losses":204,"wins":276}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":16,"losses":43,"wins":201},"GB2-02":{"draws":234,"losses":51,"wins":7},"GB2-03":{"draws":112,"losses":117,"wins":29},"GB2-04":{"draws":160,"losses":37,"wins":59},"GB2-05":{"draws":0,"losses":114,"wins":174},"GB2-06":{"draws":14,"losses":42,"wins":236},"GB2-07":{"draws":0,"losses":49,"wins":183},"GB2-08":{"draws":0,"losses":26,"wins":206}},"none":{"GB2-01":{"draws":18,"losses":224,"wins":24},"GB2-03":{"draws":29,"losses":109,"wins":106},"GB2-04":{"draws":171,"losses":67,"wins":18},"GB2-07":{"draws":0,"losses":357,"wins":61},"GB2-08":{"draws":0,"losses":178,"wins":70}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1844.8343914042882,"GB2-02":1424.4207566378134,"GB2-03":1311.9350181735313,"GB2-04":1516.0664704836915,"GB2-05":1592.7064579543924,"GB2-06":2083.2153242202776,"GB2-07":1837.5762032991306,"GB2-08":2115.497888342936},"none":{"GB2-01":1062.274452505305,"GB2-03":1474.1830362186136,"GB2-04":1406.3170901761475,"GB2-07":970.2760928243924,"GB2-08":1198.7906483108268}},"per_game_tracks":{"medium":{"GB2-01":82.8523946777341,"GB2-02":43.481004076825855,"GB2-03":36.24947180443738,"GB2-04":54.8790540693121,"GB2-05":61.84290339910371,"GB2-06":86.23234211916532,"GB2-07":77.09587653777574,"GB2-08":89.30599344752443},"none":{"GB2-01":13.986967464076603,"GB2-03":54.67541351021117,"GB2-04":40.75591879871314,"GB2-07":15.910626890185881,"GB2-08":30.33008719487908}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":66.49238001648483,"none":19.457376732258233},"reasoning_agg":{"medium":{"max":89.30599344752443,"mean":66.49238001648483,"min":36.24947180443738},"none":{"max":54.67541351021117,"mean":19.457376732258233,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":47.0350032842266}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:dd4ac46878e8b5a1","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-2026-10-09":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-2026-10-09":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-2026-10-09":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":42.28408561945078},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":61.56120900626328,"score":61.56120900626328},"GB2-02":{"attempts":1,"playable":42.893712908571246,"score":42.893712908571246},"GB2-03":{"attempts":1,"playable":39.32471098141292,"score":39.32471098141292},"GB2-04":{"attempts":1,"playable":38.49893347731976,"score":38.49893347731976},"GB2-05":{"attempts":1,"playable":14.2808925566424,"score":14.2808925566424},"GB2-06":{"attempts":1,"playable":50.89337951265252,"score":50.89337951265252},"GB2-07":{"attempts":1,"playable":47.87319556392104,"score":47.87319556392104},"GB2-08":{"attempts":1,"playable":42.94665094882307,"score":42.94665094882307}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":61.56120900626328,"score":61.56120900626328},"GB2-02":{"attempts":1,"playable":42.893712908571246,"score":42.893712908571246},"GB2-03":{"attempts":1,"playable":39.32471098141292,"score":39.32471098141292},"GB2-04":{"attempts":1,"playable":38.49893347731976,"score":38.49893347731976},"GB2-05":{"attempts":1,"playable":14.2808925566424,"score":14.2808925566424},"GB2-06":{"attempts":1,"playable":50.89337951265252,"score":50.89337951265252},"GB2-07":{"attempts":1,"playable":47.87319556392104,"score":47.87319556392104},"GB2-08":{"attempts":1,"playable":42.94665094882307,"score":42.94665094882307}}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-10-22T10:37:23Z","match_totals_all":{"draws":1093,"losses":1776,"wins":1024},"match_totals_tracks":{"none":{"draws":1093,"losses":1776,"wins":1024}},"model_slug":"gpt-4-1","overall":{"max":61.56120900626328,"mean":42.28408561945078,"min":14.2808925566424},"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":31,"losses":183,"wins":282},"GB2-02":{"draws":376,"losses":82,"wins":4},"GB2-03":{"draws":113,"losses":244,"wins":113},"GB2-04":{"draws":303,"losses":146,"wins":25},"GB2-05":{"draws":0,"losses":437,"wins":69},"GB2-06":{"draws":18,"losses":242,"wins":219},"GB2-07":{"draws":0,"losses":267,"wins":229},"GB2-08":{"draws":252,"losses":175,"wins":83}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":31,"losses":183,"wins":282},"GB2-02":{"draws":376,"losses":82,"wins":4},"GB2-03":{"draws":113,"losses":244,"wins":113},"GB2-04":{"draws":303,"losses":146,"wins":25},"GB2-05":{"draws":0,"losses":437,"wins":69},"GB2-06":{"draws":18,"losses":242,"wins":219},"GB2-07":{"draws":0,"losses":267,"wins":229},"GB2-08":{"draws":252,"losses":175,"wins":83}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1583.7638672766263,"GB2-02":1419.8754640454467,"GB2-03":1339.1450263764323,"GB2-04":1388.5069645304507,"GB2-05":898.1818566141469,"GB2-06":1441.0453846739608,"GB2-07":1422.2620857302963,"GB2-08":1329.2944296817107}},"per_game_tracks":{"none":{"GB2-01":61.56120900626328,"GB2-02":42.893712908571246,"GB2-03":39.32471098141292,"GB2-04":38.49893347731976,"GB2-05":14.2808925566424,"GB2-06":50.89337951265252,"GB2-07":47.87319556392104,"GB2-08":42.94665094882307}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":42.28408561945078},"reasoning_agg":{"none":{"max":61.56120900626328,"mean":42.28408561945078,"min":14.2808925566424}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:3646843bad82141b","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":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"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":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031540000002}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154},"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":47.57734467183152},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":7,"failed_game_aliases":["GB2-06"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03"],"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":6,"repaired_rate":0.8571428571428571}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":38.282659431067714,"score":38.282659431067714},"GB2-02":{"attempts":1,"playable":42.57830481215349,"score":42.57830481215349},"GB2-04":{"attempts":1,"playable":39.15634758358941,"score":39.15634758358941},"GB2-05":{"attempts":1,"playable":53.11076901883558,"score":53.11076901883558},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.67660638464773,"score":43.67660638464773},"GB2-08":{"attempts":1,"playable":68.65938080069517,"score":68.65938080069517}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":38.282659431067714,"score":38.282659431067714},"GB2-02":{"attempts":1,"playable":42.57830481215349,"score":42.57830481215349},"GB2-04":{"attempts":1,"playable":39.15634758358941,"score":39.15634758358941},"GB2-05":{"attempts":1,"playable":53.11076901883558,"score":53.11076901883558},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.67660638464773,"score":43.67660638464773},"GB2-08":{"attempts":1,"playable":68.65938080069517,"score":68.65938080069517}}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-10-22T09:53:11Z","match_totals_all":{"draws":680,"losses":1243,"wins":1014},"match_totals_tracks":{"medium":{"draws":680,"losses":1243,"wins":1014}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":68.65938080069517,"mean":40.78058114728416,"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","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":306,"wins":176},"GB2-02":{"draws":347,"losses":97,"wins":16},"GB2-04":{"draws":279,"losses":153,"wins":38},"GB2-05":{"draws":0,"losses":242,"wins":264},"GB2-07":{"draws":0,"losses":297,"wins":205},"GB2-08":{"draws":47,"losses":148,"wins":315}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":306,"wins":176},"GB2-02":{"draws":347,"losses":97,"wins":16},"GB2-04":{"draws":279,"losses":153,"wins":38},"GB2-05":{"draws":0,"losses":242,"wins":264},"GB2-07":{"draws":0,"losses":297,"wins":205},"GB2-08":{"draws":47,"losses":148,"wins":315}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1358.33616961167,"GB2-02":1417.4308518070254,"GB2-04":1393.7214277477976,"GB2-05":1478.6234394103278,"GB2-07":1370.1623293494656,"GB2-08":1658.3744692530477}},"per_game_tracks":{"medium":{"GB2-01":38.282659431067714,"GB2-02":42.57830481215349,"GB2-04":39.15634758358941,"GB2-05":53.11076901883558,"GB2-07":43.67660638464773,"GB2-08":68.65938080069517}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.78058114728416},"reasoning_agg":{"medium":{"max":68.65938080069517,"mean":40.78058114728416,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:921371e745cd1d84","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-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.0151682500000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"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-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.14705249999999997}},"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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.0151682500000003},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":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-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":22},"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-2026-10-09":22},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.1688104},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"medium":48.32991413130068,"none":30.349538283595596},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":52.008964775784314,"score":52.008964775784314},"GB2-02":{"attempts":2,"playable":41.96652665544258,"score":41.96652665544258},"GB2-03":{"attempts":2,"playable":45.10720556893856,"score":45.10720556893856},"GB2-04":{"attempts":2,"playable":43.51369518966905,"score":43.51369518966905},"GB2-05":{"attempts":2,"playable":29.160192584094304,"score":29.160192584094304},"GB2-06":{"attempts":2,"playable":39.15112304955206,"score":39.15112304955206},"GB2-07":{"attempts":2,"playable":26.29518503912152,"score":26.29518503912152},"GB2-08":{"attempts":2,"playable":37.51491679698274,"score":37.51491679698274}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":70.3516999888012,"score":70.3516999888012},"GB2-02":{"attempts":1,"playable":41.84577664223028,"score":41.84577664223028},"GB2-03":{"attempts":1,"playable":44.89040596659433,"score":44.89040596659433},"GB2-04":{"attempts":1,"playable":43.934323998849464,"score":43.934323998849464},"GB2-05":{"attempts":1,"playable":47.27875818160957,"score":47.27875818160957},"GB2-06":{"attempts":1,"playable":47.90646061957096,"score":47.90646061957096},"GB2-07":{"attempts":1,"playable":46.0639655117496,"score":46.0639655117496},"GB2-08":{"attempts":1,"playable":44.36792214100008,"score":44.36792214100008}},"none":{"GB2-01":{"attempts":1,"playable":33.66622956276743,"score":33.66622956276743},"GB2-02":{"attempts":1,"playable":42.08727666865489,"score":42.08727666865489},"GB2-03":{"attempts":1,"playable":45.32400517128279,"score":45.32400517128279},"GB2-04":{"attempts":1,"playable":43.09306638048864,"score":43.09306638048864},"GB2-05":{"attempts":1,"playable":11.041626986579038,"score":11.041626986579038},"GB2-06":{"attempts":1,"playable":30.39578547953317,"score":30.39578547953317},"GB2-07":{"attempts":1,"playable":6.526404566493438,"score":6.526404566493438},"GB2-08":{"attempts":1,"playable":30.661911452965395,"score":30.661911452965395}}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-10-22T10:42:27Z","match_totals_all":{"draws":2471,"losses":3602,"wins":1655},"match_totals_tracks":{"medium":{"draws":1041,"losses":1550,"wins":1275},"none":{"draws":1430,"losses":2052,"wins":380}},"model_slug":"gpt-5-4-mini","overall":{"max":70.3516999888012,"mean":39.33972620744814,"min":6.526404566493438},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":181,"losses":392,"wins":403},"GB2-02":{"draws":725,"losses":179,"wins":8},"GB2-03":{"draws":529,"losses":281,"wins":128},"GB2-04":{"draws":582,"losses":251,"wins":107},"GB2-05":{"draws":0,"losses":723,"wins":285},"GB2-06":{"draws":48,"losses":587,"wins":321},"GB2-07":{"draws":0,"losses":743,"wins":243},"GB2-08":{"draws":406,"losses":446,"wins":160}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":31,"losses":137,"wins":320},"GB2-02":{"draws":354,"losses":95,"wins":7},"GB2-03":{"draws":164,"losses":192,"wins":114},"GB2-04":{"draws":306,"losses":116,"wins":48},"GB2-05":{"draws":0,"losses":271,"wins":233},"GB2-06":{"draws":33,"losses":247,"wins":198},"GB2-07":{"draws":0,"losses":278,"wins":216},"GB2-08":{"draws":153,"losses":214,"wins":139}},"none":{"GB2-01":{"draws":150,"losses":255,"wins":83},"GB2-02":{"draws":371,"losses":84,"wins":1},"GB2-03":{"draws":365,"losses":89,"wins":14},"GB2-04":{"draws":276,"losses":135,"wins":59},"GB2-05":{"draws":0,"losses":452,"wins":52},"GB2-06":{"draws":15,"losses":340,"wins":123},"GB2-07":{"draws":0,"losses":465,"wins":27},"GB2-08":{"draws":253,"losses":232,"wins":21}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1677.8294799903783,"GB2-02":1411.7423119742184,"GB2-03":1387.6313429630118,"GB2-04":1431.0603522843971,"GB2-05":1405.9001034424807,"GB2-06":1394.6391170817485,"GB2-07":1399.7909636054642,"GB2-08":1344.225256636354},"none":{"GB2-01":1311.9374019710542,"GB2-02":1413.619518856603,"GB2-03":1391.3997036794408,"GB2-04":1424.5390749374496,"GB2-05":822.2047942498294,"GB2-06":1128.9101454039594,"GB2-07":726.199904499076,"GB2-08":1202.2941625205913}},"per_game_tracks":{"medium":{"GB2-01":70.3516999888012,"GB2-02":41.84577664223028,"GB2-03":44.89040596659433,"GB2-04":43.934323998849464,"GB2-05":47.27875818160957,"GB2-06":47.90646061957096,"GB2-07":46.0639655117496,"GB2-08":44.36792214100008},"none":{"GB2-01":33.66622956276743,"GB2-02":42.08727666865489,"GB2-03":45.32400517128279,"GB2-04":43.09306638048864,"GB2-05":11.041626986579038,"GB2-06":30.39578547953317,"GB2-07":6.526404566493438,"GB2-08":30.661911452965395}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":48.32991413130068,"none":30.349538283595596},"reasoning_agg":{"medium":{"max":70.3516999888012,"mean":48.32991413130068,"min":41.84577664223028},"none":{"max":45.32400517128279,"mean":30.349538283595596,"min":6.526404566493438}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":17.980375847705087}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:6d5125b7850c7bc8","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","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","max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"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":46.80641338931761,"none":35.075412687718455},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-02","GB2-03"],"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},"repaired_admitted":6,"repaired_rate":1.0},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":53.71017475499486,"score":53.71017475499486},"GB2-02":{"attempts":1,"playable":39.08177072821658,"score":39.08177072821658},"GB2-03":{"attempts":1,"playable":34.657471685175125,"score":34.657471685175125},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":48.553220215672845,"score":24.276610107836422},"GB2-05":{"attempts":2,"playable":22.345752481604478,"score":22.345752481604478},"GB2-06":{"attempts":2,"playable":52.6158018945196,"score":52.6158018945196},"GB2-07":{"attempts":2,"playable":45.24536375463754,"score":45.24536375463754},"GB2-08":{"attempts":2,"playable":28.119860374678673,"score":28.119860374678673}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":70.58318831117185,"score":70.58318831117185},"GB2-04":{"attempts":1,"playable":48.553220215672845,"score":48.553220215672845},"GB2-05":{"attempts":1,"playable":25.364447717222067,"score":25.364447717222067},"GB2-06":{"attempts":1,"playable":67.17991349434652,"score":67.17991349434652},"GB2-07":{"attempts":1,"playable":41.430734352143936,"score":41.430734352143936},"GB2-08":{"attempts":1,"playable":27.72697624534843,"score":27.72697624534843}},"none":{"GB2-01":{"attempts":1,"playable":36.83716119881787,"score":36.83716119881787},"GB2-02":{"attempts":1,"playable":39.08177072821658,"score":39.08177072821658},"GB2-03":{"attempts":1,"playable":34.657471685175125,"score":34.657471685175125},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":19.32705724598689,"score":19.32705724598689},"GB2-06":{"attempts":1,"playable":38.051690294692676,"score":38.051690294692676},"GB2-07":{"attempts":1,"playable":49.059993157131146,"score":49.059993157131146},"GB2-08":{"attempts":1,"playable":28.512744504008914,"score":28.512744504008914}}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-22T10:28:03Z","match_totals_all":{"draws":1426,"losses":3185,"wins":1745},"match_totals_tracks":{"medium":{"draws":567,"losses":1335,"wins":1046},"none":{"draws":859,"losses":1850,"wins":699}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":70.58318831117185,"mean":38.74869974553563,"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","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":184,"losses":369,"wins":423},"GB2-02":{"draws":307,"losses":131,"wins":20},"GB2-03":{"draws":177,"losses":236,"wins":61},"GB2-04":{"draws":238,"losses":131,"wins":105},"GB2-05":{"draws":0,"losses":791,"wins":219},"GB2-06":{"draws":19,"losses":468,"wins":469},"GB2-07":{"draws":0,"losses":569,"wins":425},"GB2-08":{"draws":501,"losses":490,"wins":23}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":59,"losses":117,"wins":312},"GB2-04":{"draws":238,"losses":131,"wins":105},"GB2-05":{"draws":0,"losses":382,"wins":124},"GB2-06":{"draws":13,"losses":158,"wins":307},"GB2-07":{"draws":0,"losses":303,"wins":191},"GB2-08":{"draws":257,"losses":244,"wins":7}},"none":{"GB2-01":{"draws":125,"losses":252,"wins":111},"GB2-02":{"draws":307,"losses":131,"wins":20},"GB2-03":{"draws":177,"losses":236,"wins":61},"GB2-05":{"draws":0,"losses":409,"wins":95},"GB2-06":{"draws":6,"losses":310,"wins":162},"GB2-07":{"draws":0,"losses":266,"wins":234},"GB2-08":{"draws":244,"losses":246,"wins":16}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1680.478566421156,"GB2-04":1466.72729111482,"GB2-05":1103.6489718813204,"GB2-06":1711.047243002766,"GB2-07":1342.215597775021,"GB2-08":1170.8891033851726},"none":{"GB2-01":1344.0143575046382,"GB2-02":1390.0958746719166,"GB2-03":1297.6194541528243,"GB2-05":999.1813011245586,"GB2-06":1244.4219648675462,"GB2-07":1437.037347228562,"GB2-08":1179.3983557443305}},"per_game_tracks":{"medium":{"GB2-01":70.58318831117185,"GB2-04":48.553220215672845,"GB2-05":25.364447717222067,"GB2-06":67.17991349434652,"GB2-07":41.430734352143936,"GB2-08":27.72697624534843},"none":{"GB2-01":36.83716119881787,"GB2-02":39.08177072821658,"GB2-03":34.657471685175125,"GB2-05":19.32705724598689,"GB2-06":38.051690294692676,"GB2-07":49.059993157131146,"GB2-08":28.512744504008914}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":46.80641338931761,"none":30.690986101753648},"reasoning_agg":{"medium":{"max":70.58318831117185,"mean":46.80641338931761,"min":25.364447717222067},"none":{"max":49.059993157131146,"mean":30.690986101753648,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.115427287563964}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:674d1207b51de1c7","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":0.7288237500000001},"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":0.18239874999999997}},"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":0.7288237499999999},"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":0.18239874999999997}},"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":45.14915657030839,"none":40.94149637661783},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.2275310855133,"score":42.2275310855133},"GB2-02":{"attempts":2,"playable":45.077830593618266,"score":45.077830593618266},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":29.482516981141504,"score":14.741258490570752},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.40091057883584,"score":21.70045528941792},"GB2-05":{"attempts":2,"playable":38.50337064046336,"score":38.50337064046336},"GB2-06":{"attempts":2,"playable":37.91879217425276,"score":37.91879217425276},"GB2-07":{"attempts":2,"playable":68.85733100239182,"score":68.85733100239182},"GB2-08":{"attempts":2,"playable":32.290716038013656,"score":32.290716038013656}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.24043994263751,"score":18.24043994263751},"GB2-02":{"attempts":1,"playable":44.329825714580906,"score":44.329825714580906},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.40091057883584,"score":43.40091057883584},"GB2-05":{"attempts":1,"playable":39.90288550174628,"score":39.90288550174628},"GB2-06":{"attempts":1,"playable":59.81169204735413,"score":59.81169204735413},"GB2-07":{"attempts":1,"playable":76.5793448492611,"score":76.5793448492611},"GB2-08":{"attempts":1,"playable":33.778997357743066,"score":33.778997357743066}},"none":{"GB2-01":{"attempts":1,"playable":66.21462222838909,"score":66.21462222838909},"GB2-02":{"attempts":1,"playable":45.825835472655626,"score":45.825835472655626},"GB2-03":{"attempts":1,"playable":29.482516981141504,"score":29.482516981141504},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":37.10385577918043,"score":37.10385577918043},"GB2-06":{"attempts":1,"playable":16.025892301151394,"score":16.025892301151394},"GB2-07":{"attempts":1,"playable":61.135317155522515,"score":61.135317155522515},"GB2-08":{"attempts":1,"playable":30.802434718284253,"score":30.802434718284253}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-10-22T09:54:22Z","match_totals_all":{"draws":1913,"losses":3030,"wins":1877},"match_totals_tracks":{"medium":{"draws":1003,"losses":1416,"wins":991},"none":{"draws":910,"losses":1614,"wins":886}},"model_slug":"qwen-qwen3-7-max","overall":{"max":76.5793448492611,"mean":37.66466066428022,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":215,"losses":473,"wins":296},"GB2-02":{"draws":668,"losses":182,"wins":66},"GB2-03":{"draws":184,"losses":255,"wins":33},"GB2-04":{"draws":254,"losses":148,"wins":72},"GB2-05":{"draws":0,"losses":631,"wins":381},"GB2-06":{"draws":51,"losses":590,"wins":315},"GB2-07":{"draws":0,"losses":320,"wins":674},"GB2-08":{"draws":541,"losses":431,"wins":40}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":69,"losses":371,"wins":48},"GB2-02":{"draws":355,"losses":84,"wins":21},"GB2-04":{"draws":254,"losses":148,"wins":72},"GB2-05":{"draws":0,"losses":308,"wins":198},"GB2-06":{"draws":48,"losses":180,"wins":250},"GB2-07":{"draws":0,"losses":121,"wins":377},"GB2-08":{"draws":277,"losses":204,"wins":25}},"none":{"GB2-01":{"draws":146,"losses":102,"wins":248},"GB2-02":{"draws":313,"losses":98,"wins":45},"GB2-03":{"draws":184,"losses":255,"wins":33},"GB2-05":{"draws":0,"losses":323,"wins":183},"GB2-06":{"draws":3,"losses":410,"wins":65},"GB2-07":{"draws":0,"losses":199,"wins":297},"GB2-08":{"draws":264,"losses":227,"wins":15}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1129.215871856405,"GB2-02":1430.977425300275,"GB2-04":1426.9272499535614,"GB2-05":1312.4904254368282,"GB2-06":1584.4955207550738,"GB2-07":1828.0850435804223,"GB2-08":1234.7943723845644},"none":{"GB2-01":1632.161561723039,"GB2-02":1442.5081402664598,"GB2-03":1249.3951199676512,"GB2-05":1275.5799820237717,"GB2-06":898.2019192560728,"GB2-07":1592.2722503064624,"GB2-08":1203.7748091647377}},"per_game_tracks":{"medium":{"GB2-01":18.24043994263751,"GB2-02":44.329825714580906,"GB2-04":43.40091057883584,"GB2-05":39.90288550174628,"GB2-06":59.81169204735413,"GB2-07":76.5793448492611,"GB2-08":33.778997357743066},"none":{"GB2-01":66.21462222838909,"GB2-02":45.825835472655626,"GB2-03":29.482516981141504,"GB2-05":37.10385577918043,"GB2-06":16.025892301151394,"GB2-07":61.135317155522515,"GB2-08":30.802434718284253}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.505511999019845,"none":35.8238093295406},"reasoning_agg":{"medium":{"max":76.5793448492611,"mean":39.505511999019845,"min":0.0},"none":{"max":66.21462222838909,"mean":35.8238093295406,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":3.681702669479243}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:3c2c213171454c60","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":0.48528459999999995}},"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":34.81980281471117},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":8,"repaired_rate":1.0}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":36.799365062359826,"score":36.799365062359826},"GB2-02":{"attempts":1,"playable":43.705069702328224,"score":43.705069702328224},"GB2-03":{"attempts":1,"playable":29.596546765854274,"score":29.596546765854274},"GB2-04":{"attempts":1,"playable":40.78381030795238,"score":40.78381030795238},"GB2-05":{"attempts":1,"playable":49.45918080802635,"score":49.45918080802635},"GB2-06":{"attempts":1,"playable":31.33446038977986,"score":31.33446038977986},"GB2-07":{"attempts":1,"playable":14.002238835750056,"score":14.002238835750056},"GB2-08":{"attempts":1,"playable":32.87775064563834,"score":32.87775064563834}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":36.799365062359826,"score":36.799365062359826},"GB2-02":{"attempts":1,"playable":43.705069702328224,"score":43.705069702328224},"GB2-03":{"attempts":1,"playable":29.596546765854274,"score":29.596546765854274},"GB2-04":{"attempts":1,"playable":40.78381030795238,"score":40.78381030795238},"GB2-05":{"attempts":1,"playable":49.45918080802635,"score":49.45918080802635},"GB2-06":{"attempts":1,"playable":31.33446038977986,"score":31.33446038977986},"GB2-07":{"attempts":1,"playable":14.002238835750056,"score":14.002238835750056},"GB2-08":{"attempts":1,"playable":32.87775064563834,"score":32.87775064563834}}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-10-22T09:08:10Z","match_totals_all":{"draws":1197,"losses":2023,"wins":678},"match_totals_tracks":{"medium":{"draws":1197,"losses":2023,"wins":678}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":49.45918080802635,"mean":34.81980281471117,"min":14.002238835750056},"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":97,"losses":272,"wins":125},"GB2-02":{"draws":368,"losses":79,"wins":9},"GB2-03":{"draws":134,"losses":281,"wins":61},"GB2-04":{"draws":320,"losses":124,"wins":26},"GB2-05":{"draws":0,"losses":262,"wins":242},"GB2-06":{"draws":4,"losses":346,"wins":132},"GB2-07":{"draws":0,"losses":441,"wins":61},"GB2-08":{"draws":274,"losses":218,"wins":22}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":97,"losses":272,"wins":125},"GB2-02":{"draws":368,"losses":79,"wins":9},"GB2-03":{"draws":134,"losses":281,"wins":61},"GB2-04":{"draws":320,"losses":124,"wins":26},"GB2-05":{"draws":0,"losses":262,"wins":242},"GB2-06":{"draws":4,"losses":346,"wins":132},"GB2-07":{"draws":0,"losses":441,"wins":61},"GB2-08":{"draws":274,"losses":218,"wins":22}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1343.637634201086,"GB2-02":1426.1528696403366,"GB2-03":1250.4934857991313,"GB2-04":1406.5356961099253,"GB2-05":1433.0278966265723,"GB2-06":1143.0989029135742,"GB2-07":931.391629204627,"GB2-08":1225.461186909474}},"per_game_tracks":{"medium":{"GB2-01":36.799365062359826,"GB2-02":43.705069702328224,"GB2-03":29.596546765854274,"GB2-04":40.78381030795238,"GB2-05":49.45918080802635,"GB2-06":31.33446038977986,"GB2-07":14.002238835750056,"GB2-08":32.87775064563834}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.81980281471117},"reasoning_agg":{"medium":{"max":49.45918080802635,"mean":34.81980281471117,"min":14.002238835750056}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-1-flash:5d9cd3676d9346a0","codegen_cost_by_reasoning":{"medium":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":2,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":3,"run_count":2,"total":0.0},"codegen_latency_ms":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1}},"codegen_output_tokens":{"attempt_count":3,"output_max":32768,"output_mean":19502.5,"output_min":6237,"run_count":2},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":1,"output_max":32768,"output_mean":32768.0,"output_min":32768,"run_count":1},"none":{"attempt_count":2,"output_max":6237,"output_mean":6237.0,"output_min":6237,"run_count":1}},"display_name":"Ling 3.1 Flash","economics":{"none":33.59740038526684},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":3,"effective_max_output_tokens":[32768],"finish_reason_observations":2,"finish_reasons":["stop"],"indexed_attempts":3,"output_token_observations":3,"provider_post_attempt_observations":3,"provider_post_attempts":4,"reasoning_token_observations":3,"reconciliation_get_attempt_observations":3,"requested_max_output_token_observations":3,"requested_max_output_tokens":[32768],"total_output_tokens":39005,"total_reasoning_output_tokens":30791,"total_visible_output_tokens":8214,"visible_token_observations":3},"generation_policy":{"generation_policy":"quality_generation_policy","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":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.1-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-08":{"admitted":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}}},"headline_games_all":{"GB2-08":{"attempts":1,"playable":33.59740038526684,"score":33.59740038526684}},"headline_games_tracks":{"none":{"GB2-08":{"attempts":1,"playable":33.59740038526684,"score":33.59740038526684}}},"id":"inclusionai/ling-3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T04:24:46Z","match_totals_all":{"draws":287,"losses":202,"wins":19},"match_totals_tracks":{"none":{"draws":287,"losses":202,"wins":19}},"model_slug":"inclusionai-ling-3-1-flash","overall":{"max":33.59740038526684,"mean":33.59740038526684,"min":33.59740038526684},"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":287,"losses":202,"wins":19}},"per_game_match_totals_tracks":{"none":{"GB2-08":{"draws":287,"losses":202,"wins":19}}},"per_game_raw_elo_tracks":{"none":{"GB2-08":1232.917024774592}},"per_game_tracks":{"none":{"GB2-08":33.59740038526684}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":33.59740038526684},"reasoning_agg":{"none":{"max":33.59740038526684,"mean":33.59740038526684,"min":33.59740038526684}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{"baseline":"none"}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:6d33adc12e3afcbf","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":2,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917795999999999},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"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":0.04176385999999999}},"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":4,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999998},"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":34.589171475613554,"none":39.69795319929934},"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":"poolside","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":13,"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.5833333333333334,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"infra_failures_excluded":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.08333333333333333,"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},"performance_rejected_game_aliases":["GB2-07"],"performance_rejections":1,"repaired_admitted":4,"repaired_rate":0.3333333333333333},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"infra_failures_excluded":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":45.605468957567616,"score":35.346741645950786},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":41.88340073337104,"score":31.695994526671736},"GB2-03":{"attempts":4,"playable":38.77465322486485,"score":38.77465322486485},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":39.8497933686054,"score":19.9248966843027},"GB2-05":{"attempts":4,"playable":38.2333546648218,"score":38.2333546648218},"GB2-06":{"attempts":2,"playable":20.11529471930411,"score":20.11529471930411},"GB2-07":{"attempts":2,"playable":45.285573556682905,"score":45.285573556682905},"GB2-08":{"attempts":4,"playable":32.82508059962158,"score":32.82508059962158}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":41.03490924646731,"score":20.517454623233654},"GB2-02":{"attempts":2,"playable":43.017176639944864,"score":43.017176639944864},"GB2-03":{"attempts":2,"playable":38.07318734099815,"score":38.07318734099815},"GB2-04":{"attempts":1,"playable":39.8497933686054,"score":39.8497933686054},"GB2-05":{"attempts":2,"playable":27.878443704390342,"score":27.878443704390342},"GB2-06":{"attempts":1,"playable":19.577306107320886,"score":19.577306107320886},"GB2-08":{"attempts":2,"playable":32.69338392156793,"score":32.69338392156793}},"none":{"GB2-01":{"attempts":2,"playable":50.176028668667925,"score":50.176028668667925},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.749624826797216,"score":20.374812413398608},"GB2-03":{"attempts":2,"playable":39.476119108731545,"score":39.476119108731545},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":2,"playable":48.588265625253264,"score":48.588265625253264},"GB2-06":{"attempts":1,"playable":20.653283331287334,"score":20.653283331287334},"GB2-07":{"attempts":2,"playable":45.285573556682905,"score":45.285573556682905},"GB2-08":{"attempts":2,"playable":32.95677727767523,"score":32.95677727767523}}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-10-22T10:57:07Z","match_totals_all":{"draws":3259,"losses":5495,"wins":2428},"match_totals_tracks":{"medium":{"draws":1911,"losses":2614,"wins":797},"none":{"draws":1348,"losses":2881,"wins":1631}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":50.176028668667925,"mean":31.923482013574713,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":237,"losses":682,"wins":551},"GB2-02":{"draws":1085,"losses":267,"wins":16},"GB2-03":{"draws":635,"losses":892,"wins":349},"GB2-04":{"draws":283,"losses":152,"wins":43},"GB2-05":{"draws":0,"losses":1266,"wins":754},"GB2-06":{"draws":17,"losses":779,"wins":160},"GB2-07":{"draws":0,"losses":562,"wins":426},"GB2-08":{"draws":1002,"losses":895,"wins":129}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":80,"losses":256,"wins":154},"GB2-02":{"draws":755,"losses":155,"wins":2},"GB2-03":{"draws":300,"losses":461,"wins":177},"GB2-04":{"draws":283,"losses":152,"wins":43},"GB2-05":{"draws":0,"losses":739,"wins":273},"GB2-06":{"draws":6,"losses":393,"wins":79},"GB2-08":{"draws":487,"losses":458,"wins":69}},"none":{"GB2-01":{"draws":157,"losses":426,"wins":397},"GB2-02":{"draws":330,"losses":112,"wins":14},"GB2-03":{"draws":335,"losses":431,"wins":172},"GB2-05":{"draws":0,"losses":527,"wins":481},"GB2-06":{"draws":11,"losses":386,"wins":81},"GB2-07":{"draws":0,"losses":562,"wins":426},"GB2-08":{"draws":515,"losses":437,"wins":60}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1385.213881201149,"GB2-02":1420.8315378405016,"GB2-03":1327.8849867732233,"GB2-04":1399.196788273296,"GB2-05":1121.182988894871,"GB2-06":959.7303651060375,"GB2-08":1223.5465061006084},"none":{"GB2-01":1473.2283024131814,"GB2-02":1403.1962729431898,"GB2-03":1340.227113730683,"GB2-05":1435.1666288413705,"GB2-06":977.4620616358358,"GB2-07":1389.9406629198206,"GB2-08":1226.2808014754105}},"per_game_tracks":{"medium":{"GB2-01":41.03490924646731,"GB2-02":43.017176639944864,"GB2-03":38.07318734099815,"GB2-04":39.8497933686054,"GB2-05":27.878443704390342,"GB2-06":19.577306107320886,"GB2-08":32.69338392156793},"none":{"GB2-01":50.176028668667925,"GB2-02":40.749624826797216,"GB2-03":39.476119108731545,"GB2-05":48.588265625253264,"GB2-06":20.653283331287334,"GB2-07":45.285573556682905,"GB2-08":32.95677727767523}},"provider_color":"#4137FF","provider_company":"Poolside","provider_key":"poolside","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.65810652943732,"none":32.18885749771211},"reasoning_agg":{"medium":{"max":43.017176639944864,"mean":31.65810652943732,"min":19.577306107320886},"none":{"max":50.176028668667925,"mean":32.18885749771211,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":0.5307509682747877}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:c097ef34d61ea2e8","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586438999999994}},"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":41.91657066221126,"none":40.491286895098995},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1,"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":71.7294481003764,"score":71.7294481003764},"GB2-02":{"attempts":2,"playable":38.455039498751404,"score":38.455039498751404},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":31.873134087214027,"score":15.936567043607013},"GB2-04":{"attempts":2,"playable":46.16063677020533,"score":46.16063677020533},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":37.4839865321811,"score":22.492738291991632},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.91966930456381,"score":8.459834652281906},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":25.892328140609568,"score":12.946164070304784},"GB2-08":{"attempts":2,"playable":37.01018133532843,"score":37.01018133532843}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":64.82477488069512,"score":64.82477488069512},"GB2-02":{"attempts":1,"playable":39.05927888680072,"score":39.05927888680072},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":44.059306494167686,"score":44.059306494167686},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":59.96499296075787,"score":29.982496480378934},"GB2-06":{"attempts":1,"playable":16.91966930456381,"score":16.91966930456381},"GB2-07":{"attempts":1,"playable":25.892328140609568,"score":25.892328140609568},"GB2-08":{"attempts":1,"playable":42.69564396788402,"score":42.69564396788402}},"none":{"GB2-01":{"attempts":1,"playable":78.6341213200577,"score":78.6341213200577},"GB2-02":{"attempts":1,"playable":37.850800110702096,"score":37.850800110702096},"GB2-03":{"attempts":1,"playable":31.873134087214027,"score":31.873134087214027},"GB2-04":{"attempts":1,"playable":48.26196704624298,"score":48.26196704624298},"GB2-05":{"attempts":1,"playable":15.00298010360433,"score":15.00298010360433},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":31.32471870277285,"score":31.32471870277285}}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-10-22T10:26:33Z","match_totals_all":{"draws":1923,"losses":2850,"wins":1541},"match_totals_tracks":{"highest":{"draws":886,"losses":1587,"wins":935},"none":{"draws":1037,"losses":1263,"wins":606}},"model_slug":"tencent-hy3-preview","overall":{"max":78.6341213200577,"mean":31.648826220355865,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":64.82477488069512,"GB2-02":39.05927888680072,"GB2-04":44.059306494167686,"GB2-05":59.96499296075787,"GB2-06":16.91966930456381,"GB2-07":25.892328140609568,"GB2-08":42.69564396788402},"per_game_match_totals_all":{"GB2-01":{"draws":152,"losses":217,"wins":611},"GB2-02":{"draws":666,"losses":242,"wins":6},"GB2-03":{"draws":115,"losses":282,"wins":79},"GB2-04":{"draws":632,"losses":203,"wins":107},"GB2-05":{"draws":0,"losses":642,"wins":370},"GB2-06":{"draws":3,"losses":406,"wins":69},"GB2-07":{"draws":0,"losses":381,"wins":119},"GB2-08":{"draws":355,"losses":477,"wins":180}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":75,"losses":143,"wins":272},"GB2-02":{"draws":332,"losses":118,"wins":6},"GB2-04":{"draws":344,"losses":98,"wins":30},"GB2-05":{"draws":0,"losses":208,"wins":298},"GB2-06":{"draws":3,"losses":406,"wins":69},"GB2-07":{"draws":0,"losses":381,"wins":119},"GB2-08":{"draws":132,"losses":233,"wins":141}},"none":{"GB2-01":{"draws":77,"losses":74,"wins":339},"GB2-02":{"draws":334,"losses":124,"wins":0},"GB2-03":{"draws":115,"losses":282,"wins":79},"GB2-04":{"draws":288,"losses":105,"wins":77},"GB2-05":{"draws":0,"losses":434,"wins":72},"GB2-08":{"draws":223,"losses":244,"wins":39}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1617.427052910851,"GB2-02":1389.918275446847,"GB2-04":1432.0279425822428,"GB2-05":1567.1612212278908,"GB2-06":914.2141878528377,"GB2-07":1136.5244621909362,"GB2-08":1326.6727861194709},"none":{"GB2-01":1781.5292936316969,"GB2-02":1380.3337640497216,"GB2-03":1272.051522222666,"GB2-04":1464.4781465451413,"GB2-05":913.6960384190005,"GB2-08":1209.2629709964294}},"per_game_tracks":{"highest":{"GB2-01":64.82477488069512,"GB2-02":39.05927888680072,"GB2-04":44.059306494167686,"GB2-05":59.96499296075787,"GB2-06":16.91966930456381,"GB2-07":25.892328140609568,"GB2-08":42.69564396788402},"none":{"GB2-01":78.6341213200577,"GB2-02":37.850800110702096,"GB2-03":31.873134087214027,"GB2-04":48.26196704624298,"GB2-05":15.00298010360433,"GB2-08":31.32471870277285}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.929187269387484,"none":30.368465171324246},"reasoning_agg":{"highest":{"max":64.82477488069512,"mean":32.929187269387484,"min":0.0},"none":{"max":78.6341213200577,"mean":30.368465171324246,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":2.5607220980632377}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-5-super-vl:8749cefd23e794d7","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":0.017223799999999997,"mean":0.011684275,"median":0.01118885,"min":0.0072799,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0934742},"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":0.0053376,"mean":0.0035628175,"median":0.00344317,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.02850254}},"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":0.017223799999999997,"mean":0.011684275,"median":0.01118885,"min":0.0072799,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0934742},"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":0.0053376,"mean":0.0035628175,"median":0.00344317,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.02850254}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.017223799999999997,"mean":0.00762354625,"median":0.00630875,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":26,"run_count":16,"total":0.12197674},"codegen_latency_ms":{"attempt_count":26,"max_ms":256073,"mean_ms":74799.75,"min_ms":5868,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":256073,"mean_ms":129205.75,"min_ms":48724,"run_count":8},"none":{"attempt_count":15,"max_ms":35513,"mean_ms":20393.75,"min_ms":5868,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":39370,"output_mean":15837.375,"output_min":2130,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":39370,"output_mean":26486.125,"output_min":16576,"run_count":8},"none":{"attempt_count":15,"output_max":9122,"output_mean":5188.625,"output_min":2130,"run_count":8}},"display_name":"Nemotron 3.5 Super Vl","economics":{"medium":50.9875724115245,"none":32.0644119790418},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[235929],"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":[235929],"total_output_tokens":253398,"total_reasoning_output_tokens":186412,"total_visible_output_tokens":66986,"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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3.5-super-vl","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":69.63411021340255,"score":34.817055106701275},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.91780640658108,"score":22.45890320329054},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":35.94696101691349,"score":17.973480508456745},"GB2-04":{"attempts":2,"playable":41.77597385222211,"score":41.77597385222211},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":60.04748795062983,"score":30.023743975314915},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":48.405415157404406,"score":24.202707578702203},"GB2-07":{"attempts":2,"playable":40.703455313323836,"score":40.703455313323836},"GB2-08":{"attempts":2,"playable":40.09158807664911,"score":40.09158807664911}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":69.63411021340255,"score":69.63411021340255},"GB2-02":{"attempts":1,"playable":44.91780640658108,"score":44.91780640658108},"GB2-03":{"attempts":1,"playable":35.94696101691349,"score":35.94696101691349},"GB2-04":{"attempts":1,"playable":41.48587152420016,"score":41.48587152420016},"GB2-05":{"attempts":1,"playable":60.04748795062983,"score":60.04748795062983},"GB2-06":{"attempts":1,"playable":48.405415157404406,"score":48.405415157404406},"GB2-07":{"attempts":1,"playable":56.402246772468224,"score":56.402246772468224},"GB2-08":{"attempts":1,"playable":51.06068025059633,"score":51.06068025059633}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.06607618024405,"score":42.06607618024405},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":25.004663854179444,"score":25.004663854179444},"GB2-08":{"attempts":1,"playable":29.122495902701896,"score":29.122495902701896}}},"id":"nvidia/nemotron-3.5-super-vl","is_recent_addition":false,"last_measured_at":"2026-10-22T10:54:50Z","match_totals_all":{"draws":863,"losses":1422,"wins":995},"match_totals_tracks":{"medium":{"draws":679,"losses":1000,"wins":867},"none":{"draws":184,"losses":422,"wins":128}},"model_slug":"nvidia-nemotron-3-5-super-vl","overall":{"max":69.63411021340255,"mean":31.50586345183259,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":68,"wins":152},"GB2-02":{"draws":218,"losses":50,"wins":12},"GB2-03":{"draws":102,"losses":139,"wins":39},"GB2-04":{"draws":500,"losses":184,"wins":44},"GB2-05":{"draws":0,"losses":136,"wins":184},"GB2-06":{"draws":7,"losses":159,"wins":106},"GB2-07":{"draws":0,"losses":286,"wins":180},"GB2-08":{"draws":0,"losses":400,"wins":278}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":36,"losses":68,"wins":152},"GB2-02":{"draws":218,"losses":50,"wins":12},"GB2-03":{"draws":102,"losses":139,"wins":39},"GB2-04":{"draws":316,"losses":123,"wins":31},"GB2-05":{"draws":0,"losses":136,"wins":184},"GB2-06":{"draws":7,"losses":159,"wins":106},"GB2-07":{"draws":0,"losses":106,"wins":130},"GB2-08":{"draws":0,"losses":219,"wins":213}},"none":{"GB2-04":{"draws":184,"losses":61,"wins":13},"GB2-07":{"draws":0,"losses":180,"wins":50},"GB2-08":{"draws":0,"losses":181,"wins":65}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1669.6868089576803,"GB2-02":1435.5123475890236,"GB2-03":1309.2289474032711,"GB2-04":1412.0281731472876,"GB2-05":1568.268227204755,"GB2-06":1402.3513989158826,"GB2-07":1529.9411439386,"GB2-08":1417.4362126637666},"none":{"GB2-04":1416.5538465246755,"GB2-07":1123.429807782052,"GB2-08":1185.9465601273303}},"per_game_tracks":{"medium":{"GB2-01":69.63411021340255,"GB2-02":44.91780640658108,"GB2-03":35.94696101691349,"GB2-04":41.48587152420016,"GB2-05":60.04748795062983,"GB2-06":48.405415157404406,"GB2-07":56.402246772468224,"GB2-08":51.06068025059633},"none":{"GB2-04":42.06607618024405,"GB2-07":25.004663854179444,"GB2-08":29.122495902701896}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":50.9875724115245,"none":12.024154492140674},"reasoning_agg":{"medium":{"max":69.63411021340255,"mean":50.9875724115245,"min":35.94696101691349},"none":{"max":42.06607618024405,"mean":12.024154492140674,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":38.96341791938383}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:73868e1098c73c0e","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","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":1,"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":6,"max":0.005169185000000001,"mean":0.002871050658333333,"median":0.0023354879666666667,"min":0.0016912200000000002,"recorded_attempt_count":37,"run_count":24,"total":0.0689052158}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"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","max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.2141143316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00295601625,"mean":0.0023887339375,"median":0.002303478175,"min":0.0017364400000000001,"recorded_attempt_count":25,"run_count":16,"total":0.038219743},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.0306854728},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","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":7,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.0016912200000000002,"recorded_attempt_count":108,"run_count":56,"total":0.7524538072},"codegen_latency_ms":{"attempt_count":32,"max_ms":2480898,"mean_ms":755138.0,"min_ms":19112,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":20,"max_ms":2480898,"mean_ms":1257942.2222222222,"min_ms":113183,"run_count":9},"none":{"attempt_count":12,"max_ms":1141174,"mean_ms":189483.25,"min_ms":19112,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":131072,"output_mean":43207.23529411765,"output_min":1607,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":20,"output_max":131072,"output_mean":76516.0,"output_min":16030,"run_count":9},"none":{"attempt_count":12,"output_max":24962,"output_mean":5734.875,"output_min":1607,"run_count":8}},"display_name":"MiMo-V2.5","economics":{"all":35.64975322927834,"highest":36.98233109786115,"medium":31.872484920343688,"none":35.167336581149186},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.0625,"game_attempts":{"GB2-01":{"admitted":2,"infra_failures_excluded":1},"GB2-02":{"admitted":3},"GB2-03":{"infra_failures_excluded":3},"GB2-04":{"admitted":3},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":2},"GB2-07":{"admitted":2,"infra_failures_excluded":1},"GB2-08":{"admitted":2,"infra_failures_excluded":1,"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0625,"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":14,"repaired_rate":0.875},"baseline":{"admitted_plugins":17,"evaluated_cells":23,"failed_game_aliases":["GB2-02","GB2-03","GB2-07","GB2-08"],"first_pass_admitted":12,"first_pass_rate":0.5217391304347826,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":1,"model_code_failures":2},"GB2-03":{"admitted":1,"model_code_failures":2},"GB2-04":{"admitted":2,"infra_failures_excluded":1},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":2,"model_code_failures":1},"GB2-08":{"admitted":2,"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-04"],"infra_failures_excluded":1,"model_code_failure_rate":0.2608695652173913,"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":5,"repaired_rate":0.21739130434782608},"intensive":{"admitted_plugins":5,"evaluated_cells":5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"admitted":1},"GB2-07":{"infra_failures_excluded":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03","GB2-05","GB2-07"],"infra_failures_excluded":3,"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":5,"repaired_rate":1.0}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":31.8461217287134,"score":31.8461217287134},"GB2-02":{"attempts":7,"failed_attempts":2,"playable":42.71405863617085,"score":33.5805437765734},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.72087717287263,"score":14.906959057624212},"GB2-04":{"attempts":6,"playable":40.010892350241285,"score":40.010892350241285},"GB2-05":{"attempts":5,"playable":26.178457576191246,"score":26.178457576191246},"GB2-06":{"attempts":5,"playable":34.49886390488825,"score":34.49886390488825},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":25.890727905357565,"score":22.382909768655203},"GB2-08":{"attempts":7,"failed_attempts":2,"playable":30.918392852639773,"score":23.811603079142884}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":23.48782092204291,"score":23.48782092204291},"GB2-02":{"attempts":1,"playable":44.266008914915766,"score":44.266008914915766},"GB2-04":{"attempts":1,"playable":39.442210935890756,"score":39.442210935890756},"GB2-06":{"attempts":1,"playable":48.92154412000902,"score":48.92154412000902},"GB2-08":{"attempts":1,"playable":28.794070596447312,"score":28.794070596447312}},"medium":{"GB2-01":{"attempts":2,"playable":29.5065460086331,"score":29.5065460086331},"GB2-02":{"attempts":3,"playable":42.77535012540826,"score":42.77535012540826},"GB2-04":{"attempts":3,"playable":38.712689280186844,"score":38.712689280186844},"GB2-05":{"attempts":2,"playable":24.341297702797537,"score":24.341297702797537},"GB2-06":{"attempts":1,"playable":21.885162583124536,"score":21.885162583124536},"GB2-07":{"attempts":2,"playable":30.734546990500956,"score":30.734546990500956},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":34.83691274274844,"score":23.224608495165626}},"none":{"GB2-01":{"attempts":3,"playable":42.543998255464196,"score":42.543998255464196},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":41.10081686818851,"score":13.70027228939617},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.72087717287263,"score":14.906959057624212},"GB2-04":{"attempts":2,"playable":41.877776834646255,"score":41.877776834646255},"GB2-05":{"attempts":3,"playable":28.015617449584955,"score":28.015617449584955},"GB2-06":{"attempts":3,"playable":32.689885011531196,"score":32.689885011531196},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":21.046908820214178,"score":14.031272546809452},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":29.124195218723568,"score":19.41613014581571}}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-10-22T11:01:43Z","match_totals_all":{"draws":5388,"losses":9399,"wins":3141},"match_totals_tracks":{"highest":{"draws":1141,"losses":986,"wins":271},"medium":{"draws":2374,"losses":3744,"wins":1130},"none":{"draws":1873,"losses":4669,"wins":1740}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":48.92154412000902,"mean":31.01622340537419,"min":13.70027228939617},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":23.48782092204291,"GB2-02":44.266008914915766,"GB2-04":39.442210935890756,"GB2-06":48.92154412000902,"GB2-08":28.794070596447312},"per_game_all":{"GB2-01":31.26589872870864,"GB2-02":42.70102492115377,"GB2-04":40.12888906826042,"GB2-06":33.23456057562908,"GB2-08":30.918392852639773},"per_game_match_totals_all":{"GB2-01":{"draws":600,"losses":1651,"wins":685},"GB2-02":{"draws":1797,"losses":436,"wins":47},"GB2-03":{"draws":176,"losses":190,"wins":110},"GB2-04":{"draws":1755,"losses":849,"wins":216},"GB2-05":{"draws":0,"losses":1873,"wins":651},"GB2-06":{"draws":50,"losses":1621,"wins":721},"GB2-07":{"draws":0,"losses":1511,"wins":463},"GB2-08":{"draws":1010,"losses":1268,"wins":248}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":207,"losses":277,"wins":4},"GB2-02":{"draws":371,"losses":74,"wins":11},"GB2-04":{"draws":293,"losses":143,"wins":34},"GB2-06":{"draws":20,"losses":250,"wins":208},"GB2-08":{"draws":250,"losses":242,"wins":14}},"medium":{"GB2-01":{"draws":123,"losses":642,"wins":213},"GB2-02":{"draws":1076,"losses":263,"wins":31},"GB2-04":{"draws":882,"losses":439,"wins":89},"GB2-05":{"draws":0,"losses":770,"wins":238},"GB2-06":{"draws":18,"losses":379,"wins":83},"GB2-07":{"draws":0,"losses":712,"wins":278},"GB2-08":{"draws":275,"losses":539,"wins":198}},"none":{"GB2-01":{"draws":270,"losses":732,"wins":468},"GB2-02":{"draws":350,"losses":99,"wins":5},"GB2-03":{"draws":176,"losses":190,"wins":110},"GB2-04":{"draws":580,"losses":267,"wins":93},"GB2-05":{"draws":0,"losses":1103,"wins":413},"GB2-06":{"draws":12,"losses":992,"wins":430},"GB2-07":{"draws":0,"losses":799,"wins":185},"GB2-08":{"draws":485,"losses":487,"wins":36}}},"per_game_raw_elo_all":{"GB2-01":1282.5965437033192,"GB2-02":1418.3564035305237,"GB2-04":1401.346808347301,"GB2-06":1170.3386909467529,"GB2-08":1202.6762986724236},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1198.6885278648788,"GB2-02":1430.4849218357097,"GB2-04":1395.9815233745207,"GB2-06":1410.3447670624153,"GB2-08":1182.425213008918},"medium":{"GB2-01":1267.309073328102,"GB2-02":1418.6451181197688,"GB2-04":1392.9743571105466,"GB2-05":1085.0459817911878,"GB2-06":997.3886767867716,"GB2-07":1200.0916462682908,"GB2-08":1240.4767183115841},"none":{"GB2-01":1381.7920299169766,"GB2-02":1405.9391706360932,"GB2-03":1386.1583530379332,"GB2-04":1415.0845445568352,"GB2-05":1198.3560104276967,"GB2-06":1103.2826289910718,"GB2-07":1043.6513369947759,"GB2-08":1185.1269646967687}},"per_game_tracks":{"highest":{"GB2-01":23.48782092204291,"GB2-02":44.266008914915766,"GB2-04":39.442210935890756,"GB2-06":48.92154412000902,"GB2-08":28.794070596447312},"medium":{"GB2-01":29.5065460086331,"GB2-02":42.736248980357026,"GB2-04":39.06667943424425,"GB2-05":24.341297702797537,"GB2-06":21.885162583124536,"GB2-07":30.734546990500956,"GB2-08":34.83691274274844},"none":{"GB2-01":40.80332925544991,"GB2-02":41.10081686818851,"GB2-03":44.72087717287263,"GB2-04":41.877776834646255,"GB2-05":33.767813455344736,"GB2-06":28.896975023753704,"GB2-07":21.046908820214178,"GB2-08":29.124195218723568}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":36.98233109786115,"medium":30.168600169402403,"none":25.89773894885902},"reasoning_agg":{"highest":{"max":48.92154412000902,"mean":36.98233109786115,"min":23.48782092204291},"medium":{"max":42.77535012540826,"mean":30.168600169402403,"min":21.885162583124536},"none":{"max":42.543998255464196,"mean":25.89773894885902,"min":13.70027228939617}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":11.08459214900213}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:3b34412be76c9325","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-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999},"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"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-2026-10-09":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-2026-10-09":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-2026-10-09":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544915},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":55},"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-2026-10-09":55},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821379},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":43.309042606018124,"none":34.80069338768311},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"model_code_failures":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"model_code_failures":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":2}},"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}},"headline_games_all":{"GB2-01":{"attempts":4,"playable":31.276579250217818,"score":31.276579250217818},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.193997746161,"score":30.228558625141634},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":34.404785661228175,"score":8.601196415307044},"GB2-04":{"attempts":4,"failed_attempts":3,"playable":51.66510923377455,"score":12.916277308443638},"GB2-05":{"attempts":4,"playable":29.507560933248108,"score":29.507560933248108},"GB2-06":{"attempts":4,"playable":50.87293707208532,"score":50.87293707208532},"GB2-07":{"attempts":4,"failed_attempts":1,"playable":28.25270173972333,"score":22.909505339989245},"GB2-08":{"attempts":4,"playable":50.24535178901739,"score":50.24535178901739}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"playable":15.863450757824838,"score":15.863450757824838},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.861756484077475,"score":19.930878242038737},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":51.66510923377455,"score":25.832554616887276},"GB2-05":{"attempts":2,"playable":50.63313450170234,"score":50.63313450170234},"GB2-06":{"attempts":2,"playable":60.131563205637946,"score":60.131563205637946},"GB2-07":{"attempts":2,"playable":35.13261788051032,"score":35.13261788051032},"GB2-08":{"attempts":2,"playable":49.8756661785994,"score":49.8756661785994}},"none":{"GB2-01":{"attempts":2,"playable":46.6897077426108,"score":46.6897077426108},"GB2-02":{"attempts":2,"playable":40.52623900824453,"score":40.52623900824453},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":34.404785661228175,"score":17.202392830614087},"GB2-04":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-05":{"attempts":2,"playable":8.381987364793883,"score":8.381987364793883},"GB2-06":{"attempts":2,"playable":41.61431093853269,"score":41.61431093853269},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":21.372785598936346,"score":10.686392799468173},"GB2-08":{"attempts":2,"playable":50.61503739943539,"score":50.61503739943539}}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-10-22T10:41:48Z","match_totals_all":{"draws":2232,"losses":6152,"wins":3314},"match_totals_tracks":{"medium":{"draws":934,"losses":2961,"wins":1977},"none":{"draws":1298,"losses":3191,"wins":1337}},"model_slug":"gpt-5-4-nano","overall":{"max":60.131563205637946,"mean":29.569745841681275,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":359,"losses":1188,"wins":407},"GB2-02":{"draws":1035,"losses":316,"wins":13},"GB2-03":{"draws":139,"losses":252,"wins":77},"GB2-04":{"draws":225,"losses":121,"wins":124},"GB2-05":{"draws":0,"losses":1436,"wins":586},"GB2-06":{"draws":35,"losses":968,"wins":909},"GB2-07":{"draws":0,"losses":1053,"wins":429},"GB2-08":{"draws":439,"losses":818,"wins":769}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":150,"losses":757,"wins":71},"GB2-02":{"draws":346,"losses":106,"wins":2},"GB2-04":{"draws":225,"losses":121,"wins":124},"GB2-05":{"draws":0,"losses":504,"wins":508},"GB2-06":{"draws":32,"losses":387,"wins":537},"GB2-07":{"draws":0,"losses":655,"wins":333},"GB2-08":{"draws":181,"losses":431,"wins":402}},"none":{"GB2-01":{"draws":209,"losses":431,"wins":336},"GB2-02":{"draws":689,"losses":210,"wins":11},"GB2-03":{"draws":139,"losses":252,"wins":77},"GB2-05":{"draws":0,"losses":932,"wins":78},"GB2-06":{"draws":3,"losses":581,"wins":372},"GB2-07":{"draws":0,"losses":398,"wins":96},"GB2-08":{"draws":258,"losses":387,"wins":367}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1053.7394484941315,"GB2-02":1396.2386846419465,"GB2-04":1490.8456141888394,"GB2-05":1490.5507420593622,"GB2-06":1590.7860098204096,"GB2-07":1209.868616498405,"GB2-08":1462.631237056311},"none":{"GB2-01":1439.2700845467216,"GB2-02":1401.4488484448261,"GB2-03":1295.3290997357526,"GB2-05":748.1427698112955,"GB2-06":1304.7283790174283,"GB2-07":1067.061497010683,"GB2-08":1457.2224605721926}},"per_game_tracks":{"medium":{"GB2-01":15.863450757824838,"GB2-02":39.861756484077475,"GB2-04":51.66510923377455,"GB2-05":50.63313450170234,"GB2-06":60.131563205637946,"GB2-07":35.13261788051032,"GB2-08":49.8756661785994},"none":{"GB2-01":46.6897077426108,"GB2-02":40.52623900824453,"GB2-03":34.404785661228175,"GB2-05":8.381987364793883,"GB2-06":41.61431093853269,"GB2-07":21.372785598936346,"GB2-08":50.61503739943539}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.174983172900106,"none":26.96450851046244},"reasoning_agg":{"medium":{"max":60.131563205637946,"mean":32.174983172900106,"min":0.0},"none":{"max":50.61503739943539,"mean":26.96450851046244,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":5.210474662437665}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:a35e565c531736ab","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.030739789999999996},"none":{"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":0.00371018,"mean":0.00186558375,"median":0.00131646,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.014924670000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.03073979},"historical-provider-setting-baseline":{"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":0.00371018,"mean":0.00186558375,"median":0.00131646,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.01492467}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0061656,"mean":0.0028540287500000002,"median":0.00232709,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"recorded_attempt_count":25,"run_count":16,"total":0.045664460000000004},"codegen_latency_ms":{"attempt_count":25,"max_ms":425398,"mean_ms":137358.0,"min_ms":22859,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":14,"max_ms":425398,"mean_ms":207893.5,"min_ms":65353,"run_count":8},"none":{"attempt_count":11,"max_ms":256957,"mean_ms":66822.5,"min_ms":22859,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":12120,"output_mean":4888.4375,"output_min":1108,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":14,"output_max":12120,"output_mean":7438.375,"output_min":3314,"run_count":8},"none":{"attempt_count":11,"output_max":4877,"output_mean":2338.5,"output_min":1108,"run_count":8}},"display_name":"Gemma 4 31B","economics":{"medium":38.100485817468154,"none":27.208128043711856},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[16384],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":26,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[16384],"total_output_tokens":78215,"total_reasoning_output_tokens":27437,"total_visible_output_tokens":50778,"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":16384,"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":22.04307570871336,"score":11.02153785435668},"GB2-02":{"attempts":2,"playable":41.92431814538726,"score":41.92431814538726},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":44.182492926352225,"score":22.091246463176113},"GB2-04":{"attempts":2,"playable":44.744394025578785,"score":44.744394025578785},"GB2-05":{"attempts":2,"playable":44.18287714142919,"score":44.18287714142919},"GB2-06":{"attempts":2,"playable":22.375253687977676,"score":22.375253687977676},"GB2-07":{"attempts":2,"playable":14.245209629342956,"score":14.245209629342956},"GB2-08":{"attempts":2,"playable":33.44149045375951,"score":33.44149045375951}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":22.04307570871336,"score":22.04307570871336},"GB2-02":{"attempts":1,"playable":43.56994700874741,"score":43.56994700874741},"GB2-03":{"attempts":1,"playable":44.182492926352225,"score":44.182492926352225},"GB2-04":{"attempts":1,"playable":43.16928725870067,"score":43.16928725870067},"GB2-05":{"attempts":1,"playable":72.09404935388896,"score":72.09404935388896},"GB2-06":{"attempts":1,"playable":27.892207095191736,"score":27.892207095191736},"GB2-07":{"attempts":1,"playable":18.058827623277516,"score":18.058827623277516},"GB2-08":{"attempts":1,"playable":33.79399956487334,"score":33.79399956487334}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":40.27868928202711,"score":40.27868928202711},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":46.3195007924569,"score":46.3195007924569},"GB2-05":{"attempts":1,"playable":16.271704928969406,"score":16.271704928969406},"GB2-06":{"attempts":1,"playable":16.858300280763615,"score":16.858300280763615},"GB2-07":{"attempts":1,"playable":10.431591635408395,"score":10.431591635408395},"GB2-08":{"attempts":1,"playable":33.08898134264568,"score":33.08898134264568}}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-10-22T09:54:24Z","match_totals_all":{"draws":2131,"losses":3563,"wins":1080},"match_totals_tracks":{"medium":{"draws":1205,"losses":1864,"wins":799},"none":{"draws":926,"losses":1699,"wins":281}},"model_slug":"google-gemma-4-31b-it","overall":{"max":72.09404935388896,"mean":29.253290925126024,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":124,"losses":324,"wins":40},"GB2-02":{"draws":711,"losses":189,"wins":14},"GB2-03":{"draws":106,"losses":224,"wins":138},"GB2-04":{"draws":604,"losses":228,"wins":108},"GB2-05":{"draws":0,"losses":571,"wins":437},"GB2-06":{"draws":37,"losses":745,"wins":170},"GB2-07":{"draws":0,"losses":866,"wins":124},"GB2-08":{"draws":549,"losses":416,"wins":49}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":124,"losses":324,"wins":40},"GB2-02":{"draws":359,"losses":84,"wins":11},"GB2-03":{"draws":106,"losses":224,"wins":138},"GB2-04":{"draws":308,"losses":119,"wins":43},"GB2-05":{"draws":0,"losses":146,"wins":358},"GB2-06":{"draws":35,"losses":340,"wins":101},"GB2-07":{"draws":0,"losses":418,"wins":80},"GB2-08":{"draws":273,"losses":209,"wins":28}},"none":{"GB2-02":{"draws":352,"losses":105,"wins":3},"GB2-04":{"draws":296,"losses":109,"wins":65},"GB2-05":{"draws":0,"losses":425,"wins":79},"GB2-06":{"draws":2,"losses":405,"wins":69},"GB2-07":{"draws":0,"losses":448,"wins":44},"GB2-08":{"draws":276,"losses":207,"wins":21}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1180.615012009787,"GB2-02":1425.1084441766795,"GB2-03":1381.4812800868292,"GB2-04":1425.1305877053778,"GB2-05":1752.1102268325108,"GB2-06":1090.9004175412945,"GB2-07":1010.5140994213637,"GB2-08":1234.9493980400944},"none":{"GB2-02":1399.5102135021048,"GB2-04":1449.489176103839,"GB2-05":939.989625821925,"GB2-06":913.1277935541874,"GB2-07":847.3725555697839,"GB2-08":1227.6524544869114}},"per_game_tracks":{"medium":{"GB2-01":22.04307570871336,"GB2-02":43.56994700874741,"GB2-03":44.182492926352225,"GB2-04":43.16928725870067,"GB2-05":72.09404935388896,"GB2-06":27.892207095191736,"GB2-07":18.058827623277516,"GB2-08":33.79399956487334},"none":{"GB2-02":40.27868928202711,"GB2-04":46.3195007924569,"GB2-05":16.271704928969406,"GB2-06":16.858300280763615,"GB2-07":10.431591635408395,"GB2-08":33.08898134264568}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.100485817468154,"none":20.406096032783893},"reasoning_agg":{"medium":{"max":72.09404935388896,"mean":38.100485817468154,"min":18.058827623277516},"none":{"max":46.3195007924569,"mean":20.406096032783893,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":17.69438978468426}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:ac7ced464d5aa42a","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":0.21404720400000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.21404720400000002}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.6004064599999996},"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":36.73073136399519,"none":35.149625387034604},"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":"meituan","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"model_code_failures":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"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}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":2,"playable":42.623812568554015,"score":21.311906284277008},"GB2-02":{"attempts":4,"failed_attempts":2,"playable":42.03395353642176,"score":21.01697676821088},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":37.67548549583146,"score":27.507515909312964},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":42.139572691552274,"score":30.689490916497355},"GB2-05":{"attempts":4,"playable":22.534479000183556,"score":22.534479000183556},"GB2-06":{"attempts":4,"playable":30.946456114495646,"score":30.946456114495646},"GB2-07":{"attempts":4,"playable":36.198501222405866,"score":36.198501222405866},"GB2-08":{"attempts":4,"playable":36.315706976954004,"score":36.315706976954004}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.56419816188643,"score":21.782099080943215},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":40.671878346073974,"score":20.335939173036987},"GB2-04":{"attempts":2,"playable":38.47881828288487,"score":38.47881828288487},"GB2-05":{"attempts":2,"playable":33.27543163354356,"score":33.27543163354356},"GB2-06":{"attempts":2,"playable":25.030592522790226,"score":25.030592522790226},"GB2-07":{"attempts":2,"playable":37.32572235732706,"score":37.32572235732706},"GB2-08":{"attempts":2,"playable":38.768478243460216,"score":38.768478243460216}},"none":{"GB2-01":{"attempts":2,"playable":42.623812568554015,"score":42.623812568554015},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.50370891095709,"score":20.251854455478544},"GB2-03":{"attempts":2,"playable":34.679092645588945,"score":34.679092645588945},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":45.800327100219675,"score":22.900163550109838},"GB2-05":{"attempts":2,"playable":11.79352636682355,"score":11.79352636682355},"GB2-06":{"attempts":2,"playable":36.86231970620106,"score":36.86231970620106},"GB2-07":{"attempts":2,"playable":35.071280087484666,"score":35.071280087484666},"GB2-08":{"attempts":2,"playable":33.8629357104478,"score":33.8629357104478}}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-10-22T10:35:42Z","match_totals_all":{"draws":2951,"losses":6996,"wins":2684},"match_totals_tracks":{"medium":{"draws":1275,"losses":3203,"wins":1351},"none":{"draws":1676,"losses":3793,"wins":1333}},"model_slug":"meituan-longcat-2-0","overall":{"max":42.623812568554015,"mean":28.315129149042157,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":234,"losses":457,"wins":287},"GB2-02":{"draws":734,"losses":173,"wins":3},"GB2-03":{"draws":421,"losses":726,"wins":259},"GB2-04":{"draws":792,"losses":455,"wins":164},"GB2-05":{"draws":0,"losses":1575,"wins":441},"GB2-06":{"draws":72,"losses":1342,"wins":498},"GB2-07":{"draws":0,"losses":1296,"wins":680},"GB2-08":{"draws":698,"losses":972,"wins":352}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":378,"losses":74,"wins":2},"GB2-03":{"draws":142,"losses":223,"wins":103},"GB2-04":{"draws":520,"losses":330,"wins":91},"GB2-05":{"draws":0,"losses":679,"wins":329},"GB2-06":{"draws":31,"losses":729,"wins":196},"GB2-07":{"draws":0,"losses":634,"wins":356},"GB2-08":{"draws":204,"losses":534,"wins":274}},"none":{"GB2-01":{"draws":234,"losses":457,"wins":287},"GB2-02":{"draws":356,"losses":99,"wins":1},"GB2-03":{"draws":279,"losses":503,"wins":156},"GB2-04":{"draws":272,"losses":125,"wins":73},"GB2-05":{"draws":0,"losses":896,"wins":112},"GB2-06":{"draws":41,"losses":613,"wins":302},"GB2-07":{"draws":0,"losses":662,"wins":324},"GB2-08":{"draws":494,"losses":438,"wins":78}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1425.064000370959,"GB2-03":1350.9356965400152,"GB2-04":1388.1868883266297,"GB2-05":1192.718635119355,"GB2-06":1046.4192868362395,"GB2-07":1258.1696157949395,"GB2-08":1287.9800499430935},"none":{"GB2-01":1400.5471912547166,"GB2-02":1401.2726393040914,"GB2-03":1296.2731737521794,"GB2-04":1445.4826083842695,"GB2-05":837.671825110967,"GB2-06":1226.8406835511832,"GB2-07":1259.8707407761635,"GB2-08":1235.6581586327497}},"per_game_tracks":{"medium":{"GB2-02":43.56419816188643,"GB2-03":40.671878346073974,"GB2-04":38.47881828288487,"GB2-05":33.27543163354356,"GB2-06":25.030592522790226,"GB2-07":37.32572235732706,"GB2-08":38.768478243460216},"none":{"GB2-01":42.623812568554015,"GB2-02":40.50370891095709,"GB2-03":34.679092645588945,"GB2-04":45.800327100219675,"GB2-05":11.79352636682355,"GB2-06":36.86231970620106,"GB2-07":35.071280087484666,"GB2-08":33.8629357104478}},"provider_color":"#29E154","provider_company":"Meituan","provider_key":"meituan","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.874635161748262,"none":29.75562313633605},"reasoning_agg":{"medium":{"max":38.768478243460216,"mean":26.874635161748262,"min":0.0},"none":{"max":42.623812568554015,"mean":29.75562313633605,"min":11.79352636682355}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":2.8809879745877893}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:4f8a822e4f118742","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":0.20304798000000004}},"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":0.20304798}},"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":27.269808806745406,"none":40.699585234517556},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":39.04004059149842,"score":39.04004059149842},"GB2-02":{"attempts":2,"playable":39.56764327262259,"score":39.56764327262259},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":40.06635133154271,"score":20.033175665771356},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.405347398165084,"score":20.202673699082542},"GB2-05":{"attempts":2,"playable":15.55007058571485,"score":15.55007058571485},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.80456079910004,"score":8.40228039955002},"GB2-07":{"attempts":2,"playable":33.059282855413116,"score":33.059282855413116},"GB2-08":{"attempts":2,"playable":41.6879194575087,"score":41.6879194575087}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.778745307637628,"score":18.778745307637628},"GB2-02":{"attempts":1,"playable":39.06599876160225,"score":39.06599876160225},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.405347398165084,"score":40.405347398165084},"GB2-05":{"attempts":1,"playable":2.2121534414203436,"score":2.2121534414203436},"GB2-06":{"attempts":1,"playable":16.80456079910004,"score":16.80456079910004},"GB2-07":{"attempts":1,"playable":42.23702616143087,"score":42.23702616143087},"GB2-08":{"attempts":1,"playable":31.38482977786162,"score":31.38482977786162}},"none":{"GB2-01":{"attempts":1,"playable":59.30133587535921,"score":59.30133587535921},"GB2-02":{"attempts":1,"playable":40.06928778364292,"score":40.06928778364292},"GB2-03":{"attempts":1,"playable":40.06635133154271,"score":40.06635133154271},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":28.887987730009357,"score":28.887987730009357},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.881539549395356,"score":23.881539549395356},"GB2-08":{"attempts":1,"playable":51.99100913715577,"score":51.99100913715577}}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-10-22T10:26:26Z","match_totals_all":{"draws":1471,"losses":3593,"wins":1280},"match_totals_tracks":{"medium":{"draws":922,"losses":2079,"wins":419},"none":{"draws":549,"losses":1514,"wins":861}},"model_slug":"minimax-minimax-m3","overall":{"max":59.30133587535921,"mean":27.1928858158952,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":101,"losses":557,"wins":320},"GB2-02":{"draws":693,"losses":217,"wins":4},"GB2-03":{"draws":100,"losses":245,"wins":123},"GB2-04":{"draws":310,"losses":137,"wins":33},"GB2-05":{"draws":0,"losses":862,"wins":150},"GB2-06":{"draws":4,"losses":406,"wins":68},"GB2-07":{"draws":0,"losses":689,"wins":307},"GB2-08":{"draws":263,"losses":480,"wins":275}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":22,"losses":391,"wins":77},"GB2-02":{"draws":344,"losses":113,"wins":1},"GB2-04":{"draws":310,"losses":137,"wins":33},"GB2-05":{"draws":0,"losses":500,"wins":8},"GB2-06":{"draws":4,"losses":406,"wins":68},"GB2-07":{"draws":0,"losses":298,"wins":200},"GB2-08":{"draws":242,"losses":234,"wins":32}},"none":{"GB2-01":{"draws":79,"losses":166,"wins":243},"GB2-02":{"draws":349,"losses":104,"wins":3},"GB2-03":{"draws":100,"losses":245,"wins":123},"GB2-05":{"draws":0,"losses":362,"wins":142},"GB2-07":{"draws":0,"losses":391,"wins":107},"GB2-08":{"draws":21,"losses":246,"wins":243}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1136.888820437685,"GB2-02":1389.9713395004376,"GB2-04":1403.5666238832239,"GB2-05":447.58785642004636,"GB2-06":912.174948429874,"GB2-07":1352.2637862787258,"GB2-08":1209.8931708090565},"none":{"GB2-01":1561.080520838179,"GB2-02":1397.8681058709558,"GB2-03":1345.6432656296265,"GB2-05":1158.8659536474051,"GB2-07":1106.5092161648377,"GB2-08":1428.128982549687}},"per_game_tracks":{"medium":{"GB2-01":18.778745307637628,"GB2-02":39.06599876160225,"GB2-04":40.405347398165084,"GB2-05":2.2121534414203436,"GB2-06":16.80456079910004,"GB2-07":42.23702616143087,"GB2-08":31.38482977786162},"none":{"GB2-01":59.30133587535921,"GB2-02":40.06928778364292,"GB2-03":40.06635133154271,"GB2-05":28.887987730009357,"GB2-07":23.881539549395356,"GB2-08":51.99100913715577}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":23.86108270590223,"none":30.524688925888167},"reasoning_agg":{"medium":{"max":42.23702616143087,"mean":23.86108270590223,"min":0.0},"none":{"max":59.30133587535921,"mean":30.524688925888167,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.663606219985937}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:6176a3e741e3127b","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":0.5409853360167188},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.3975426639832813}},"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":1.9385280000000003},"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":33.50757187778807,"none":26.44776777498774},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":12.45962527131149,"score":6.229812635655745},"GB2-02":{"attempts":2,"playable":42.86347351303362,"score":42.86347351303362},"GB2-03":{"attempts":2,"playable":36.27366948436212,"score":36.27366948436212},"GB2-04":{"attempts":2,"playable":36.863254899649974,"score":36.863254899649974},"GB2-05":{"attempts":2,"playable":25.439947397828767,"score":25.439947397828767},"GB2-06":{"attempts":2,"playable":22.254475126036414,"score":22.254475126036414},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":13.250469295806075,"score":6.625234647903038},"GB2-08":{"attempts":2,"playable":33.293821080245635,"score":33.293821080245635}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.57312539062483,"score":44.57312539062483},"GB2-03":{"attempts":1,"playable":38.44866092576753,"score":38.44866092576753},"GB2-04":{"attempts":1,"playable":39.73085653201643,"score":39.73085653201643},"GB2-05":{"attempts":1,"playable":37.94539058432547,"score":37.94539058432547},"GB2-06":{"attempts":1,"playable":26.76446637780745,"score":26.76446637780745},"GB2-07":{"attempts":1,"playable":13.250469295806075,"score":13.250469295806075},"GB2-08":{"attempts":1,"playable":33.84003403816865,"score":33.84003403816865}},"none":{"GB2-01":{"attempts":1,"playable":12.45962527131149,"score":12.45962527131149},"GB2-02":{"attempts":1,"playable":41.153821635442405,"score":41.153821635442405},"GB2-03":{"attempts":1,"playable":34.0986780429567,"score":34.0986780429567},"GB2-04":{"attempts":1,"playable":33.99565326728352,"score":33.99565326728352},"GB2-05":{"attempts":1,"playable":12.934504211332062,"score":12.934504211332062},"GB2-06":{"attempts":1,"playable":17.744483874265377,"score":17.744483874265377},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":32.74760812232262,"score":32.74760812232262}}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-10-22T11:01:24Z","match_totals_all":{"draws":2060,"losses":3837,"wins":871},"match_totals_tracks":{"highest":{"draws":1085,"losses":1782,"wins":527},"none":{"draws":975,"losses":2055,"wins":344}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":44.57312539062483,"mean":26.230461098089414,"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":null,"overall_ranking_status":"provisional","per_game":{"GB2-02":44.57312539062483,"GB2-03":38.44866092576753,"GB2-04":39.73085653201643,"GB2-05":37.94539058432547,"GB2-06":26.76446637780745,"GB2-07":13.250469295806075,"GB2-08":33.84003403816865},"per_game_match_totals_all":{"GB2-01":{"draws":45,"losses":411,"wins":34},"GB2-02":{"draws":724,"losses":171,"wins":19},"GB2-03":{"draws":234,"losses":510,"wins":192},"GB2-04":{"draws":532,"losses":339,"wins":69},"GB2-05":{"draws":0,"losses":762,"wins":250},"GB2-06":{"draws":17,"losses":760,"wins":179},"GB2-07":{"draws":0,"losses":440,"wins":58},"GB2-08":{"draws":508,"losses":444,"wins":70}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":363,"losses":77,"wins":18},"GB2-03":{"draws":128,"losses":240,"wins":100},"GB2-04":{"draws":311,"losses":133,"wins":26},"GB2-05":{"draws":0,"losses":318,"wins":188},"GB2-06":{"draws":15,"losses":357,"wins":106},"GB2-07":{"draws":0,"losses":440,"wins":58},"GB2-08":{"draws":268,"losses":217,"wins":31}},"none":{"GB2-01":{"draws":45,"losses":411,"wins":34},"GB2-02":{"draws":361,"losses":94,"wins":1},"GB2-03":{"draws":106,"losses":270,"wins":92},"GB2-04":{"draws":221,"losses":206,"wins":43},"GB2-05":{"draws":0,"losses":444,"wins":62},"GB2-06":{"draws":2,"losses":403,"wins":73},"GB2-08":{"draws":240,"losses":227,"wins":39}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1432.8545070469197,"GB2-03":1331.4417174777204,"GB2-04":1398.259385595957,"GB2-05":1286.7964095015573,"GB2-06":1073.6575750935533,"GB2-07":915.0803817684391,"GB2-08":1235.4250340622225},"none":{"GB2-01":1034.623837418859,"GB2-02":1406.3527349568858,"GB2-03":1292.5472221247132,"GB2-04":1351.9818402520982,"GB2-05":868.009636586203,"GB2-06":928.645464486557,"GB2-08":1224.1098493720804}},"per_game_tracks":{"highest":{"GB2-02":44.57312539062483,"GB2-03":38.44866092576753,"GB2-04":39.73085653201643,"GB2-05":37.94539058432547,"GB2-06":26.76446637780745,"GB2-07":13.250469295806075,"GB2-08":33.84003403816865},"none":{"GB2-01":12.45962527131149,"GB2-02":41.153821635442405,"GB2-03":34.0986780429567,"GB2-04":33.99565326728352,"GB2-05":12.934504211332062,"GB2-06":17.744483874265377,"GB2-08":32.74760812232262}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.319125393064557,"none":23.14179680311427},"reasoning_agg":{"highest":{"max":44.57312539062483,"mean":29.319125393064557,"min":0.0},"none":{"max":41.153821635442405,"mean":23.14179680311427,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":6.177328589950285}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:3dafa78aad15f07d","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":1,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","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":1,"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","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":1,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.4057992500000003},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":18.943157554104324,"none":36.21811851327803},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":6,"failed_game_aliases":["GB2-04"],"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02"],"infra_failures_excluded":2,"model_code_failure_rate":0.16666666666666666,"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":5,"repaired_rate":0.8333333333333334},"baseline":{"admitted_plugins":7,"evaluated_cells":7,"game_attempts":{"GB2-01":{"infra_failures_excluded":2},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"admitted":1,"infra_failures_excluded":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":1,"infra_failures_excluded":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1,"infra_failures_excluded":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":9,"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":7,"repaired_rate":1.0}},"headline_games_all":{"GB2-02":{"attempts":1,"playable":36.686260159940495,"score":36.686260159940495},"GB2-03":{"attempts":2,"playable":32.83574030534699,"score":32.83574030534699},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.97023877378501,"score":20.985119386892507},"GB2-05":{"attempts":2,"playable":21.043273639830726,"score":21.043273639830726},"GB2-06":{"attempts":2,"playable":12.957904860377141,"score":12.957904860377141},"GB2-07":{"attempts":2,"playable":44.140329435708395,"score":44.140329435708395},"GB2-08":{"attempts":2,"playable":23.815810973607903,"score":23.815810973607903}},"headline_games_tracks":{"medium":{"GB2-03":{"attempts":1,"playable":31.49086957501534,"score":31.49086957501534},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":11.516485107945453,"score":11.516485107945453},"GB2-06":{"attempts":1,"playable":15.62491270499384,"score":15.62491270499384},"GB2-07":{"attempts":1,"playable":23.34883555074003,"score":23.34883555074003},"GB2-08":{"attempts":1,"playable":12.734684831826948,"score":12.734684831826948}},"none":{"GB2-02":{"attempts":1,"playable":36.686260159940495,"score":36.686260159940495},"GB2-03":{"attempts":1,"playable":34.180611035678645,"score":34.180611035678645},"GB2-04":{"attempts":1,"playable":41.97023877378501,"score":41.97023877378501},"GB2-05":{"attempts":1,"playable":30.570062171716,"score":30.570062171716},"GB2-06":{"attempts":1,"playable":10.290897015760441,"score":10.290897015760441},"GB2-07":{"attempts":1,"playable":64.93182332067676,"score":64.93182332067676},"GB2-08":{"attempts":1,"playable":34.89693711538886,"score":34.89693711538886}}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-10-22T10:26:57Z","match_totals_all":{"draws":1354,"losses":3566,"wins":926},"match_totals_tracks":{"medium":{"draws":219,"losses":1921,"wins":310},"none":{"draws":1135,"losses":1645,"wins":616}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":64.93182332067676,"mean":26.002041570849148,"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","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-02":{"draws":311,"losses":139,"wins":6},"GB2-03":{"draws":380,"losses":467,"wins":89},"GB2-04":{"draws":347,"losses":106,"wins":21},"GB2-05":{"draws":0,"losses":805,"wins":207},"GB2-06":{"draws":24,"losses":837,"wins":95},"GB2-07":{"draws":0,"losses":566,"wins":424},"GB2-08":{"draws":292,"losses":646,"wins":84}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":159,"losses":254,"wins":55},"GB2-05":{"draws":0,"losses":451,"wins":55},"GB2-06":{"draws":18,"losses":404,"wins":56},"GB2-07":{"draws":0,"losses":387,"wins":105},"GB2-08":{"draws":42,"losses":425,"wins":39}},"none":{"GB2-02":{"draws":311,"losses":139,"wins":6},"GB2-03":{"draws":221,"losses":213,"wins":34},"GB2-04":{"draws":347,"losses":106,"wins":21},"GB2-05":{"draws":0,"losses":354,"wins":152},"GB2-06":{"draws":6,"losses":433,"wins":39},"GB2-07":{"draws":0,"losses":179,"wins":319},"GB2-08":{"draws":250,"losses":221,"wins":45}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1268.477593571664,"GB2-05":834.1285580384786,"GB2-06":890.8763516355275,"GB2-07":1098.3341801887643,"GB2-08":974.0465736598441},"none":{"GB2-02":1371.0103500437867,"GB2-03":1293.292622140549,"GB2-04":1415.8070777583723,"GB2-05":1184.004883509418,"GB2-06":780.886304478825,"GB2-07":1644.513413269539,"GB2-08":1246.3222384298285}},"per_game_tracks":{"medium":{"GB2-03":31.49086957501534,"GB2-05":11.516485107945453,"GB2-06":15.62491270499384,"GB2-07":23.34883555074003,"GB2-08":12.734684831826948},"none":{"GB2-02":36.686260159940495,"GB2-03":34.180611035678645,"GB2-04":41.97023877378501,"GB2-05":30.570062171716,"GB2-06":10.290897015760441,"GB2-07":64.93182332067676,"GB2-08":34.89693711538886}},"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":15.785964628420269,"none":36.21811851327803},"reasoning_agg":{"medium":{"max":31.49086957501534,"mean":15.785964628420269,"min":0.0},"none":{"max":64.93182332067676,"mean":36.21811851327803,"min":10.290897015760441}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":20.43215388485776}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:fe9fa4ea3efdb4dc","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":0.43500896},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896000000006},"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":44.32370846695221,"none":25.696067201873344},"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"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}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":34.6958612586714,"score":29.917770656380775},"GB2-02":{"attempts":2,"playable":41.26226389630145,"score":41.26226389630145},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.414206712472755,"score":21.707103356236377},"GB2-05":{"attempts":2,"playable":38.23010816046079,"score":38.23010816046079},"GB2-06":{"attempts":2,"playable":41.75151575836755,"score":41.75151575836755},"GB2-07":{"attempts":2,"playable":16.359911240027213,"score":16.359911240027213},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":32.10512667282373,"score":16.052563336411865}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":50.27936010818029,"score":50.27936010818029},"GB2-02":{"attempts":1,"playable":43.57914154988858,"score":43.57914154988858},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":44.37672054818504,"score":44.37672054818504},"GB2-06":{"attempts":1,"playable":71.00203207089135,"score":71.00203207089135},"GB2-07":{"attempts":1,"playable":24.599869851744245,"score":24.599869851744245},"GB2-08":{"attempts":1,"playable":32.10512667282373,"score":32.10512667282373}},"none":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":19.11236240916251,"score":9.556181204581256},"GB2-02":{"attempts":1,"playable":38.94538624271431,"score":38.94538624271431},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.414206712472755,"score":43.414206712472755},"GB2-05":{"attempts":1,"playable":32.08349577273654,"score":32.08349577273654},"GB2-06":{"attempts":1,"playable":12.50099944584376,"score":12.50099944584376},"GB2-07":{"attempts":1,"playable":8.119952628310179,"score":8.119952628310179},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-10-22T10:36:59Z","match_totals_all":{"draws":1522,"losses":3132,"wins":1193},"match_totals_tracks":{"medium":{"draws":757,"losses":1319,"wins":872},"none":{"draws":765,"losses":1813,"wins":321}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":71.00203207089135,"mean":25.660154550523252,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":186,"losses":561,"wins":235},"GB2-02":{"draws":717,"losses":190,"wins":7},"GB2-04":{"draws":319,"losses":112,"wins":40},"GB2-05":{"draws":0,"losses":636,"wins":378},"GB2-06":{"draws":25,"losses":562,"wins":371},"GB2-07":{"draws":0,"losses":849,"wins":145},"GB2-08":{"draws":275,"losses":222,"wins":17}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":81,"losses":209,"wins":198},"GB2-02":{"draws":379,"losses":75,"wins":4},"GB2-05":{"draws":0,"losses":287,"wins":221},"GB2-06":{"draws":22,"losses":137,"wins":321},"GB2-07":{"draws":0,"losses":389,"wins":111},"GB2-08":{"draws":275,"losses":222,"wins":17}},"none":{"GB2-01":{"draws":105,"losses":352,"wins":37},"GB2-02":{"draws":338,"losses":115,"wins":3},"GB2-04":{"draws":319,"losses":112,"wins":40},"GB2-05":{"draws":0,"losses":349,"wins":157},"GB2-06":{"draws":3,"losses":425,"wins":50},"GB2-07":{"draws":0,"losses":460,"wins":34}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1473.6333848986653,"GB2-02":1425.1795248959297,"GB2-05":1369.6017331591977,"GB2-06":1779.8797045546453,"GB2-07":1117.378626939297,"GB2-08":1217.4233432913832},"none":{"GB2-01":1141.5713371459353,"GB2-02":1389.0185429987218,"GB2-04":1427.0303480183572,"GB2-05":1206.022857875622,"GB2-06":829.9193853533882,"GB2-07":780.9729478205787}},"per_game_tracks":{"medium":{"GB2-01":50.27936010818029,"GB2-02":43.57914154988858,"GB2-05":44.37672054818504,"GB2-06":71.00203207089135,"GB2-07":24.599869851744245,"GB2-08":32.10512667282373},"none":{"GB2-01":19.11236240916251,"GB2-02":38.94538624271431,"GB2-04":43.414206712472755,"GB2-05":32.08349577273654,"GB2-06":12.50099944584376,"GB2-07":8.119952628310179}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.24278135021416,"none":18.07752775083235},"reasoning_agg":{"medium":{"max":71.00203207089135,"mean":33.24278135021416,"min":0.0},"none":{"max":43.414206712472755,"mean":18.07752775083235,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":15.16525359938181}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:89a8944edc0ab22a","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.00217964,"mean":0.000272455,"median":0.0,"min":0.0,"recorded_attempt_count":53,"run_count":17,"total":0.00653892},"none":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0010891599999999998,"mean":0.00013614499999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":43,"run_count":17,"total":0.0032674799999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00653892,"mean":0.00653892,"median":0.00653892,"min":0.00653892,"recorded_attempt_count":1,"run_count":1,"total":0.00653892},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","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-variant-1":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0032674799999999997,"mean":0.0032674799999999997,"median":0.0032674799999999997,"min":0.0032674799999999997,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":3,"run_count":1,"total":0.0032674799999999997},"historical-provider-setting-baseline-variant-2":{"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":17,"cell_count":16,"cost_basis_counts":{"provider_reported":96},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.00217964,"mean":0.00020429999999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":96,"run_count":34,"total":0.0098064},"codegen_latency_ms":{"attempt_count":96,"max_ms":410978,"mean_ms":155707.0,"min_ms":18717,"run_count":33},"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":43,"max_ms":90441,"mean_ms":48570.82352941176,"min_ms":18717,"run_count":17}},"codegen_output_tokens":{"attempt_count":96,"output_max":92074,"output_mean":32817.64705882353,"output_min":2036,"run_count":34},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":53,"output_max":92074,"output_mean":58883.76470588235,"output_min":20000,"run_count":17},"none":{"attempt_count":43,"output_max":17378,"output_mean":6751.529411764706,"output_min":2036,"run_count":17}},"display_name":"Ling 3.0 Flash","economics":{"medium":30.2314283970584,"none":31.6083516569095},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[32768],"finish_reason_observations":96,"finish_reasons":["length","stop","unknown"],"indexed_attempts":98,"output_token_observations":97,"provider_post_attempt_observations":4,"provider_post_attempts":5,"reasoning_token_observations":69,"reconciliation_get_attempt_observations":4,"requested_max_output_token_observations":4,"requested_max_output_tokens":[32768],"total_output_tokens":1115800,"total_reasoning_output_tokens":656294,"total_visible_output_tokens":120852,"visible_token_observations":59},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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":1,"first_pass_rate":0.16666666666666666,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"infra_failures_excluded":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"infra_failures_excluded":2}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":10,"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":5,"repaired_rate":0.8333333333333334},"baseline":{"admitted_plugins":11,"evaluated_cells":17,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.4117647058823529,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"model_code_failures":2},"GB2-06":{"admitted":2},"GB2-07":{"model_code_failures":2},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.35294117647058826,"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":0.23529411764705882}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":27.160978949973064,"score":27.160978949973064},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":39.03885999134337,"score":28.93813574565625},"GB2-03":{"attempts":2,"playable":28.67461091101103,"score":28.67461091101103},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":42.371773360977315,"score":31.202492027641615},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":3,"playable":14.152312648216006,"score":14.152312648216006},"GB2-07":{"attempts":4,"failed_attempts":2,"playable":35.59421257212087,"score":17.797106286060433},"GB2-08":{"attempts":3,"playable":31.294406040383105,"score":31.294406040383105}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":19.008550008016865,"score":19.008550008016865},"GB2-02":{"attempts":1,"playable":37.67482299993826,"score":37.67482299993826},"GB2-04":{"attempts":1,"playable":40.06642138861183,"score":40.06642138861183},"GB2-06":{"attempts":1,"playable":18.813135016604193,"score":18.813135016604193},"GB2-07":{"attempts":2,"playable":35.59421257212087,"score":35.59421257212087}},"none":{"GB2-01":{"attempts":2,"playable":35.313407891929266,"score":35.313407891929266},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.40289698274849,"score":20.201448491374244},"GB2-03":{"attempts":2,"playable":28.67461091101103,"score":28.67461091101103},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.6771253333428,"score":22.3385626666714},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":2,"playable":9.491490279827818,"score":9.491490279827818},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":3,"playable":31.294406040383105,"score":31.294406040383105}}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-10-22T10:29:08Z","match_totals_all":{"draws":2679,"losses":4526,"wins":979},"match_totals_tracks":{"medium":{"draws":780,"losses":1647,"wins":449},"none":{"draws":1899,"losses":2879,"wins":530}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":40.06642138861183,"mean":24.322834591104005,"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","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":304,"losses":893,"wins":267},"GB2-02":{"draws":675,"losses":231,"wins":4},"GB2-03":{"draws":293,"losses":548,"wins":95},"GB2-04":{"draws":669,"losses":218,"wins":53},"GB2-06":{"draws":9,"losses":1274,"wins":151},"GB2-07":{"draws":0,"losses":660,"wins":324},"GB2-08":{"draws":729,"losses":702,"wins":85}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":121,"losses":340,"wins":27},"GB2-02":{"draws":327,"losses":127,"wins":2},"GB2-04":{"draws":329,"losses":122,"wins":19},"GB2-06":{"draws":3,"losses":398,"wins":77},"GB2-07":{"draws":0,"losses":660,"wins":324}},"none":{"GB2-01":{"draws":183,"losses":553,"wins":240},"GB2-02":{"draws":348,"losses":104,"wins":2},"GB2-03":{"draws":293,"losses":548,"wins":95},"GB2-04":{"draws":340,"losses":96,"wins":34},"GB2-06":{"draws":6,"losses":876,"wins":74},"GB2-08":{"draws":729,"losses":702,"wins":85}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1140.1200695006742,"GB2-02":1378.930711007107,"GB2-04":1400.9024129360046,"GB2-06":946.9184568712385,"GB2-07":1268.286469796868},"none":{"GB2-01":1327.22570605612,"GB2-02":1400.483319192886,"GB2-03":1240.3992774844078,"GB2-04":1436.80702600874,"GB2-06":635.481577334894,"GB2-08":1206.7198650700986}},"per_game_tracks":{"medium":{"GB2-01":19.008550008016865,"GB2-02":37.67482299993826,"GB2-04":40.06642138861183,"GB2-06":18.813135016604193,"GB2-07":35.59421257212087},"none":{"GB2-01":35.313407891929266,"GB2-02":40.40289698274849,"GB2-03":28.67461091101103,"GB2-04":44.6771253333428,"GB2-06":9.491490279827818,"GB2-08":31.090578542597605}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.231428397058398,"none":18.41424078514961},"reasoning_agg":{"medium":{"max":40.06642138861183,"mean":30.231428397058398,"min":18.813135016604193},"none":{"max":35.313407891929266,"mean":18.41424078514961,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":11.817187611908789}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-5-pro:be93bdee78d767ea","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02555855,"mean":0.00555063125,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":11,"run_count":9,"total":0.04440505},"medium":{"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.020746485000000002,"mean":0.0054863575000000005,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":5},"recorded_attempt_count":12,"run_count":9,"total":0.043890860000000004},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007327775,"mean":0.0040270015625,"median":0.0034028549999999998,"min":0.0009412025,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":9,"total":0.033157215}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.020746485000000002,"mean":0.0054863575000000005,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":5},"recorded_attempt_count":11,"run_count":8,"total":0.043890860000000004},"historical-provider-setting-balanced-variant-2":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007327775,"mean":0.0041446518750000005,"median":0.0034028549999999998,"min":0.001882405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.033157215},"historical-provider-setting-baseline-variant-2":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"historical-provider-setting-intensive-variant-1":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02555855,"mean":0.00555063125,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":10,"run_count":8,"total":0.04440505},"historical-provider-setting-intensive-variant-2":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.02555855,"mean":0.0050213301041666675,"median":0.00152996375,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":38,"run_count":27,"total":0.12145312500000001},"codegen_latency_ms":{"attempt_count":23,"max_ms":2441104,"mean_ms":798480.3076923077,"min_ms":99802,"run_count":13},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":4,"max_ms":2441104,"mean_ms":2103669.0,"min_ms":1766234,"run_count":2},"medium":{"attempt_count":5,"max_ms":1803928,"mean_ms":1240602.3333333333,"min_ms":254972,"run_count":3},"none":{"attempt_count":14,"max_ms":535646,"mean_ms":306387.375,"min_ms":99802,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":170673,"output_mean":49682.0,"output_min":3766,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":91928,"output_mean":64861.0,"output_min":10319,"run_count":9},"medium":{"attempt_count":12,"output_max":170673,"output_mean":72901.44444444444,"output_min":9244,"run_count":9},"none":{"attempt_count":15,"output_max":20225,"output_mean":11283.555555555555,"output_min":3766,"run_count":9}},"display_name":"Nex N2.5 Pro","economics":{"highest":41.64762177370112,"none":36.474959746402575},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":38,"effective_max_output_tokens":[235929],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":40,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"requested_max_output_token_observations":38,"requested_max_output_tokens":[235929],"total_output_tokens":1341414,"total_reasoning_output_tokens":1137994,"total_visible_output_tokens":203420,"visible_token_observations":38},"generation_policy":{"generation_policy":"quality_generation_policy","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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2.5-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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"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":1,"evaluated_cells":2,"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"infra_failures_excluded":1},"GB2-07":{"admitted":1},"GB2-08":{"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.5,"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}}},"headline_games_all":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":39.273863757442115,"score":39.273863757442115},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":43.91610909152351,"score":21.958054545761755},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":2,"playable":37.48014909783397,"score":37.48014909783397},"GB2-08":{"attempts":1,"playable":29.397189714677847,"score":29.397189714677847}},"headline_games_tracks":{"highest":{"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":41.64762177370112,"score":41.64762177370112}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":39.273863757442115,"score":39.273863757442115},"GB2-03":{"attempts":1,"playable":43.91610909152351,"score":43.91610909152351},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":33.31267642196683,"score":33.31267642196683},"GB2-08":{"attempts":1,"playable":29.397189714677847,"score":29.397189714677847}}},"id":"nex-agi/nex-n2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-22T10:35:00Z","match_totals_all":{"draws":302,"losses":689,"wins":283},"match_totals_tracks":{"highest":{"draws":0,"losses":134,"wins":82},"none":{"draws":302,"losses":555,"wins":201}},"model_slug":"nex-agi-nex-n2-5-pro","overall":{"max":43.91610909152351,"mean":19.530645380025923,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-07":41.64762177370112},"per_game_match_totals_all":{"GB2-02":{"draws":214,"losses":74,"wins":0},"GB2-03":{"draws":88,"losses":118,"wins":64},"GB2-07":{"draws":0,"losses":299,"wins":145},"GB2-08":{"draws":0,"losses":198,"wins":74}},"per_game_match_totals_tracks":{"highest":{"GB2-07":{"draws":0,"losses":134,"wins":82}},"none":{"GB2-02":{"draws":214,"losses":74,"wins":0},"GB2-03":{"draws":88,"losses":118,"wins":64},"GB2-07":{"draws":0,"losses":165,"wins":63},"GB2-08":{"draws":0,"losses":198,"wins":74}}},"per_game_raw_elo_tracks":{"highest":{"GB2-07":1344.9205604679294},"none":{"GB2-02":1391.6115817237169,"GB2-03":1379.1673221764545,"GB2-07":1238.8085829512993,"GB2-08":1188.8820993467862}},"per_game_tracks":{"highest":{"GB2-07":41.64762177370112},"none":{"GB2-02":39.273863757442115,"GB2-03":43.91610909152351,"GB2-07":33.31267642196683,"GB2-08":29.397189714677847}},"provider_color":"#111827","provider_company":"Nex AGI","provider_key":"nex-agi","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.82381088685056,"none":18.237479873201288},"reasoning_agg":{"highest":{"max":41.64762177370112,"mean":20.82381088685056,"min":0.0},"none":{"max":43.91610909152351,"mean":18.237479873201288,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":2.5863310136492714}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:66d97deb60755939","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":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"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":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":9,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":30,"run_count":16,"total":0.0},"codegen_latency_ms":{"attempt_count":30,"max_ms":905283,"mean_ms":265606.6875,"min_ms":7507,"run_count":16},"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":15,"max_ms":59126,"mean_ms":22095.0,"min_ms":7507,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":52275,"output_mean":16877.75,"output_min":1148,"run_count":16},"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":15,"output_max":7281,"output_mean":3649.625,"output_min":1148,"run_count":8}},"display_name":"North Mini Code","economics":{"medium":31.464597180019876,"none":18.058320863817702},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":15,"effective_max_output_tokens":[64000],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":15,"provider_post_attempts":15,"reasoning_token_observations":15,"reconciliation_get_attempt_observations":15,"requested_max_output_token_observations":15,"requested_max_output_tokens":[64000],"total_output_tokens":270044,"total_visible_output_tokens":29197,"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":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"cohere","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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","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,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":22.070135853811088,"score":11.035067926905544},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.63036732210667,"score":20.815183661053336},"GB2-05":{"attempts":2,"playable":33.12474556363289,"score":33.12474556363289},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.99811477359857,"score":8.999057386799285},"GB2-07":{"attempts":2,"playable":16.035998664911958,"score":16.035998664911958},"GB2-08":{"attempts":2,"playable":31.471219632483162,"score":31.471219632483162}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":22.070135853811088,"score":22.070135853811088},"GB2-04":{"attempts":1,"playable":41.63036732210667,"score":41.63036732210667},"GB2-05":{"attempts":1,"playable":46.21542501522914,"score":46.21542501522914},"GB2-06":{"attempts":1,"playable":17.99811477359857,"score":17.99811477359857},"GB2-07":{"attempts":1,"playable":29.884910871200564,"score":29.884910871200564},"GB2-08":{"attempts":1,"playable":30.98862924417322,"score":30.98862924417322}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":20.03406611203665,"score":20.03406611203665},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":2.1870864586233547,"score":2.1870864586233547},"GB2-08":{"attempts":1,"playable":31.953810020793107,"score":31.953810020793107}}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":806,"losses":2903,"wins":731},"match_totals_tracks":{"medium":{"draws":523,"losses":1799,"wins":614},"none":{"draws":283,"losses":1104,"wins":117}},"model_slug":"cohere-north-mini-code","overall":{"max":46.21542501522914,"mean":15.185159104473271,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-03":{"draws":111,"losses":324,"wins":37},"GB2-04":{"draws":297,"losses":136,"wins":45},"GB2-05":{"draws":0,"losses":688,"wins":326},"GB2-06":{"draws":4,"losses":401,"wins":73},"GB2-07":{"draws":0,"losses":844,"wins":144},"GB2-08":{"draws":394,"losses":510,"wins":106}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":111,"losses":324,"wins":37},"GB2-04":{"draws":297,"losses":136,"wins":45},"GB2-05":{"draws":0,"losses":278,"wins":228},"GB2-06":{"draws":4,"losses":401,"wins":73},"GB2-07":{"draws":0,"losses":359,"wins":137},"GB2-08":{"draws":111,"losses":301,"wins":94}},"none":{"GB2-05":{"draws":0,"losses":410,"wins":98},"GB2-07":{"draws":0,"losses":485,"wins":7},"GB2-08":{"draws":283,"losses":209,"wins":12}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1172.5995345651875,"GB2-04":1413.1563367727215,"GB2-05":1392.640274998929,"GB2-06":933.0232066689356,"GB2-07":1192.908464055949,"GB2-08":1205.733994060175},"none":{"GB2-05":1012.1837518444809,"GB2-07":482.58923232130326,"GB2-08":1215.8445747177493}},"per_game_tracks":{"medium":{"GB2-03":22.070135853811088,"GB2-04":41.63036732210667,"GB2-05":46.21542501522914,"GB2-06":17.99811477359857,"GB2-07":29.884910871200564,"GB2-08":30.98862924417322},"none":{"GB2-05":20.03406611203665,"GB2-07":2.1870864586233547,"GB2-08":31.953810020793107}},"provider_color":"#FF7759","provider_company":"Cohere","provider_key":"cohere","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":23.598447885014906,"none":6.77187032393164},"reasoning_agg":{"medium":{"max":46.21542501522914,"mean":23.598447885014906,"min":0.0},"none":{"max":31.953810020793107,"mean":6.77187032393164,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.826577561083266}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:5bdc59de009e8b9b","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507}},"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507},"codegen_latency_ms":{"attempt_count":13,"max_ms":44784,"mean_ms":22388.5,"min_ms":11128,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":13,"max_ms":44784,"mean_ms":22388.5,"min_ms":11128,"run_count":8}},"codegen_output_tokens":{"attempt_count":13,"output_max":4341,"output_mean":2556.0,"output_min":1068,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":13,"output_max":4341,"output_mean":2556.0,"output_min":1068,"run_count":8}},"display_name":"GPT-4.1 Nano","economics":{"none":31.341232942750363},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":13,"effective_max_output_tokens":[32768],"finish_reason_observations":13,"finish_reasons":["stop"],"indexed_attempts":13,"output_token_observations":13,"provider_post_attempt_observations":13,"provider_post_attempts":13,"reasoning_token_observations":13,"reconciliation_get_attempt_observations":13,"requested_max_output_token_observations":13,"requested_max_output_tokens":[32768],"total_output_tokens":20448,"total_visible_output_tokens":20448,"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":"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":32768,"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":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.4099201747862,"score":41.4099201747862},"GB2-03":{"attempts":1,"playable":34.855114483611274,"score":34.855114483611274},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":17.75866416985362,"score":17.75866416985362},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.4099201747862,"score":41.4099201747862},"GB2-03":{"attempts":1,"playable":34.855114483611274,"score":34.855114483611274},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":17.75866416985362,"score":17.75866416985362},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-10-22T09:44:48Z","match_totals_all":{"draws":649,"losses":673,"wins":80},"match_totals_tracks":{"none":{"draws":649,"losses":673,"wins":80}},"model_slug":"gpt-4-1-nano","overall":{"max":41.4099201747862,"mean":11.752962353531386,"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-02":{"draws":360,"losses":95,"wins":3},"GB2-03":{"draws":283,"losses":179,"wins":6},"GB2-06":{"draws":6,"losses":399,"wins":71}},"per_game_match_totals_tracks":{"none":{"GB2-02":{"draws":360,"losses":95,"wins":3},"GB2-03":{"draws":283,"losses":179,"wins":6},"GB2-06":{"draws":6,"losses":399,"wins":71}}},"per_game_raw_elo_tracks":{"none":{"GB2-02":1408.3494433989129,"GB2-03":1299.4072128929402,"GB2-06":928.890930572036}},"per_game_tracks":{"none":{"GB2-02":41.4099201747862,"GB2-03":34.855114483611274,"GB2-06":17.75866416985362}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":11.752962353531386},"reasoning_agg":{"none":{"max":41.4099201747862,"mean":11.752962353531386,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"}}],"public_release_id":"gb2-20261022-b406d1207d31","rating_method":{"bootstrap_iterations":0,"first_player_advantage":true,"method":"bradley_terry_newton","reference_field":{"manifest_sha256":"f02ffdc046ccbb060241b53df78dedf7e60ba7d8e68807f11921754cf4f0345a","population_revision":"62c0f9ac87b4c843aacf3d3e0c418e498bb133c2c43cf3ae7fd93c0d1fef2ed0","rule":"model_balanced_common_field_v1","source":"frozen_manifest","version":"v1"}},"results_cut_id":"gb2-20261022-b406d1207d31","schema_version":2,"snapshot_id":"20261022_112737","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-10-22 11:27 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":27},"claude-fable-5":{"draws":20,"losses":95,"wins":17},"claude-fable-5-1":{"draws":5,"losses":140,"wins":3},"claude-haiku-5-5":{"draws":27,"losses":74,"wins":25},"claude-opus-4-5":{"draws":73,"losses":90,"wins":51},"claude-opus-4-8":{"draws":30,"losses":70,"wins":20},"claude-opus-5":{"draws":27,"losses":179,"wins":20},"claude-opus-5-5":{"draws":6,"losses":131,"wins":7},"claude-sonnet-5":{"draws":41,"losses":68,"wins":23},"claude-sonnet-5-5":{"draws":28,"losses":79,"wins":25},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":23},"deepseek/deepseek-v4-flash":{"draws":63,"losses":62,"wins":71},"deepseek/deepseek-v4-pro":{"draws":30,"losses":60,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":53,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":60,"wins":32},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":49,"wins":9},"elorian/glimpse":{"draws":9,"losses":18,"wins":13},"fireworks/ember-1":{"draws":40,"losses":68,"wins":24},"gemini-3.1-pro-preview":{"draws":36,"losses":58,"wins":38},"gemini-4-argon":{"draws":2,"losses":60,"wins":2},"google/gemini-3.1-flash-lite":{"draws":29,"losses":19,"wins":40},"google/gemini-3.5-flash":{"draws":37,"losses":82,"wins":47},"google/gemini-3.5-flash-lite":{"draws":78,"losses":74,"wins":82},"google/gemini-3.6-flash":{"draws":67,"losses":136,"wins":51},"google/gemini-3.8-flash":{"draws":30,"losses":79,"wins":23},"google/gemma-4-31b-it":{"draws":27,"losses":24,"wins":25},"gpt-4.1":{"draws":16,"losses":17,"wins":11},"gpt-4.1-nano":{"draws":8,"losses":4,"wins":4},"gpt-5":{"draws":35,"losses":43,"wins":38},"gpt-5.4":{"draws":31,"losses":70,"wins":27},"gpt-5.4-mini":{"draws":35,"losses":25,"wins":28},"gpt-5.4-nano":{"draws":30,"losses":48,"wins":54},"gpt-5.5":{"draws":47,"losses":54,"wins":21},"gpt-5.6-luna":{"draws":43,"losses":42,"wins":47},"gpt-5.6-sol":{"draws":22,"losses":95,"wins":15},"gpt-5.6-terra":{"draws":37,"losses":65,"wins":24},"gpt-6-astra":{"draws":6,"losses":118,"wins":8},"gpt-6-luna":{"draws":39,"losses":54,"wins":39},"gpt-6-sol":{"draws":15,"losses":102,"wins":15},"gpt-6.1-sol":{"draws":10,"losses":114,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":36,"losses":24,"wins":32},"inception/mercury-3":{"draws":11,"losses":20,"wins":9},"inclusionai/ling-3.0-flash":{"draws":39,"losses":16,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":41,"losses":41,"wins":62},"meta/muse-glimmer-30b":{"draws":46,"losses":33,"wins":37},"meta/muse-spark-1.2":{"draws":32,"losses":64,"wins":30},"meta/muse-spark-1.3":{"draws":29,"losses":81,"wins":22},"meta/muse-spark-open":{"draws":15,"losses":40,"wins":13},"meta/muse-wonder":{"draws":30,"losses":86,"wins":16},"minimax/minimax-m3":{"draws":20,"losses":15,"wins":35},"minimax/minimax-m3.1-flash":{"draws":17,"losses":34,"wins":21},"mistralai/mistral-large-4-0":{"draws":25,"losses":33,"wins":24},"mistralai/mistral-medium-3-5":{"draws":34,"losses":18,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":15,"wins":8},"moonshotai/kimi-k3":{"draws":36,"losses":60,"wins":30},"nex-agi/nex-n2-pro":{"draws":18,"losses":12,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":35,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":6,"wins":9},"o3":{"draws":40,"losses":88,"wins":56},"openai/gpt-oss-120b":{"draws":40,"losses":32,"wins":42},"poolside/laguna-s-2.1":{"draws":51,"losses":39,"wins":38},"qwen/qwen3.7-max":{"draws":26,"losses":27,"wins":23},"qwen/qwen3.7-plus":{"draws":22,"losses":20,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":66,"wins":25},"qwen/qwen3.8-27b":{"draws":23,"losses":48,"wins":23},"qwen/qwen3.8-flash":{"draws":30,"losses":39,"wins":19},"qwen/qwen3.8-max":{"draws":47,"losses":52,"wins":33},"qwen/qwen3.8-max-0902":{"draws":37,"losses":74,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":29,"wins":12},"stealth/ox-alpha":{"draws":102,"losses":251,"wins":87},"stealth/space-bunny-alpha":{"draws":35,"losses":38,"wins":31},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":38},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":23,"losses":23,"wins":26},"tencent/hy4-preview":{"draws":41,"losses":72,"wins":15},"thinkingmachines/inkling":{"draws":61,"losses":46,"wins":71},"thinkingmachines/inkling-small":{"draws":50,"losses":30,"wins":52},"unbiased/pareto-26.10":{"draws":2,"losses":30,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":15,"wins":14},"x-ai/grok-4.5":{"draws":30,"losses":84,"wins":18},"x-ai/grok-4.6":{"draws":35,"losses":82,"wins":15},"x-ai/grok-4.7":{"draws":6,"losses":91,"wins":17},"x-ai/grok-build-0.1":{"draws":16,"losses":10,"wins":18},"xiaomi/mimo-v2.5":{"draws":72,"losses":52,"wins":80},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":24,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":49,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":57,"wins":18},"z-ai/glm-5.2":{"draws":96,"losses":96,"wins":72},"z-ai/glm-5.3":{"draws":25,"losses":84,"wins":17},"z-ai/glm-5.3-flash":{"draws":29,"losses":75,"wins":28},"z-ai/glm-5.3-flashx":{"draws":24,"losses":83,"wins":25}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":17,"wins":95},"claude-fable-5":{"draws":12,"losses":42,"wins":42},"claude-fable-5-1":{"draws":9,"losses":133,"wins":20},"claude-haiku-5-5":{"draws":24,"losses":42,"wins":72},"claude-opus-4-5":{"draws":38,"losses":36,"wins":160},"claude-opus-4-8":{"draws":26,"losses":36,"wins":70},"claude-opus-5":{"draws":41,"losses":141,"wins":64},"claude-opus-5-5":{"draws":10,"losses":126,"wins":20},"claude-sonnet-5":{"draws":27,"losses":25,"wins":92},"claude-sonnet-5-5":{"draws":25,"losses":57,"wins":62},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":36,"losses":14,"wins":166},"deepseek/deepseek-v4-pro":{"draws":26,"losses":27,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":27,"wins":86},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":35,"wins":73},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":34,"wins":46},"elorian/glimpse":{"draws":4,"losses":14,"wins":18},"fireworks/ember-1":{"draws":29,"losses":22,"wins":93},"gemini-3.1-pro-preview":{"draws":28,"losses":31,"wins":85},"gemini-4-argon":{"draws":10,"losses":53,"wins":15},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":81},"google/gemini-3.5-flash":{"draws":34,"losses":33,"wins":113},"google/gemini-3.5-flash-lite":{"draws":46,"losses":28,"wins":178},"google/gemini-3.6-flash":{"draws":48,"losses":82,"wins":146},"google/gemini-3.8-flash":{"draws":23,"losses":53,"wins":68},"google/gemma-4-31b-it":{"draws":18,"losses":8,"wins":58},"gpt-4.1":{"draws":9,"losses":12,"wins":27},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":24,"losses":21,"wins":81},"gpt-5.4":{"draws":33,"losses":42,"wins":63},"gpt-5.4-mini":{"draws":23,"losses":11,"wins":62},"gpt-5.4-nano":{"draws":19,"losses":13,"wins":112},"gpt-5.5":{"draws":31,"losses":38,"wins":63},"gpt-5.6-luna":{"draws":34,"losses":18,"wins":92},"gpt-5.6-sol":{"draws":17,"losses":58,"wins":69},"gpt-5.6-terra":{"draws":38,"losses":19,"wins":81},"gpt-6-astra":{"draws":8,"losses":112,"wins":24},"gpt-6-luna":{"draws":30,"losses":28,"wins":86},"gpt-6-sol":{"draws":20,"losses":83,"wins":41},"gpt-6.1-sol":{"draws":11,"losses":101,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":5,"wins":72},"inception/mercury-3":{"draws":18,"losses":4,"wins":26},"inclusionai/ling-3.0-flash":{"draws":18,"losses":4,"wins":80},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":21,"losses":20,"wins":115},"meta/muse-glimmer-30b":{"draws":27,"losses":7,"wins":92},"meta/muse-spark-1.2":{"draws":22,"losses":31,"wins":85},"meta/muse-spark-1.3":{"draws":25,"losses":42,"wins":77},"meta/muse-spark-open":{"draws":6,"losses":17,"wins":39},"meta/muse-wonder":{"draws":25,"losses":57,"wins":62},"minimax/minimax-m3":{"draws":20,"losses":6,"wins":52},"minimax/minimax-m3.1-flash":{"draws":14,"losses":10,"wins":36},"mistralai/mistral-large-4-0":{"draws":18,"losses":23,"wins":49},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":26,"losses":28,"wins":84},"nex-agi/nex-n2-pro":{"draws":14,"losses":1,"wins":57},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":10,"wins":89},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":33},"o3":{"draws":18,"losses":29,"wins":151},"openai/gpt-oss-120b":{"draws":29,"losses":11,"wins":86},"poolside/laguna-s-2.1":{"draws":27,"losses":21,"wins":90},"qwen/qwen3.7-max":{"draws":15,"losses":13,"wins":56},"qwen/qwen3.7-plus":{"draws":14,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":34,"wins":74},"qwen/qwen3.8-27b":{"draws":20,"losses":16,"wins":66},"qwen/qwen3.8-flash":{"draws":23,"losses":18,"wins":55},"qwen/qwen3.8-max":{"draws":27,"losses":37,"wins":80},"qwen/qwen3.8-max-0902":{"draws":29,"losses":34,"wins":81},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":18,"wins":24},"stealth/ox-alpha":{"draws":82,"losses":115,"wins":277},"stealth/space-bunny-alpha":{"draws":31,"losses":15,"wins":68},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":82},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":22,"losses":11,"wins":45},"tencent/hy4-preview":{"draws":25,"losses":32,"wins":81},"thinkingmachines/inkling":{"draws":40,"losses":12,"wins":140},"thinkingmachines/inkling-small":{"draws":29,"losses":14,"wins":101},"unbiased/pareto-26.10":{"draws":1,"losses":26,"wins":3},"unbiased/pareto-26.10-preview":{"draws":5,"losses":33,"wins":10},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":28},"x-ai/grok-4.5":{"draws":22,"losses":48,"wins":74},"x-ai/grok-4.6":{"draws":34,"losses":49,"wins":61},"x-ai/grok-4.7":{"draws":7,"losses":75,"wins":44},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":31},"xiaomi/mimo-v2.5":{"draws":45,"losses":5,"wins":172},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":65},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":22,"wins":51},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":41,"wins":48},"z-ai/glm-5.2":{"draws":61,"losses":43,"wins":184},"z-ai/glm-5.3":{"draws":21,"losses":64,"wins":53},"z-ai/glm-5.3-flash":{"draws":24,"losses":44,"wins":76},"z-ai/glm-5.3-flashx":{"draws":27,"losses":44,"wins":73}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":140},"claude-fable-5":{"draws":9,"losses":20,"wins":133},"claude-fable-5-1":{"draws":12,"losses":60,"wins":60},"claude-haiku-5-5":{"draws":8,"losses":8,"wins":138},"claude-opus-4-5":{"draws":14,"losses":9,"wins":239},"claude-opus-4-8":{"draws":8,"losses":11,"wins":127},"claude-opus-5":{"draws":27,"losses":82,"wins":169},"claude-opus-5-5":{"draws":17,"losses":93,"wins":64},"claude-sonnet-5":{"draws":9,"losses":4,"wins":149},"claude-sonnet-5-5":{"draws":10,"losses":34,"wins":118},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":231},"deepseek/deepseek-v4-pro":{"draws":9,"losses":3,"wins":138},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":144},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"wins":133},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":15,"wins":63},"elorian/glimpse":{"draws":4,"losses":2,"wins":40},"fireworks/ember-1":{"draws":5,"losses":8,"wins":149},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":150},"gemini-4-argon":{"draws":6,"losses":27,"wins":45},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":101},"google/gemini-3.5-flash":{"draws":11,"losses":8,"wins":183},"google/gemini-3.5-flash-lite":{"draws":21,"losses":2,"wins":261},"google/gemini-3.6-flash":{"draws":25,"losses":17,"wins":270},"google/gemini-3.8-flash":{"draws":8,"losses":14,"wins":140},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":89},"gpt-4.1":{"draws":3,"losses":2,"wins":49},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":20},"gpt-5":{"draws":7,"losses":1,"wins":134},"gpt-5.4":{"draws":10,"losses":16,"wins":130},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":104},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":153},"gpt-5.5":{"draws":5,"losses":18,"wins":127},"gpt-5.6-luna":{"draws":9,"losses":5,"wins":148},"gpt-5.6-sol":{"draws":12,"losses":21,"wins":129},"gpt-5.6-terra":{"draws":11,"losses":3,"wins":142},"gpt-6-astra":{"draws":15,"losses":89,"wins":58},"gpt-6-luna":{"draws":10,"losses":6,"wins":146},"gpt-6-sol":{"draws":15,"losses":37,"wins":110},"gpt-6.1-sol":{"draws":13,"losses":75,"wins":74},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":105},"inception/mercury-3":{"draws":3,"losses":0,"wins":59},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":107},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":164},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":133},"meta/muse-spark-1.2":{"draws":8,"losses":8,"wins":140},"meta/muse-spark-1.3":{"draws":11,"losses":17,"wins":134},"meta/muse-spark-open":{"draws":4,"losses":10,"wins":68},"meta/muse-wonder":{"draws":13,"losses":31,"wins":118},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":84},"minimax/minimax-m3.1-flash":{"draws":7,"losses":4,"wins":79},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":92},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":88},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":36},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":137},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":78},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":129},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":37},"o3":{"draws":5,"losses":9,"wins":204},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":137},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":145},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":88},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":72},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":6,"wins":145},"qwen/qwen3.8-27b":{"draws":6,"losses":1,"wins":107},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":97},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":151},"qwen/qwen3.8-max-0902":{"draws":6,"losses":15,"wins":141},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":0,"wins":58},"stealth/ox-alpha":{"draws":32,"losses":26,"wins":492},"stealth/space-bunny-alpha":{"draws":6,"losses":3,"wins":121},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":111},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":74},"tencent/hy4-preview":{"draws":9,"losses":12,"wins":135},"thinkingmachines/inkling":{"draws":9,"losses":0,"wins":209},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":155},"unbiased/pareto-26.10":{"draws":6,"losses":11,"wins":11},"unbiased/pareto-26.10-preview":{"draws":3,"losses":29,"wins":22},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":37},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":141},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":132},"x-ai/grok-4.7":{"draws":6,"losses":38,"wins":96},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":53},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":227},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":84},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":84},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":10,"wins":84},"z-ai/glm-5.2":{"draws":20,"losses":8,"wins":296},"z-ai/glm-5.3":{"draws":11,"losses":22,"wins":123},"z-ai/glm-5.3-flash":{"draws":8,"losses":15,"wins":139},"z-ai/glm-5.3-flashx":{"draws":15,"losses":13,"wins":134}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":74},"claude-fable-5":{"draws":24,"losses":72,"wins":42},"claude-fable-5-1":{"draws":8,"losses":138,"wins":8},"claude-haiku-5-5":{"draws":16,"losses":36,"wins":36},"claude-opus-4-5":{"draws":64,"losses":57,"wins":105},"claude-opus-4-8":{"draws":28,"losses":57,"wins":45},"claude-opus-5":{"draws":35,"losses":160,"wins":39},"claude-opus-5-5":{"draws":16,"losses":126,"wins":8},"claude-sonnet-5":{"draws":35,"losses":40,"wins":63},"claude-sonnet-5-5":{"draws":25,"losses":70,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":57,"losses":30,"wins":121},"deepseek/deepseek-v4-pro":{"draws":35,"losses":41,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":29,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":39,"wins":56},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":32,"wins":21},"elorian/glimpse":{"draws":5,"losses":16,"wins":17},"fireworks/ember-1":{"draws":36,"losses":38,"wins":64},"gemini-3.1-pro-preview":{"draws":32,"losses":46,"wins":60},"gemini-4-argon":{"draws":9,"losses":35,"wins":10},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":66},"google/gemini-3.5-flash":{"draws":39,"losses":58,"wins":77},"google/gemini-3.5-flash-lite":{"draws":53,"losses":40,"wins":149},"google/gemini-3.6-flash":{"draws":65,"losses":99,"wins":100},"google/gemini-3.8-flash":{"draws":33,"losses":62,"wins":43},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":50},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":9},"gpt-5":{"draws":31,"losses":27,"wins":62},"gpt-5.4":{"draws":31,"losses":50,"wins":51},"gpt-5.4-mini":{"draws":27,"losses":12,"wins":53},"gpt-5.4-nano":{"draws":27,"losses":39,"wins":76},"gpt-5.5":{"draws":46,"losses":35,"wins":45},"gpt-5.6-luna":{"draws":40,"losses":24,"wins":74},"gpt-5.6-sol":{"draws":21,"losses":76,"wins":41},"gpt-5.6-terra":{"draws":39,"losses":37,"wins":56},"gpt-6-astra":{"draws":10,"losses":121,"wins":7},"gpt-6-luna":{"draws":36,"losses":39,"wins":63},"gpt-6-sol":{"draws":27,"losses":84,"wins":27},"gpt-6.1-sol":{"draws":15,"losses":113,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":68},"inception/mercury-3":{"draws":17,"losses":12,"wins":21},"inclusionai/ling-3.0-flash":{"draws":32,"losses":5,"wins":61},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":21,"wins":96},"meta/muse-glimmer-30b":{"draws":37,"losses":15,"wins":68},"meta/muse-spark-1.2":{"draws":26,"losses":41,"wins":65},"meta/muse-spark-1.3":{"draws":26,"losses":51,"wins":61},"meta/muse-spark-open":{"draws":12,"losses":33,"wins":13},"meta/muse-wonder":{"draws":30,"losses":79,"wins":29},"minimax/minimax-m3":{"draws":8,"losses":15,"wins":53},"minimax/minimax-m3.1-flash":{"draws":19,"losses":15,"wins":40},"mistralai/mistral-large-4-0":{"draws":30,"losses":28,"wins":28},"mistralai/mistral-medium-3-5":{"draws":22,"losses":4,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":15},"moonshotai/kimi-k3":{"draws":34,"losses":40,"wins":58},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":26,"wins":66},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":10,"wins":14},"o3":{"draws":32,"losses":61,"wins":101},"openai/gpt-oss-120b":{"draws":30,"losses":12,"wins":78},"poolside/laguna-s-2.1":{"draws":34,"losses":35,"wins":61},"qwen/qwen3.7-max":{"draws":27,"losses":20,"wins":35},"qwen/qwen3.7-plus":{"draws":14,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":47,"wins":55},"qwen/qwen3.8-27b":{"draws":22,"losses":29,"wins":47},"qwen/qwen3.8-flash":{"draws":28,"losses":19,"wins":45},"qwen/qwen3.8-max":{"draws":34,"losses":37,"wins":67},"qwen/qwen3.8-max-0902":{"draws":40,"losses":48,"wins":50},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":14,"wins":35},"stealth/ox-alpha":{"draws":96,"losses":165,"wins":173},"stealth/space-bunny-alpha":{"draws":33,"losses":23,"wins":54},"stepfun/step-3.7-flash":{"draws":15,"losses":16,"wins":67},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":25,"losses":20,"wins":31},"tencent/hy4-preview":{"draws":30,"losses":54,"wins":48},"thinkingmachines/inkling":{"draws":49,"losses":23,"wins":110},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":92},"unbiased/pareto-26.10":{"draws":2,"losses":26,"wins":4},"unbiased/pareto-26.10-preview":{"draws":2,"losses":35,"wins":9},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":30,"losses":60,"wins":48},"x-ai/grok-4.6":{"draws":36,"losses":60,"wins":42},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":20},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":29},"xiaomi/mimo-v2.5":{"draws":56,"losses":31,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":18,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":27,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":43,"wins":32},"z-ai/glm-5.2":{"draws":64,"losses":64,"wins":148},"z-ai/glm-5.3":{"draws":24,"losses":76,"wins":32},"z-ai/glm-5.3-flash":{"draws":27,"losses":57,"wins":54},"z-ai/glm-5.3-flashx":{"draws":27,"losses":51,"wins":60}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":30,"wins":62},"claude-fable-5":{"draws":23,"losses":95,"wins":26},"claude-fable-5-1":{"draws":12,"losses":144,"wins":6},"claude-haiku-5-5":{"draws":40,"losses":55,"wins":43},"claude-opus-4-5":{"draws":63,"losses":52,"wins":71},"claude-opus-4-8":{"draws":37,"losses":57,"wins":38},"claude-opus-5":{"draws":39,"losses":184,"wins":23},"claude-opus-5-5":{"draws":12,"losses":134,"wins":10},"claude-sonnet-5":{"draws":50,"losses":42,"wins":52},"claude-sonnet-5-5":{"draws":30,"losses":74,"wins":40},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":43},"deepseek/deepseek-v4-flash":{"draws":62,"losses":42,"wins":112},"deepseek/deepseek-v4-pro":{"draws":35,"losses":48,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":46,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":62,"wins":44},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":50,"wins":15},"elorian/glimpse":{"draws":8,"losses":19,"wins":11},"fireworks/ember-1":{"draws":50,"losses":55,"wins":39},"gemini-3.1-pro-preview":{"draws":36,"losses":47,"wins":61},"gemini-4-argon":{"draws":5,"losses":65,"wins":4},"google/gemini-3.1-flash-lite":{"draws":22,"losses":5,"wins":69},"google/gemini-3.5-flash":{"draws":49,"losses":69,"wins":62},"google/gemini-3.5-flash-lite":{"draws":83,"losses":53,"wins":116},"google/gemini-3.6-flash":{"draws":78,"losses":123,"wins":75},"google/gemini-3.8-flash":{"draws":43,"losses":74,"wins":27},"google/gemma-4-31b-it":{"draws":28,"losses":10,"wins":46},"gpt-4.1":{"draws":20,"losses":12,"wins":16},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":6},"gpt-5":{"draws":38,"losses":39,"wins":49},"gpt-5.4":{"draws":40,"losses":68,"wins":30},"gpt-5.4-mini":{"draws":39,"losses":20,"wins":37},"gpt-5.4-nano":{"draws":42,"losses":33,"wins":69},"gpt-5.5":{"draws":56,"losses":52,"wins":24},"gpt-5.6-luna":{"draws":53,"losses":32,"wins":59},"gpt-5.6-sol":{"draws":22,"losses":96,"wins":26},"gpt-5.6-terra":{"draws":54,"losses":39,"wins":45},"gpt-6-astra":{"draws":9,"losses":124,"wins":11},"gpt-6-luna":{"draws":45,"losses":47,"wins":52},"gpt-6-sol":{"draws":24,"losses":105,"wins":15},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":43,"losses":6,"wins":53},"inception/mercury-3":{"draws":21,"losses":19,"wins":14},"inclusionai/ling-3.0-flash":{"draws":37,"losses":10,"wins":55},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":42,"losses":21,"wins":93},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":65},"meta/muse-spark-1.2":{"draws":34,"losses":66,"wins":38},"meta/muse-spark-1.3":{"draws":28,"losses":80,"wins":36},"meta/muse-spark-open":{"draws":20,"losses":28,"wins":12},"meta/muse-wonder":{"draws":27,"losses":87,"wins":30},"minimax/minimax-m3":{"draws":21,"losses":9,"wins":48},"minimax/minimax-m3.1-flash":{"draws":24,"losses":17,"wins":45},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":33},"mistralai/mistral-medium-3-5":{"draws":26,"losses":8,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":9,"wins":19},"moonshotai/kimi-k3":{"draws":48,"losses":48,"wins":42},"nex-agi/nex-n2-pro":{"draws":17,"losses":9,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":17,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":14,"wins":11},"o3":{"draws":29,"losses":53,"wins":116},"openai/gpt-oss-120b":{"draws":40,"losses":22,"wins":64},"poolside/laguna-s-2.1":{"draws":49,"losses":21,"wins":68},"qwen/qwen3.7-max":{"draws":24,"losses":20,"wins":40},"qwen/qwen3.7-plus":{"draws":22,"losses":15,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":53,"losses":56,"wins":35},"qwen/qwen3.8-27b":{"draws":31,"losses":36,"wins":35},"qwen/qwen3.8-flash":{"draws":35,"losses":29,"wins":32},"qwen/qwen3.8-max":{"draws":41,"losses":60,"wins":43},"qwen/qwen3.8-max-0902":{"draws":36,"losses":58,"wins":50},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":24,"wins":18},"stealth/ox-alpha":{"draws":132,"losses":200,"wins":142},"stealth/space-bunny-alpha":{"draws":36,"losses":27,"wins":51},"stepfun/step-3.7-flash":{"draws":15,"losses":21,"wins":66},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":27,"losses":18,"wins":33},"tencent/hy4-preview":{"draws":34,"losses":61,"wins":43},"thinkingmachines/inkling":{"draws":58,"losses":33,"wins":101},"thinkingmachines/inkling-small":{"draws":49,"losses":18,"wins":77},"unbiased/pareto-26.10":{"draws":5,"losses":31,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":42,"losses":61,"wins":41},"x-ai/grok-4.6":{"draws":36,"losses":75,"wins":33},"x-ai/grok-4.7":{"draws":11,"losses":91,"wins":24},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":26},"xiaomi/mimo-v2.5":{"draws":73,"losses":30,"wins":119},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":26,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":43,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":52,"wins":20},"z-ai/glm-5.2":{"draws":90,"losses":79,"wins":119},"z-ai/glm-5.3":{"draws":33,"losses":83,"wins":22},"z-ai/glm-5.3-flash":{"draws":33,"losses":73,"wins":38},"z-ai/glm-5.3-flashx":{"draws":37,"losses":74,"wins":33}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":20,"wins":70},"claude-fable-5":{"draws":26,"losses":70,"wins":36},"claude-fable-5-1":{"draws":8,"losses":127,"wins":11},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":57},"claude-opus-4-5":{"draws":64,"losses":54,"wins":100},"claude-opus-4-8":{"draws":14,"losses":35,"wins":35},"claude-opus-5":{"draws":35,"losses":152,"wins":35},"claude-opus-5-5":{"draws":13,"losses":113,"wins":18},"claude-sonnet-5":{"draws":36,"losses":38,"wins":58},"claude-sonnet-5-5":{"draws":28,"losses":62,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":38},"deepseek/deepseek-v4-flash":{"draws":48,"losses":27,"wins":125},"deepseek/deepseek-v4-pro":{"draws":28,"losses":36,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":39,"wins":53},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":53,"wins":47},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":34,"wins":22},"elorian/glimpse":{"draws":7,"losses":20,"wins":15},"fireworks/ember-1":{"draws":44,"losses":37,"wins":51},"gemini-3.1-pro-preview":{"draws":35,"losses":35,"wins":62},"gemini-4-argon":{"draws":3,"losses":48,"wins":11},"google/gemini-3.1-flash-lite":{"draws":20,"losses":5,"wins":71},"google/gemini-3.5-flash":{"draws":37,"losses":49,"wins":82},"google/gemini-3.5-flash-lite":{"draws":63,"losses":22,"wins":147},"google/gemini-3.6-flash":{"draws":56,"losses":102,"wins":94},"google/gemini-3.8-flash":{"draws":28,"losses":61,"wins":43},"google/gemma-4-31b-it":{"draws":23,"losses":10,"wins":47},"gpt-4.1":{"draws":14,"losses":5,"wins":25},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":7},"gpt-5":{"draws":30,"losses":30,"wins":54},"gpt-5.4":{"draws":29,"losses":54,"wins":43},"gpt-5.4-mini":{"draws":23,"losses":21,"wins":44},"gpt-5.4-nano":{"draws":25,"losses":31,"wins":84},"gpt-5.5":{"draws":38,"losses":47,"wins":35},"gpt-5.6-luna":{"draws":42,"losses":28,"wins":62},"gpt-5.6-sol":{"draws":17,"losses":72,"wins":43},"gpt-5.6-terra":{"draws":32,"losses":35,"wins":59},"gpt-6-astra":{"draws":8,"losses":113,"wins":11},"gpt-6-luna":{"draws":35,"losses":36,"wins":61},"gpt-6-sol":{"draws":20,"losses":79,"wins":33},"gpt-6.1-sol":{"draws":7,"losses":110,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":10,"wins":56},"inception/mercury-3":{"draws":12,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":29,"losses":0,"wins":65},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":33,"losses":21,"wins":90},"meta/muse-glimmer-30b":{"draws":32,"losses":16,"wins":66},"meta/muse-spark-1.2":{"draws":29,"losses":44,"wins":53},"meta/muse-spark-1.3":{"draws":26,"losses":55,"wins":51},"meta/muse-spark-open":{"draws":19,"losses":19,"wins":20},"meta/muse-wonder":{"draws":26,"losses":62,"wins":44},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":48},"minimax/minimax-m3.1-flash":{"draws":19,"losses":17,"wins":36},"mistralai/mistral-large-4-0":{"draws":18,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":25,"losses":6,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":7,"wins":19},"moonshotai/kimi-k3":{"draws":32,"losses":43,"wins":51},"nex-agi/nex-n2-pro":{"draws":16,"losses":4,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":18,"wins":77},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":6,"wins":21},"o3":{"draws":27,"losses":55,"wins":108},"openai/gpt-oss-120b":{"draws":36,"losses":10,"wins":68},"poolside/laguna-s-2.1":{"draws":37,"losses":16,"wins":69},"qwen/qwen3.7-max":{"draws":24,"losses":21,"wins":35},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":50,"wins":44},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":43},"qwen/qwen3.8-flash":{"draws":31,"losses":16,"wins":41},"qwen/qwen3.8-max":{"draws":26,"losses":45,"wins":61},"qwen/qwen3.8-max-0902":{"draws":33,"losses":48,"wins":51},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":20,"wins":27},"stealth/ox-alpha":{"draws":85,"losses":156,"wins":153},"stealth/space-bunny-alpha":{"draws":30,"losses":24,"wins":52},"stepfun/step-3.7-flash":{"draws":16,"losses":17,"wins":61},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":20,"losses":16,"wins":38},"tencent/hy4-preview":{"draws":31,"losses":49,"wins":46},"thinkingmachines/inkling":{"draws":43,"losses":21,"wins":108},"thinkingmachines/inkling-small":{"draws":40,"losses":12,"wins":80},"unbiased/pareto-26.10":{"draws":3,"losses":24,"wins":3},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":35,"losses":51,"wins":46},"x-ai/grok-4.6":{"draws":32,"losses":58,"wins":42},"x-ai/grok-4.7":{"draws":16,"losses":72,"wins":30},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":28},"xiaomi/mimo-v2.5":{"draws":63,"losses":24,"wins":131},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":38,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":42,"wins":35},"z-ai/glm-5.2":{"draws":74,"losses":57,"wins":133},"z-ai/glm-5.3":{"draws":21,"losses":73,"wins":32},"z-ai/glm-5.3-flash":{"draws":20,"losses":61,"wins":51},"z-ai/glm-5.3-flashx":{"draws":25,"losses":48,"wins":59}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":20,"wins":179},"claude-fable-5":{"draws":41,"losses":64,"wins":141},"claude-fable-5-1":{"draws":27,"losses":169,"wins":82},"claude-haiku-5-5":{"draws":35,"losses":39,"wins":160},"claude-opus-4-5":{"draws":69,"losses":39,"wins":290},"claude-opus-4-8":{"draws":35,"losses":35,"wins":152},"claude-opus-5":{"draws":54,"losses":165,"wins":165},"claude-opus-5-5":{"draws":25,"losses":166,"wins":79},"claude-sonnet-5":{"draws":34,"losses":33,"wins":179},"claude-sonnet-5-5":{"draws":24,"losses":84,"wins":138},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":80},"deepseek/deepseek-v4-flash":{"draws":39,"losses":21,"wins":302},"deepseek/deepseek-v4-pro":{"draws":26,"losses":31,"wins":175},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":27,"wins":175},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":37,"wins":171},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":35,"wins":94},"elorian/glimpse":{"draws":6,"losses":13,"wins":45},"fireworks/ember-1":{"draws":27,"losses":44,"wins":175},"gemini-3.1-pro-preview":{"draws":23,"losses":38,"wins":185},"gemini-4-argon":{"draws":16,"losses":46,"wins":38},"google/gemini-3.1-flash-lite":{"draws":16,"losses":8,"wins":126},"google/gemini-3.5-flash":{"draws":37,"losses":30,"wins":237},"google/gemini-3.5-flash-lite":{"draws":55,"losses":30,"wins":339},"google/gemini-3.6-flash":{"draws":65,"losses":81,"wins":322},"google/gemini-3.8-flash":{"draws":28,"losses":54,"wins":164},"google/gemma-4-31b-it":{"draws":21,"losses":10,"wins":109},"gpt-4.1":{"draws":9,"losses":5,"wins":68},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":18},"gpt-5":{"draws":23,"losses":18,"wins":179},"gpt-5.4":{"draws":29,"losses":36,"wins":169},"gpt-5.4-mini":{"draws":32,"losses":12,"wins":120},"gpt-5.4-nano":{"draws":21,"losses":17,"wins":198},"gpt-5.5":{"draws":31,"losses":45,"wins":156},"gpt-5.6-luna":{"draws":26,"losses":25,"wins":195},"gpt-5.6-sol":{"draws":29,"losses":60,"wins":157},"gpt-5.6-terra":{"draws":29,"losses":21,"wins":184},"gpt-6-astra":{"draws":23,"losses":166,"wins":57},"gpt-6-luna":{"draws":45,"losses":22,"wins":179},"gpt-6-sol":{"draws":33,"losses":93,"wins":120},"gpt-6.1-sol":{"draws":32,"losses":139,"wins":75},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":31,"losses":6,"wins":129},"inception/mercury-3":{"draws":11,"losses":8,"wins":65},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":132},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":26,"losses":22,"wins":208},"meta/muse-glimmer-30b":{"draws":15,"losses":23,"wins":192},"meta/muse-spark-1.2":{"draws":30,"losses":35,"wins":179},"meta/muse-spark-1.3":{"draws":30,"losses":50,"wins":166},"meta/muse-spark-open":{"draws":14,"losses":17,"wins":99},"meta/muse-wonder":{"draws":29,"losses":76,"wins":141},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":117},"minimax/minimax-m3.1-flash":{"draws":11,"losses":11,"wins":84},"mistralai/mistral-large-4-0":{"draws":24,"losses":19,"wins":119},"mistralai/mistral-medium-3-5":{"draws":21,"losses":12,"wins":111},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":59},"moonshotai/kimi-k3":{"draws":38,"losses":39,"wins":167},"nex-agi/nex-n2-pro":{"draws":3,"losses":6,"wins":107},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":6,"wins":180},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":7,"wins":42},"o3":{"draws":26,"losses":20,"wins":266},"openai/gpt-oss-120b":{"draws":32,"losses":11,"wins":177},"poolside/laguna-s-2.1":{"draws":25,"losses":14,"wins":209},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":111},"qwen/qwen3.7-plus":{"draws":16,"losses":8,"wins":92},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":40,"wins":174},"qwen/qwen3.8-27b":{"draws":28,"losses":13,"wins":125},"qwen/qwen3.8-flash":{"draws":23,"losses":14,"wins":127},"qwen/qwen3.8-max":{"draws":36,"losses":30,"wins":180},"qwen/qwen3.8-max-0902":{"draws":35,"losses":42,"wins":169},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":13,"wins":87},"stealth/ox-alpha":{"draws":129,"losses":121,"wins":582},"stealth/space-bunny-alpha":{"draws":31,"losses":14,"wins":151},"stepfun/step-3.7-flash":{"draws":14,"losses":7,"wins":141},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":25,"losses":11,"wins":106},"tencent/hy4-preview":{"draws":24,"losses":35,"wins":175},"thinkingmachines/inkling":{"draws":48,"losses":29,"wins":261},"thinkingmachines/inkling-small":{"draws":38,"losses":12,"wins":196},"unbiased/pareto-26.10":{"draws":7,"losses":31,"wins":16},"unbiased/pareto-26.10-preview":{"draws":3,"losses":50,"wins":29},"upstage/solar-mini4":{"draws":7,"losses":1,"wins":40},"x-ai/grok-4.5":{"draws":37,"losses":42,"wins":167},"x-ai/grok-4.6":{"draws":36,"losses":50,"wins":159},"x-ai/grok-4.7":{"draws":22,"losses":98,"wins":100},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":65},"xiaomi/mimo-v2.5":{"draws":57,"losses":26,"wins":295},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":5,"wins":110},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":17,"wins":119},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":39,"wins":99},"z-ai/glm-5.2":{"draws":74,"losses":33,"wins":385},"z-ai/glm-5.3":{"draws":33,"losses":63,"wins":138},"z-ai/glm-5.3-flash":{"draws":37,"losses":46,"wins":163},"z-ai/glm-5.3-flashx":{"draws":36,"losses":44,"wins":166}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":131},"claude-fable-5":{"draws":10,"losses":20,"wins":126},"claude-fable-5-1":{"draws":17,"losses":64,"wins":93},"claude-haiku-5-5":{"draws":16,"losses":8,"wins":126},"claude-opus-4-5":{"draws":20,"losses":17,"wins":217},"claude-opus-4-8":{"draws":13,"losses":18,"wins":113},"claude-opus-5":{"draws":25,"losses":79,"wins":166},"claude-opus-5-5":{"draws":10,"losses":57,"wins":57},"claude-sonnet-5":{"draws":11,"losses":11,"wins":134},"claude-sonnet-5-5":{"draws":16,"losses":29,"wins":111},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":60},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":218},"deepseek/deepseek-v4-pro":{"draws":11,"losses":5,"wins":128},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":134},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":132},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":13,"wins":59},"elorian/glimpse":{"draws":3,"losses":1,"wins":36},"fireworks/ember-1":{"draws":8,"losses":11,"wins":137},"gemini-3.1-pro-preview":{"draws":9,"losses":10,"wins":137},"gemini-4-argon":{"draws":3,"losses":29,"wins":44},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":96},"google/gemini-3.5-flash":{"draws":10,"losses":9,"wins":177},"google/gemini-3.5-flash-lite":{"draws":18,"losses":1,"wins":253},"google/gemini-3.6-flash":{"draws":23,"losses":20,"wins":253},"google/gemini-3.8-flash":{"draws":15,"losses":19,"wins":122},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":87},"gpt-4.1":{"draws":5,"losses":1,"wins":46},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":5,"wins":124},"gpt-5.4":{"draws":11,"losses":13,"wins":126},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":97},"gpt-5.4-nano":{"draws":7,"losses":2,"wins":151},"gpt-5.5":{"draws":14,"losses":15,"wins":115},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":134},"gpt-5.6-sol":{"draws":12,"losses":21,"wins":123},"gpt-5.6-terra":{"draws":9,"losses":3,"wins":138},"gpt-6-astra":{"draws":16,"losses":73,"wins":67},"gpt-6-luna":{"draws":14,"losses":2,"wins":140},"gpt-6-sol":{"draws":15,"losses":39,"wins":102},"gpt-6.1-sol":{"draws":18,"losses":63,"wins":75},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":102},"inception/mercury-3":{"draws":1,"losses":1,"wins":50},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":107},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":156},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":131},"meta/muse-spark-1.2":{"draws":12,"losses":9,"wins":129},"meta/muse-spark-1.3":{"draws":8,"losses":14,"wins":134},"meta/muse-spark-open":{"draws":6,"losses":4,"wins":66},"meta/muse-wonder":{"draws":9,"losses":31,"wins":116},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"minimax/minimax-m3.1-flash":{"draws":5,"losses":0,"wins":71},"mistralai/mistral-large-4-0":{"draws":14,"losses":5,"wins":79},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":85},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":36},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":132},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":74},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":136},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":40},"o3":{"draws":11,"losses":3,"wins":204},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":129},"poolside/laguna-s-2.1":{"draws":10,"losses":0,"wins":144},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":86},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":71},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":127},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":98},"qwen/qwen3.8-flash":{"draws":10,"losses":3,"wins":91},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":131},"qwen/qwen3.8-max-0902":{"draws":16,"losses":12,"wins":128},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":2,"wins":64},"stealth/ox-alpha":{"draws":46,"losses":28,"wins":432},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":116},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":106},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":16},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":78},"tencent/hy4-preview":{"draws":12,"losses":13,"wins":125},"thinkingmachines/inkling":{"draws":18,"losses":0,"wins":186},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":146},"unbiased/pareto-26.10":{"draws":2,"losses":11,"wins":17},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":26},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":17,"losses":16,"wins":123},"x-ai/grok-4.6":{"draws":17,"losses":15,"wins":124},"x-ai/grok-4.7":{"draws":11,"losses":31,"wins":96},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":51},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":227},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":82},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":2,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":80},"z-ai/glm-5.2":{"draws":18,"losses":12,"wins":282},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":116},"z-ai/glm-5.3-flash":{"draws":13,"losses":10,"wins":133},"z-ai/glm-5.3-flashx":{"draws":16,"losses":10,"wins":130}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":23,"wins":68},"claude-fable-5":{"draws":27,"losses":92,"wins":25},"claude-fable-5-1":{"draws":9,"losses":149,"wins":4},"claude-haiku-5-5":{"draws":35,"losses":63,"wins":40},"claude-opus-4-5":{"draws":77,"losses":81,"wins":76},"claude-opus-4-8":{"draws":36,"losses":58,"wins":38},"claude-opus-5":{"draws":34,"losses":179,"wins":33},"claude-opus-5-5":{"draws":11,"losses":134,"wins":11},"claude-sonnet-5":{"draws":28,"losses":34,"wins":34},"claude-sonnet-5-5":{"draws":25,"losses":83,"wins":36},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":38},"deepseek/deepseek-v4-flash":{"draws":63,"losses":40,"wins":113},"deepseek/deepseek-v4-pro":{"draws":40,"losses":46,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":48,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":44,"losses":53,"wins":47},"deepseek/deepseek-v4.1-flash-1017":{"draws":19,"losses":50,"wins":19},"elorian/glimpse":{"draws":10,"losses":10,"wins":10},"fireworks/ember-1":{"draws":44,"losses":60,"wins":40},"gemini-3.1-pro-preview":{"draws":43,"losses":50,"wins":51},"gemini-4-argon":{"draws":4,"losses":60,"wins":2},"google/gemini-3.1-flash-lite":{"draws":29,"losses":7,"wins":60},"google/gemini-3.5-flash":{"draws":50,"losses":74,"wins":56},"google/gemini-3.5-flash-lite":{"draws":71,"losses":52,"wins":129},"google/gemini-3.6-flash":{"draws":65,"losses":123,"wins":88},"google/gemini-3.8-flash":{"draws":33,"losses":78,"wins":33},"google/gemma-4-31b-it":{"draws":27,"losses":12,"wins":45},"gpt-4.1":{"draws":17,"losses":14,"wins":17},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":37,"losses":35,"wins":54},"gpt-5.4":{"draws":37,"losses":70,"wins":31},"gpt-5.4-mini":{"draws":38,"losses":28,"wins":30},"gpt-5.4-nano":{"draws":33,"losses":40,"wins":71},"gpt-5.5":{"draws":49,"losses":58,"wins":25},"gpt-5.6-luna":{"draws":45,"losses":38,"wins":61},"gpt-5.6-sol":{"draws":20,"losses":105,"wins":19},"gpt-5.6-terra":{"draws":53,"losses":44,"wins":41},"gpt-6-astra":{"draws":6,"losses":130,"wins":8},"gpt-6-luna":{"draws":38,"losses":56,"wins":50},"gpt-6-sol":{"draws":24,"losses":101,"wins":19},"gpt-6.1-sol":{"draws":6,"losses":129,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":38,"losses":10,"wins":54},"inception/mercury-3":{"draws":23,"losses":18,"wins":9},"inclusionai/ling-3.0-flash":{"draws":36,"losses":8,"wins":58},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":43,"losses":30,"wins":83},"meta/muse-glimmer-30b":{"draws":43,"losses":19,"wins":64},"meta/muse-spark-1.2":{"draws":38,"losses":64,"wins":36},"meta/muse-spark-1.3":{"draws":37,"losses":74,"wins":33},"meta/muse-spark-open":{"draws":21,"losses":41,"wins":12},"meta/muse-wonder":{"draws":31,"losses":85,"wins":28},"minimax/minimax-m3":{"draws":21,"losses":15,"wins":42},"minimax/minimax-m3.1-flash":{"draws":17,"losses":22,"wins":33},"mistralai/mistral-large-4-0":{"draws":27,"losses":24,"wins":39},"mistralai/mistral-medium-3-5":{"draws":32,"losses":10,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":41,"losses":59,"wins":38},"nex-agi/nex-n2-pro":{"draws":24,"losses":11,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":29,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":16},"o3":{"draws":27,"losses":82,"wins":89},"openai/gpt-oss-120b":{"draws":38,"losses":17,"wins":71},"poolside/laguna-s-2.1":{"draws":43,"losses":26,"wins":69},"qwen/qwen3.7-max":{"draws":27,"losses":17,"wins":40},"qwen/qwen3.7-plus":{"draws":20,"losses":17,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":62,"wins":37},"qwen/qwen3.8-27b":{"draws":26,"losses":38,"wins":38},"qwen/qwen3.8-flash":{"draws":32,"losses":31,"wins":33},"qwen/qwen3.8-max":{"draws":46,"losses":54,"wins":44},"qwen/qwen3.8-max-0902":{"draws":42,"losses":66,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":21,"wins":22},"stealth/ox-alpha":{"draws":108,"losses":233,"wins":133},"stealth/space-bunny-alpha":{"draws":30,"losses":37,"wins":47},"stepfun/step-3.7-flash":{"draws":21,"losses":27,"wins":54},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":25,"losses":22,"wins":31},"tencent/hy4-preview":{"draws":40,"losses":64,"wins":34},"thinkingmachines/inkling":{"draws":62,"losses":28,"wins":102},"thinkingmachines/inkling-small":{"draws":47,"losses":24,"wins":73},"unbiased/pareto-26.10":{"draws":3,"losses":27,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":48,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":39,"losses":71,"wins":34},"x-ai/grok-4.6":{"draws":39,"losses":73,"wins":32},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":19,"losses":3,"wins":26},"xiaomi/mimo-v2.5":{"draws":81,"losses":38,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":50,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":57,"wins":24},"z-ai/glm-5.2":{"draws":79,"losses":88,"wins":121},"z-ai/glm-5.3":{"draws":28,"losses":91,"wins":19},"z-ai/glm-5.3-flash":{"draws":25,"losses":78,"wins":41},"z-ai/glm-5.3-flashx":{"draws":39,"losses":72,"wins":33}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":79},"claude-fable-5":{"draws":25,"losses":62,"wins":57},"claude-fable-5-1":{"draws":10,"losses":118,"wins":34},"claude-haiku-5-5":{"draws":25,"losses":43,"wins":70},"claude-opus-4-5":{"draws":48,"losses":58,"wins":128},"claude-opus-4-8":{"draws":28,"losses":42,"wins":62},"claude-opus-5":{"draws":24,"losses":138,"wins":84},"claude-opus-5-5":{"draws":16,"losses":111,"wins":29},"claude-sonnet-5":{"draws":25,"losses":36,"wins":83},"claude-sonnet-5-5":{"draws":8,"losses":44,"wins":44},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":40},"deepseek/deepseek-v4-flash":{"draws":45,"losses":31,"wins":140},"deepseek/deepseek-v4-pro":{"draws":32,"losses":33,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":40,"wins":72},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":34,"wins":27},"elorian/glimpse":{"draws":9,"losses":12,"wins":19},"fireworks/ember-1":{"draws":29,"losses":43,"wins":72},"gemini-3.1-pro-preview":{"draws":22,"losses":39,"wins":83},"gemini-4-argon":{"draws":9,"losses":48,"wins":25},"google/gemini-3.1-flash-lite":{"draws":15,"losses":12,"wins":69},"google/gemini-3.5-flash":{"draws":30,"losses":46,"wins":104},"google/gemini-3.5-flash-lite":{"draws":49,"losses":39,"wins":164},"google/gemini-3.6-flash":{"draws":52,"losses":98,"wins":126},"google/gemini-3.8-flash":{"draws":20,"losses":56,"wins":68},"google/gemma-4-31b-it":{"draws":14,"losses":16,"wins":54},"gpt-4.1":{"draws":10,"losses":8,"wins":30},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":27,"losses":26,"wins":73},"gpt-5.4":{"draws":36,"losses":43,"wins":59},"gpt-5.4-mini":{"draws":17,"losses":17,"wins":62},"gpt-5.4-nano":{"draws":20,"losses":19,"wins":105},"gpt-5.5":{"draws":29,"losses":42,"wins":61},"gpt-5.6-luna":{"draws":33,"losses":27,"wins":84},"gpt-5.6-sol":{"draws":15,"losses":71,"wins":58},"gpt-5.6-terra":{"draws":33,"losses":31,"wins":74},"gpt-6-astra":{"draws":13,"losses":103,"wins":28},"gpt-6-luna":{"draws":32,"losses":44,"wins":68},"gpt-6-sol":{"draws":14,"losses":82,"wins":48},"gpt-6.1-sol":{"draws":4,"losses":104,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":65},"inception/mercury-3":{"draws":6,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":26,"losses":7,"wins":69},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":20,"losses":31,"wins":105},"meta/muse-glimmer-30b":{"draws":21,"losses":21,"wins":84},"meta/muse-spark-1.2":{"draws":26,"losses":43,"wins":69},"meta/muse-spark-1.3":{"draws":22,"losses":54,"wins":68},"meta/muse-spark-open":{"draws":12,"losses":23,"wins":23},"meta/muse-wonder":{"draws":21,"losses":54,"wins":69},"minimax/minimax-m3":{"draws":13,"losses":13,"wins":52},"minimax/minimax-m3.1-flash":{"draws":16,"losses":13,"wins":39},"mistralai/mistral-large-4-0":{"draws":23,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":19,"losses":8,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":28,"losses":47,"wins":63},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":22,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":6,"wins":20},"o3":{"draws":17,"losses":46,"wins":135},"openai/gpt-oss-120b":{"draws":26,"losses":18,"wins":82},"poolside/laguna-s-2.1":{"draws":25,"losses":26,"wins":87},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":44},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":51,"wins":62},"qwen/qwen3.8-27b":{"draws":17,"losses":25,"wins":60},"qwen/qwen3.8-flash":{"draws":17,"losses":30,"wins":49},"qwen/qwen3.8-max":{"draws":23,"losses":42,"wins":79},"qwen/qwen3.8-max-0902":{"draws":26,"losses":51,"wins":67},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":19,"wins":42},"stealth/ox-alpha":{"draws":85,"losses":164,"wins":225},"stealth/space-bunny-alpha":{"draws":22,"losses":24,"wins":68},"stepfun/step-3.7-flash":{"draws":11,"losses":26,"wins":65},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":49},"tencent/hy4-preview":{"draws":24,"losses":47,"wins":67},"thinkingmachines/inkling":{"draws":41,"losses":41,"wins":110},"thinkingmachines/inkling-small":{"draws":32,"losses":21,"wins":91},"unbiased/pareto-26.10":{"draws":3,"losses":22,"wins":5},"unbiased/pareto-26.10-preview":{"draws":2,"losses":37,"wins":9},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":31,"losses":50,"wins":63},"x-ai/grok-4.6":{"draws":24,"losses":59,"wins":61},"x-ai/grok-4.7":{"draws":15,"losses":64,"wins":47},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":49,"losses":27,"wins":146},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":13,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":34,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":37,"wins":46},"z-ai/glm-5.2":{"draws":55,"losses":66,"wins":167},"z-ai/glm-5.3":{"draws":24,"losses":62,"wins":52},"z-ai/glm-5.3-flash":{"draws":20,"losses":55,"wins":69},"z-ai/glm-5.3-flashx":{"draws":25,"losses":54,"wins":65}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":23,"wins":14},"claude-fable-5":{"draws":8,"losses":44,"wins":2},"claude-fable-5-1":{"draws":0,"losses":61,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":9},"claude-opus-4-5":{"draws":9,"losses":71,"wins":8},"claude-opus-4-8":{"draws":9,"losses":38,"wins":3},"claude-opus-5":{"draws":6,"losses":80,"wins":4},"claude-opus-5-5":{"draws":2,"losses":60,"wins":0},"claude-sonnet-5":{"draws":8,"losses":38,"wins":8},"claude-sonnet-5-5":{"draws":6,"losses":40,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":21,"losses":34,"wins":25},"deepseek/deepseek-v4-pro":{"draws":9,"losses":29,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":32,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":33,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":23,"wins":0},"elorian/glimpse":{"draws":3,"losses":8,"wins":5},"fireworks/ember-1":{"draws":11,"losses":34,"wins":9},"gemini-3.1-pro-preview":{"draws":10,"losses":28,"wins":16},"gemini-4-argon":{"draws":0,"losses":24,"wins":2},"google/gemini-3.1-flash-lite":{"draws":11,"losses":15,"wins":16},"google/gemini-3.5-flash":{"draws":14,"losses":44,"wins":12},"google/gemini-3.5-flash-lite":{"draws":32,"losses":34,"wins":32},"google/gemini-3.6-flash":{"draws":20,"losses":75,"wins":9},"google/gemini-3.8-flash":{"draws":8,"losses":40,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":18,"wins":6},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":34,"wins":6},"gpt-5.4":{"draws":9,"losses":35,"wins":10},"gpt-5.4-mini":{"draws":9,"losses":17,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":36,"wins":13},"gpt-5.5":{"draws":12,"losses":36,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":28,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":47,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":33,"wins":6},"gpt-6-astra":{"draws":2,"losses":52,"wins":0},"gpt-6-luna":{"draws":12,"losses":33,"wins":9},"gpt-6-sol":{"draws":4,"losses":49,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":52,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":15,"wins":13},"inception/mercury-3":{"draws":2,"losses":14,"wins":4},"inclusionai/ling-3.0-flash":{"draws":12,"losses":13,"wins":9},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":39,"wins":15},"meta/muse-glimmer-30b":{"draws":18,"losses":17,"wins":15},"meta/muse-spark-1.2":{"draws":3,"losses":40,"wins":9},"meta/muse-spark-1.3":{"draws":4,"losses":48,"wins":2},"meta/muse-spark-open":{"draws":5,"losses":27,"wins":4},"meta/muse-wonder":{"draws":3,"losses":47,"wins":4},"minimax/minimax-m3":{"draws":3,"losses":17,"wins":10},"minimax/minimax-m3.1-flash":{"draws":5,"losses":13,"wins":6},"mistralai/mistral-large-4-0":{"draws":9,"losses":20,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":11,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":35,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":17,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":20,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":11,"wins":3},"o3":{"draws":13,"losses":61,"wins":14},"openai/gpt-oss-120b":{"draws":15,"losses":20,"wins":15},"poolside/laguna-s-2.1":{"draws":13,"losses":18,"wins":23},"qwen/qwen3.7-max":{"draws":11,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":45,"wins":3},"qwen/qwen3.8-27b":{"draws":3,"losses":25,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":18,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":41,"wins":4},"qwen/qwen3.8-max-0902":{"draws":8,"losses":41,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":14,"wins":3},"stealth/ox-alpha":{"draws":24,"losses":131,"wins":23},"stealth/space-bunny-alpha":{"draws":11,"losses":28,"wins":7},"stepfun/step-3.7-flash":{"draws":8,"losses":25,"wins":7},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":14,"losses":37,"wins":3},"thinkingmachines/inkling":{"draws":18,"losses":33,"wins":21},"thinkingmachines/inkling-small":{"draws":15,"losses":22,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":18,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":43,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":41,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":45,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":31,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":22,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":30,"losses":60,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":44,"wins":2},"z-ai/glm-5.3-flash":{"draws":6,"losses":36,"wins":12},"z-ai/glm-5.3-flashx":{"draws":9,"losses":40,"wins":5}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":63,"losses":71,"wins":62},"claude-fable-5":{"draws":36,"losses":166,"wins":14},"claude-fable-5-1":{"draws":8,"losses":231,"wins":1},"claude-haiku-5-5":{"draws":57,"losses":121,"wins":30},"claude-opus-4-5":{"draws":106,"losses":182,"wins":64},"claude-opus-4-8":{"draws":48,"losses":125,"wins":27},"claude-opus-5":{"draws":39,"losses":302,"wins":21},"claude-opus-5-5":{"draws":13,"losses":218,"wins":5},"claude-sonnet-5":{"draws":63,"losses":113,"wins":40},"claude-sonnet-5-5":{"draws":45,"losses":140,"wins":31},"cohere/north-mini-code":{"draws":21,"losses":25,"wins":34},"deepseek/deepseek-v4-flash":{"draws":82,"losses":89,"wins":89},"deepseek/deepseek-v4-pro":{"draws":53,"losses":100,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":91,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":70,"losses":121,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":80,"wins":19},"elorian/glimpse":{"draws":13,"losses":30,"wins":15},"fireworks/ember-1":{"draws":69,"losses":110,"wins":37},"gemini-3.1-pro-preview":{"draws":67,"losses":96,"wins":53},"gemini-4-argon":{"draws":10,"losses":97,"wins":3},"google/gemini-3.1-flash-lite":{"draws":46,"losses":26,"wins":74},"google/gemini-3.5-flash":{"draws":67,"losses":145,"wins":58},"google/gemini-3.5-flash-lite":{"draws":116,"losses":134,"wins":124},"google/gemini-3.6-flash":{"draws":99,"losses":256,"wins":57},"google/gemini-3.8-flash":{"draws":37,"losses":155,"wins":24},"google/gemma-4-31b-it":{"draws":58,"losses":22,"wins":46},"gpt-4.1":{"draws":22,"losses":34,"wins":16},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":8},"gpt-5":{"draws":58,"losses":91,"wins":41},"gpt-5.4":{"draws":54,"losses":121,"wins":31},"gpt-5.4-mini":{"draws":56,"losses":50,"wins":38},"gpt-5.4-nano":{"draws":51,"losses":94,"wins":81},"gpt-5.5":{"draws":69,"losses":106,"wins":21},"gpt-5.6-luna":{"draws":83,"losses":83,"wins":50},"gpt-5.6-sol":{"draws":29,"losses":167,"wins":20},"gpt-5.6-terra":{"draws":67,"losses":109,"wins":32},"gpt-6-astra":{"draws":11,"losses":200,"wins":5},"gpt-6-luna":{"draws":66,"losses":105,"wins":45},"gpt-6-sol":{"draws":32,"losses":168,"wins":16},"gpt-6.1-sol":{"draws":14,"losses":197,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":64,"losses":28,"wins":60},"inception/mercury-3":{"draws":28,"losses":34,"wins":16},"inclusionai/ling-3.0-flash":{"draws":63,"losses":42,"wins":53},"inclusionai/ling-3.1-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":66,"losses":76,"wins":92},"meta/muse-glimmer-30b":{"draws":82,"losses":46,"wins":58},"meta/muse-spark-1.2":{"draws":52,"losses":120,"wins":34},"meta/muse-spark-1.3":{"draws":41,"losses":151,"wins":24},"meta/muse-spark-open":{"draws":20,"losses":74,"wins":12},"meta/muse-wonder":{"draws":37,"losses":148,"wins":31},"minimax/minimax-m3":{"draws":36,"losses":42,"wins":42},"minimax/minimax-m3.1-flash":{"draws":27,"losses":51,"wins":36},"mistralai/mistral-large-4-0":{"draws":45,"losses":69,"wins":20},"mistralai/mistral-medium-3-5":{"draws":53,"losses":29,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":30,"wins":11},"moonshotai/kimi-k3":{"draws":59,"losses":105,"wins":42},"nex-agi/nex-n2-pro":{"draws":25,"losses":32,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":11,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":68,"losses":57,"wins":69},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":19,"wins":14},"o3":{"draws":45,"losses":180,"wins":81},"openai/gpt-oss-120b":{"draws":72,"losses":63,"wins":55},"poolside/laguna-s-2.1":{"draws":77,"losses":72,"wins":61},"qwen/qwen3.7-max":{"draws":54,"losses":48,"wins":28},"qwen/qwen3.7-plus":{"draws":33,"losses":36,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":69,"losses":115,"wins":32},"qwen/qwen3.8-27b":{"draws":38,"losses":81,"wins":35},"qwen/qwen3.8-flash":{"draws":46,"losses":68,"wins":30},"qwen/qwen3.8-max":{"draws":68,"losses":112,"wins":36},"qwen/qwen3.8-max-0902":{"draws":64,"losses":123,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":44,"wins":17},"stealth/ox-alpha":{"draws":170,"losses":400,"wins":126},"stealth/space-bunny-alpha":{"draws":58,"losses":71,"wins":39},"stepfun/step-3.7-flash":{"draws":35,"losses":57,"wins":66},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":35,"losses":43,"wins":38},"tencent/hy4-preview":{"draws":55,"losses":116,"wins":35},"thinkingmachines/inkling":{"draws":94,"losses":98,"wins":92},"thinkingmachines/inkling-small":{"draws":89,"losses":48,"wins":79},"unbiased/pareto-26.10":{"draws":4,"losses":50,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":71,"wins":1},"upstage/solar-mini4":{"draws":10,"losses":16,"wins":28},"x-ai/grok-4.5":{"draws":39,"losses":143,"wins":34},"x-ai/grok-4.6":{"draws":54,"losses":140,"wins":22},"x-ai/grok-4.7":{"draws":20,"losses":157,"wins":15},"x-ai/grok-build-0.1":{"draws":27,"losses":18,"wins":27},"xiaomi/mimo-v2.5":{"draws":117,"losses":108,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":36,"losses":45,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":31,"losses":83,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":95,"wins":24},"z-ai/glm-5.2":{"draws":151,"losses":179,"wins":102},"z-ai/glm-5.3":{"draws":44,"losses":150,"wins":12},"z-ai/glm-5.3-flash":{"draws":54,"losses":121,"wins":41},"z-ai/glm-5.3-flashx":{"draws":58,"losses":126,"wins":32}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":32,"wins":60},"claude-fable-5":{"draws":26,"losses":79,"wins":27},"claude-fable-5-1":{"draws":9,"losses":138,"wins":3},"claude-haiku-5-5":{"draws":35,"losses":50,"wins":41},"claude-opus-4-5":{"draws":60,"losses":78,"wins":76},"claude-opus-4-8":{"draws":28,"losses":56,"wins":36},"claude-opus-5":{"draws":26,"losses":175,"wins":31},"claude-opus-5-5":{"draws":11,"losses":128,"wins":5},"claude-sonnet-5":{"draws":40,"losses":46,"wins":46},"claude-sonnet-5-5":{"draws":32,"losses":67,"wins":33},"cohere/north-mini-code":{"draws":9,"losses":14,"wins":29},"deepseek/deepseek-v4-flash":{"draws":53,"losses":43,"wins":100},"deepseek/deepseek-v4-pro":{"draws":20,"losses":30,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":45,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":55,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":57,"wins":11},"elorian/glimpse":{"draws":14,"losses":22,"wins":10},"fireworks/ember-1":{"draws":39,"losses":53,"wins":40},"gemini-3.1-pro-preview":{"draws":33,"losses":46,"wins":53},"gemini-4-argon":{"draws":7,"losses":46,"wins":5},"google/gemini-3.1-flash-lite":{"draws":25,"losses":7,"wins":56},"google/gemini-3.5-flash":{"draws":41,"losses":70,"wins":55},"google/gemini-3.5-flash-lite":{"draws":61,"losses":65,"wins":106},"google/gemini-3.6-flash":{"draws":64,"losses":106,"wins":84},"google/gemini-3.8-flash":{"draws":27,"losses":72,"wins":33},"google/gemma-4-31b-it":{"draws":28,"losses":14,"wins":34},"gpt-4.1":{"draws":13,"losses":9,"wins":22},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":30,"losses":35,"wins":53},"gpt-5.4":{"draws":29,"losses":61,"wins":38},"gpt-5.4-mini":{"draws":32,"losses":23,"wins":33},"gpt-5.4-nano":{"draws":18,"losses":45,"wins":67},"gpt-5.5":{"draws":36,"losses":60,"wins":28},"gpt-5.6-luna":{"draws":43,"losses":37,"wins":52},"gpt-5.6-sol":{"draws":16,"losses":86,"wins":30},"gpt-5.6-terra":{"draws":40,"losses":42,"wins":44},"gpt-6-astra":{"draws":11,"losses":113,"wins":8},"gpt-6-luna":{"draws":34,"losses":56,"wins":42},"gpt-6-sol":{"draws":12,"losses":98,"wins":22},"gpt-6.1-sol":{"draws":8,"losses":116,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":37,"losses":8,"wins":45},"inception/mercury-3":{"draws":17,"losses":19,"wins":16},"inclusionai/ling-3.0-flash":{"draws":34,"losses":14,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":31,"losses":28,"wins":85},"meta/muse-glimmer-30b":{"draws":37,"losses":27,"wins":56},"meta/muse-spark-1.2":{"draws":24,"losses":59,"wins":45},"meta/muse-spark-1.3":{"draws":20,"losses":76,"wins":36},"meta/muse-spark-open":{"draws":19,"losses":34,"wins":19},"meta/muse-wonder":{"draws":23,"losses":79,"wins":30},"minimax/minimax-m3":{"draws":13,"losses":11,"wins":48},"minimax/minimax-m3.1-flash":{"draws":15,"losses":12,"wins":21},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":26},"mistralai/mistral-medium-3-5":{"draws":20,"losses":9,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":12,"wins":14},"moonshotai/kimi-k3":{"draws":28,"losses":56,"wins":44},"nex-agi/nex-n2-pro":{"draws":17,"losses":12,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":19,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":14,"wins":12},"o3":{"draws":22,"losses":70,"wins":92},"openai/gpt-oss-120b":{"draws":35,"losses":26,"wins":55},"poolside/laguna-s-2.1":{"draws":36,"losses":43,"wins":49},"qwen/qwen3.7-max":{"draws":25,"losses":15,"wins":36},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":60,"wins":36},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":31},"qwen/qwen3.8-flash":{"draws":22,"losses":36,"wins":30},"qwen/qwen3.8-max":{"draws":37,"losses":59,"wins":36},"qwen/qwen3.8-max-0902":{"draws":34,"losses":63,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":15,"wins":21},"stealth/ox-alpha":{"draws":106,"losses":204,"wins":132},"stealth/space-bunny-alpha":{"draws":31,"losses":28,"wins":47},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":55},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":24,"losses":18,"wins":30},"tencent/hy4-preview":{"draws":32,"losses":60,"wins":36},"thinkingmachines/inkling":{"draws":56,"losses":31,"wins":93},"thinkingmachines/inkling-small":{"draws":47,"losses":17,"wins":68},"unbiased/pareto-26.10":{"draws":1,"losses":22,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":43,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":22},"x-ai/grok-4.5":{"draws":34,"losses":59,"wins":39},"x-ai/grok-4.6":{"draws":33,"losses":73,"wins":26},"x-ai/grok-4.7":{"draws":10,"losses":85,"wins":21},"x-ai/grok-build-0.1":{"draws":18,"losses":9,"wins":17},"xiaomi/mimo-v2.5":{"draws":73,"losses":31,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":22,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":35,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":47,"wins":25},"z-ai/glm-5.2":{"draws":90,"losses":75,"wins":99},"z-ai/glm-5.3":{"draws":23,"losses":78,"wins":25},"z-ai/glm-5.3-flash":{"draws":22,"losses":74,"wins":36},"z-ai/glm-5.3-flashx":{"draws":32,"losses":60,"wins":40}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":34,"wins":53},"claude-fable-5":{"draws":19,"losses":86,"wins":27},"claude-fable-5-1":{"draws":4,"losses":144,"wins":2},"claude-haiku-5-5":{"draws":34,"losses":63,"wins":29},"claude-opus-4-5":{"draws":61,"losses":77,"wins":76},"claude-opus-4-8":{"draws":28,"losses":53,"wins":39},"claude-opus-5":{"draws":20,"losses":175,"wins":27},"claude-opus-5-5":{"draws":6,"losses":134,"wins":4},"claude-sonnet-5":{"draws":43,"losses":41,"wins":48},"claude-sonnet-5-5":{"draws":22,"losses":77,"wins":33},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":32},"deepseek/deepseek-v4-flash":{"draws":58,"losses":49,"wins":91},"deepseek/deepseek-v4-pro":{"draws":36,"losses":41,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":33,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":63,"wins":32},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":45,"wins":17},"elorian/glimpse":{"draws":8,"losses":15,"wins":15},"fireworks/ember-1":{"draws":34,"losses":56,"wins":42},"gemini-3.1-pro-preview":{"draws":34,"losses":44,"wins":54},"gemini-4-argon":{"draws":5,"losses":56,"wins":1},"google/gemini-3.1-flash-lite":{"draws":25,"losses":10,"wins":53},"google/gemini-3.5-flash":{"draws":43,"losses":72,"wins":51},"google/gemini-3.5-flash-lite":{"draws":71,"losses":49,"wins":112},"google/gemini-3.6-flash":{"draws":58,"losses":118,"wins":78},"google/gemini-3.8-flash":{"draws":31,"losses":67,"wins":34},"google/gemma-4-31b-it":{"draws":31,"losses":7,"wins":38},"gpt-4.1":{"draws":13,"losses":11,"wins":20},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":27,"losses":44,"wins":45},"gpt-5.4":{"draws":26,"losses":65,"wins":37},"gpt-5.4-mini":{"draws":33,"losses":17,"wins":38},"gpt-5.4-nano":{"draws":26,"losses":41,"wins":63},"gpt-5.5":{"draws":35,"losses":51,"wins":36},"gpt-5.6-luna":{"draws":43,"losses":38,"wins":51},"gpt-5.6-sol":{"draws":17,"losses":88,"wins":27},"gpt-5.6-terra":{"draws":40,"losses":48,"wins":40},"gpt-6-astra":{"draws":8,"losses":123,"wins":1},"gpt-6-luna":{"draws":36,"losses":49,"wins":47},"gpt-6-sol":{"draws":13,"losses":99,"wins":20},"gpt-6.1-sol":{"draws":8,"losses":121,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":34,"losses":12,"wins":46},"inception/mercury-3":{"draws":13,"losses":22,"wins":17},"inclusionai/ling-3.0-flash":{"draws":38,"losses":16,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":42,"losses":33,"wins":69},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":58},"meta/muse-spark-1.2":{"draws":25,"losses":61,"wins":40},"meta/muse-spark-1.3":{"draws":27,"losses":66,"wins":39},"meta/muse-spark-open":{"draws":6,"losses":32,"wins":20},"meta/muse-wonder":{"draws":27,"losses":78,"wins":27},"minimax/minimax-m3":{"draws":17,"losses":13,"wins":40},"minimax/minimax-m3.1-flash":{"draws":14,"losses":26,"wins":32},"mistralai/mistral-large-4-0":{"draws":30,"losses":24,"wins":28},"mistralai/mistral-medium-3-5":{"draws":23,"losses":12,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":37,"losses":39,"wins":50},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":15,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":17,"wins":12},"o3":{"draws":29,"losses":55,"wins":100},"openai/gpt-oss-120b":{"draws":36,"losses":27,"wins":51},"poolside/laguna-s-2.1":{"draws":39,"losses":32,"wins":53},"qwen/qwen3.7-max":{"draws":27,"losses":17,"wins":32},"qwen/qwen3.7-plus":{"draws":17,"losses":20,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":56,"wins":43},"qwen/qwen3.8-27b":{"draws":26,"losses":38,"wins":30},"qwen/qwen3.8-flash":{"draws":27,"losses":30,"wins":31},"qwen/qwen3.8-max":{"draws":41,"losses":52,"wins":39},"qwen/qwen3.8-max-0902":{"draws":39,"losses":54,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":13,"wins":14},"stealth/ox-alpha":{"draws":110,"losses":182,"wins":148},"stealth/space-bunny-alpha":{"draws":31,"losses":27,"wins":46},"stepfun/step-3.7-flash":{"draws":21,"losses":20,"wins":55},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":26,"losses":20,"wins":24},"tencent/hy4-preview":{"draws":29,"losses":56,"wins":43},"thinkingmachines/inkling":{"draws":58,"losses":43,"wins":75},"thinkingmachines/inkling-small":{"draws":43,"losses":24,"wins":65},"unbiased/pareto-26.10":{"draws":3,"losses":24,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":3,"wins":26},"x-ai/grok-4.5":{"draws":29,"losses":60,"wins":43},"x-ai/grok-4.6":{"draws":41,"losses":62,"wins":29},"x-ai/grok-4.7":{"draws":9,"losses":83,"wins":22},"x-ai/grok-build-0.1":{"draws":19,"losses":4,"wins":21},"xiaomi/mimo-v2.5":{"draws":69,"losses":37,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":20,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":31,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":48,"wins":27},"z-ai/glm-5.2":{"draws":89,"losses":81,"wins":94},"z-ai/glm-5.3":{"draws":24,"losses":77,"wins":25},"z-ai/glm-5.3-flash":{"draws":21,"losses":73,"wins":38},"z-ai/glm-5.3-flashx":{"draws":30,"losses":63,"wins":39}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":32,"wins":60},"claude-fable-5":{"draws":36,"losses":73,"wins":35},"claude-fable-5-1":{"draws":17,"losses":133,"wins":12},"claude-haiku-5-5":{"draws":43,"losses":56,"wins":39},"claude-opus-4-5":{"draws":62,"losses":68,"wins":104},"claude-opus-4-8":{"draws":32,"losses":47,"wins":53},"claude-opus-5":{"draws":38,"losses":171,"wins":37},"claude-opus-5-5":{"draws":9,"losses":132,"wins":15},"claude-sonnet-5":{"draws":44,"losses":47,"wins":53},"claude-sonnet-5-5":{"draws":32,"losses":72,"wins":40},"cohere/north-mini-code":{"draws":13,"losses":8,"wins":33},"deepseek/deepseek-v4-flash":{"draws":70,"losses":25,"wins":121},"deepseek/deepseek-v4-pro":{"draws":35,"losses":42,"wins":55},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":32,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":37,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":37,"wins":17},"elorian/glimpse":{"draws":10,"losses":18,"wins":14},"fireworks/ember-1":{"draws":46,"losses":53,"wins":45},"gemini-3.1-pro-preview":{"draws":41,"losses":50,"wins":53},"gemini-4-argon":{"draws":4,"losses":55,"wins":7},"google/gemini-3.1-flash-lite":{"draws":35,"losses":8,"wins":53},"google/gemini-3.5-flash":{"draws":52,"losses":54,"wins":74},"google/gemini-3.5-flash-lite":{"draws":76,"losses":51,"wins":125},"google/gemini-3.6-flash":{"draws":76,"losses":112,"wins":88},"google/gemini-3.8-flash":{"draws":36,"losses":62,"wins":46},"google/gemma-4-31b-it":{"draws":34,"losses":12,"wins":38},"gpt-4.1":{"draws":13,"losses":11,"wins":24},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":41,"losses":29,"wins":56},"gpt-5.4":{"draws":42,"losses":53,"wins":43},"gpt-5.4-mini":{"draws":37,"losses":20,"wins":39},"gpt-5.4-nano":{"draws":37,"losses":35,"wins":72},"gpt-5.5":{"draws":45,"losses":42,"wins":45},"gpt-5.6-luna":{"draws":54,"losses":26,"wins":64},"gpt-5.6-sol":{"draws":26,"losses":75,"wins":43},"gpt-5.6-terra":{"draws":55,"losses":34,"wins":49},"gpt-6-astra":{"draws":16,"losses":122,"wins":6},"gpt-6-luna":{"draws":45,"losses":39,"wins":60},"gpt-6-sol":{"draws":26,"losses":86,"wins":32},"gpt-6.1-sol":{"draws":14,"losses":115,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":45,"losses":9,"wins":48},"inception/mercury-3":{"draws":15,"losses":10,"wins":27},"inclusionai/ling-3.0-flash":{"draws":44,"losses":9,"wins":49},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":36,"losses":35,"wins":85},"meta/muse-glimmer-30b":{"draws":52,"losses":14,"wins":60},"meta/muse-spark-1.2":{"draws":33,"losses":52,"wins":53},"meta/muse-spark-1.3":{"draws":30,"losses":62,"wins":52},"meta/muse-spark-open":{"draws":7,"losses":19,"wins":22},"meta/muse-wonder":{"draws":37,"losses":71,"wins":36},"minimax/minimax-m3":{"draws":19,"losses":17,"wins":42},"minimax/minimax-m3.1-flash":{"draws":18,"losses":15,"wins":35},"mistralai/mistral-large-4-0":{"draws":33,"losses":26,"wins":31},"mistralai/mistral-medium-3-5":{"draws":30,"losses":9,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":15},"moonshotai/kimi-k3":{"draws":40,"losses":41,"wins":57},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":50},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":22,"wins":58},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":9,"wins":18},"o3":{"draws":39,"losses":63,"wins":96},"openai/gpt-oss-120b":{"draws":40,"losses":24,"wins":62},"poolside/laguna-s-2.1":{"draws":59,"losses":22,"wins":57},"qwen/qwen3.7-max":{"draws":30,"losses":19,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":7,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":50,"wins":57},"qwen/qwen3.8-27b":{"draws":24,"losses":29,"wins":49},"qwen/qwen3.8-flash":{"draws":35,"losses":20,"wins":41},"qwen/qwen3.8-max":{"draws":42,"losses":48,"wins":54},"qwen/qwen3.8-max-0902":{"draws":49,"losses":43,"wins":52},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":24,"wins":31},"stealth/ox-alpha":{"draws":110,"losses":181,"wins":182},"stealth/space-bunny-alpha":{"draws":36,"losses":25,"wins":53},"stepfun/step-3.7-flash":{"draws":24,"losses":16,"wins":62},"stepfun/step-5-preview":{"draws":4,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":26,"losses":16,"wins":36},"tencent/hy4-preview":{"draws":41,"losses":56,"wins":41},"thinkingmachines/inkling":{"draws":63,"losses":30,"wins":99},"thinkingmachines/inkling-small":{"draws":45,"losses":25,"wins":74},"unbiased/pareto-26.10":{"draws":3,"losses":28,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":43,"wins":3},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":31,"losses":65,"wins":48},"x-ai/grok-4.6":{"draws":40,"losses":61,"wins":43},"x-ai/grok-4.7":{"draws":11,"losses":83,"wins":32},"x-ai/grok-build-0.1":{"draws":16,"losses":5,"wins":27},"xiaomi/mimo-v2.5":{"draws":75,"losses":29,"wins":118},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":20,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":32,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":23,"losses":43,"wins":30},"z-ai/glm-5.2":{"draws":103,"losses":63,"wins":122},"z-ai/glm-5.3":{"draws":28,"losses":83,"wins":27},"z-ai/glm-5.3-flash":{"draws":28,"losses":61,"wins":55},"z-ai/glm-5.3-flashx":{"draws":40,"losses":61,"wins":43}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":49},"claude-fable-5":{"draws":16,"losses":46,"wins":34},"claude-fable-5-1":{"draws":4,"losses":63,"wins":15},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":32},"claude-opus-4-5":{"draws":22,"losses":22,"wins":78},"claude-opus-4-8":{"draws":12,"losses":22,"wins":34},"claude-opus-5":{"draws":21,"losses":94,"wins":35},"claude-opus-5-5":{"draws":4,"losses":59,"wins":13},"claude-sonnet-5":{"draws":19,"losses":19,"wins":50},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":34},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":23},"deepseek/deepseek-v4-flash":{"draws":25,"losses":19,"wins":80},"deepseek/deepseek-v4-pro":{"draws":16,"losses":11,"wins":57},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":17,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":17,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":31,"wins":31},"elorian/glimpse":{"draws":17,"losses":24,"wins":33},"fireworks/ember-1":{"draws":23,"losses":15,"wins":46},"gemini-3.1-pro-preview":{"draws":19,"losses":18,"wins":53},"gemini-4-argon":{"draws":18,"losses":100,"wins":16},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":39},"google/gemini-3.5-flash":{"draws":15,"losses":28,"wins":53},"google/gemini-3.5-flash-lite":{"draws":23,"losses":12,"wins":115},"google/gemini-3.6-flash":{"draws":23,"losses":54,"wins":73},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":43},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":31},"gpt-4.1":{"draws":7,"losses":2,"wins":17},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":16,"losses":14,"wins":40},"gpt-5.4":{"draws":16,"losses":27,"wins":33},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":34},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":55},"gpt-5.5":{"draws":27,"losses":26,"wins":25},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":54},"gpt-5.6-sol":{"draws":16,"losses":37,"wins":25},"gpt-5.6-terra":{"draws":18,"losses":17,"wins":41},"gpt-6-astra":{"draws":6,"losses":68,"wins":4},"gpt-6-luna":{"draws":15,"losses":17,"wins":46},"gpt-6-sol":{"draws":6,"losses":45,"wins":19},"gpt-6.1-sol":{"draws":3,"losses":54,"wins":17},"inception/mercury-2.5-preview":{"draws":17,"losses":3,"wins":28},"inception/mercury-3":{"draws":22,"losses":15,"wins":55},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":44},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":13,"losses":13,"wins":58},"meta/muse-glimmer-30b":{"draws":18,"losses":8,"wins":46},"meta/muse-spark-1.2":{"draws":11,"losses":22,"wins":35},"meta/muse-spark-1.3":{"draws":7,"losses":36,"wins":43},"meta/muse-spark-open":{"draws":27,"losses":37,"wins":64},"meta/muse-wonder":{"draws":20,"losses":27,"wins":31},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":32},"minimax/minimax-m3.1-flash":{"draws":29,"losses":22,"wins":61},"mistralai/mistral-large-4-0":{"draws":7,"losses":12,"wins":29},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k3":{"draws":8,"losses":22,"wins":44},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":29},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":2,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":54},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":11,"wins":33},"o3":{"draws":9,"losses":31,"wins":80},"openai/gpt-oss-120b":{"draws":23,"losses":11,"wins":60},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":60},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":28},"qwen/qwen3.7-plus":{"draws":5,"losses":9,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":25,"wins":46},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":31},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":38},"qwen/qwen3.8-max":{"draws":21,"losses":18,"wins":49},"qwen/qwen3.8-max-0902":{"draws":15,"losses":23,"wins":38},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":27,"wins":70},"stealth/ox-alpha":{"draws":41,"losses":93,"wins":146},"stealth/space-bunny-alpha":{"draws":15,"losses":6,"wins":45},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":37},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":18,"losses":7,"wins":31},"tencent/hy4-preview":{"draws":13,"losses":26,"wins":47},"thinkingmachines/inkling":{"draws":28,"losses":9,"wins":75},"thinkingmachines/inkling-small":{"draws":17,"losses":4,"wins":65},"unbiased/pareto-26.10":{"draws":6,"losses":39,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":6},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":21},"x-ai/grok-4.5":{"draws":15,"losses":35,"wins":36},"x-ai/grok-4.6":{"draws":19,"losses":25,"wins":30},"x-ai/grok-4.7":{"draws":9,"losses":39,"wins":20},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":19},"xiaomi/mimo-v2.5":{"draws":25,"losses":9,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":13,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":7,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":23,"wins":22},"z-ai/glm-5.2":{"draws":24,"losses":28,"wins":114},"z-ai/glm-5.3":{"draws":9,"losses":37,"wins":28},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":51},"z-ai/glm-5.3-flashx":{"draws":7,"losses":24,"wins":43}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":13,"wins":18},"claude-fable-5":{"draws":4,"losses":18,"wins":14},"claude-fable-5-1":{"draws":4,"losses":40,"wins":2},"claude-haiku-5-5":{"draws":5,"losses":17,"wins":16},"claude-opus-4-5":{"draws":10,"losses":17,"wins":31},"claude-opus-4-8":{"draws":7,"losses":15,"wins":20},"claude-opus-5":{"draws":6,"losses":45,"wins":13},"claude-opus-5-5":{"draws":3,"losses":36,"wins":1},"claude-sonnet-5":{"draws":10,"losses":10,"wins":10},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":13,"losses":15,"wins":30},"deepseek/deepseek-v4-pro":{"draws":14,"losses":10,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":33,"wins":24},"elorian/glimpse":{"draws":2,"losses":7,"wins":7},"fireworks/ember-1":{"draws":6,"losses":10,"wins":8},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":19},"gemini-4-argon":{"draws":8,"losses":59,"wins":11},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":11,"losses":24,"wins":17},"google/gemini-3.5-flash-lite":{"draws":13,"losses":16,"wins":31},"google/gemini-3.6-flash":{"draws":15,"losses":31,"wins":26},"google/gemini-3.8-flash":{"draws":10,"losses":27,"wins":15},"google/gemma-4-31b-it":{"draws":11,"losses":2,"wins":7},"gpt-4.1":{"draws":4,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":10,"wins":17},"gpt-5.4":{"draws":6,"losses":18,"wins":12},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":11,"wins":18},"gpt-5.5":{"draws":7,"losses":28,"wins":13},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":23},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":12},"gpt-5.6-terra":{"draws":8,"losses":11,"wins":15},"gpt-6-astra":{"draws":1,"losses":32,"wins":3},"gpt-6-luna":{"draws":8,"losses":16,"wins":18},"gpt-6-sol":{"draws":6,"losses":23,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":14},"inception/mercury-3":{"draws":6,"losses":19,"wins":23},"inclusionai/ling-3.0-flash":{"draws":7,"losses":7,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":12,"wins":16},"meta/muse-glimmer-30b":{"draws":8,"losses":13,"wins":13},"meta/muse-spark-1.2":{"draws":5,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":9},"meta/muse-spark-open":{"draws":13,"losses":25,"wins":34},"meta/muse-wonder":{"draws":12,"losses":19,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":13},"minimax/minimax-m3.1-flash":{"draws":18,"losses":15,"wins":33},"mistralai/mistral-large-4-0":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":10,"losses":12,"wins":16},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":6,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":10,"wins":16},"o3":{"draws":6,"losses":20,"wins":26},"openai/gpt-oss-120b":{"draws":10,"losses":11,"wins":19},"poolside/laguna-s-2.1":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.7-max":{"draws":4,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":5,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":18,"wins":11},"qwen/qwen3.8-max-0902":{"draws":15,"losses":11,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":19,"wins":33},"stealth/ox-alpha":{"draws":35,"losses":66,"wins":41},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":11},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":1,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":17,"wins":15},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":24},"thinkingmachines/inkling-small":{"draws":10,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":17,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":13,"wins":15},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":13,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":10},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":11,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":19,"losses":26,"wins":33},"z-ai/glm-5.3":{"draws":8,"losses":22,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":16},"z-ai/glm-5.3-flashx":{"draws":7,"losses":14,"wins":9}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":24,"wins":68},"claude-fable-5":{"draws":29,"losses":93,"wins":22},"claude-fable-5-1":{"draws":5,"losses":149,"wins":8},"claude-haiku-5-5":{"draws":36,"losses":64,"wins":38},"claude-opus-4-5":{"draws":81,"losses":63,"wins":90},"claude-opus-4-8":{"draws":44,"losses":51,"wins":37},"claude-opus-5":{"draws":27,"losses":175,"wins":44},"claude-opus-5-5":{"draws":8,"losses":137,"wins":11},"claude-sonnet-5":{"draws":44,"losses":40,"wins":60},"claude-sonnet-5-5":{"draws":29,"losses":72,"wins":43},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":34},"deepseek/deepseek-v4-flash":{"draws":69,"losses":37,"wins":110},"deepseek/deepseek-v4-pro":{"draws":39,"losses":40,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":42,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":45,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":46,"wins":15},"elorian/glimpse":{"draws":6,"losses":8,"wins":10},"fireworks/ember-1":{"draws":28,"losses":34,"wins":34},"gemini-3.1-pro-preview":{"draws":40,"losses":40,"wins":64},"gemini-4-argon":{"draws":7,"losses":41,"wins":2},"google/gemini-3.1-flash-lite":{"draws":22,"losses":5,"wins":69},"google/gemini-3.5-flash":{"draws":51,"losses":60,"wins":69},"google/gemini-3.5-flash-lite":{"draws":93,"losses":46,"wins":113},"google/gemini-3.6-flash":{"draws":79,"losses":96,"wins":101},"google/gemini-3.8-flash":{"draws":35,"losses":61,"wins":48},"google/gemma-4-31b-it":{"draws":31,"losses":12,"wins":41},"gpt-4.1":{"draws":14,"losses":15,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":8},"gpt-5":{"draws":36,"losses":30,"wins":60},"gpt-5.4":{"draws":40,"losses":60,"wins":38},"gpt-5.4-mini":{"draws":36,"losses":15,"wins":45},"gpt-5.4-nano":{"draws":35,"losses":31,"wins":78},"gpt-5.5":{"draws":42,"losses":49,"wins":41},"gpt-5.6-luna":{"draws":50,"losses":40,"wins":54},"gpt-5.6-sol":{"draws":23,"losses":83,"wins":38},"gpt-5.6-terra":{"draws":44,"losses":36,"wins":58},"gpt-6-astra":{"draws":10,"losses":128,"wins":6},"gpt-6-luna":{"draws":39,"losses":41,"wins":64},"gpt-6-sol":{"draws":21,"losses":100,"wins":23},"gpt-6.1-sol":{"draws":9,"losses":118,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":44,"losses":6,"wins":52},"inception/mercury-3":{"draws":18,"losses":20,"wins":14},"inclusionai/ling-3.0-flash":{"draws":44,"losses":4,"wins":54},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":45,"losses":22,"wins":89},"meta/muse-glimmer-30b":{"draws":44,"losses":15,"wins":67},"meta/muse-spark-1.2":{"draws":37,"losses":48,"wins":53},"meta/muse-spark-1.3":{"draws":39,"losses":63,"wins":42},"meta/muse-spark-open":{"draws":16,"losses":31,"wins":21},"meta/muse-wonder":{"draws":38,"losses":76,"wins":30},"minimax/minimax-m3":{"draws":19,"losses":5,"wins":54},"minimax/minimax-m3.1-flash":{"draws":17,"losses":10,"wins":31},"mistralai/mistral-large-4-0":{"draws":26,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":27,"losses":6,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":45,"losses":37,"wins":56},"nex-agi/nex-n2-pro":{"draws":19,"losses":9,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":18,"wins":59},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":5,"wins":15},"o3":{"draws":40,"losses":48,"wins":110},"openai/gpt-oss-120b":{"draws":48,"losses":14,"wins":64},"poolside/laguna-s-2.1":{"draws":52,"losses":22,"wins":64},"qwen/qwen3.7-max":{"draws":26,"losses":19,"wins":39},"qwen/qwen3.7-plus":{"draws":23,"losses":11,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":47,"wins":47},"qwen/qwen3.8-27b":{"draws":29,"losses":38,"wins":35},"qwen/qwen3.8-flash":{"draws":34,"losses":29,"wins":33},"qwen/qwen3.8-max":{"draws":44,"losses":42,"wins":58},"qwen/qwen3.8-max-0902":{"draws":44,"losses":58,"wins":42},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":37,"wins":28},"stealth/ox-alpha":{"draws":123,"losses":180,"wins":171},"stealth/space-bunny-alpha":{"draws":36,"losses":23,"wins":55},"stepfun/step-3.7-flash":{"draws":23,"losses":18,"wins":61},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":30,"losses":12,"wins":36},"tencent/hy4-preview":{"draws":42,"losses":54,"wins":42},"thinkingmachines/inkling":{"draws":60,"losses":25,"wins":107},"thinkingmachines/inkling-small":{"draws":50,"losses":17,"wins":77},"unbiased/pareto-26.10":{"draws":2,"losses":28,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":23},"x-ai/grok-4.5":{"draws":33,"losses":71,"wins":40},"x-ai/grok-4.6":{"draws":40,"losses":61,"wins":43},"x-ai/grok-4.7":{"draws":11,"losses":88,"wins":27},"x-ai/grok-build-0.1":{"draws":18,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":83,"losses":27,"wins":112},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":18,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":45,"wins":30},"z-ai/glm-5.2":{"draws":94,"losses":66,"wins":128},"z-ai/glm-5.3":{"draws":26,"losses":85,"wins":27},"z-ai/glm-5.3-flash":{"draws":28,"losses":70,"wins":46},"z-ai/glm-5.3-flashx":{"draws":35,"losses":59,"wins":50}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":38,"wins":58},"claude-fable-5":{"draws":28,"losses":85,"wins":31},"claude-fable-5-1":{"draws":6,"losses":150,"wins":6},"claude-haiku-5-5":{"draws":32,"losses":60,"wins":46},"claude-opus-4-5":{"draws":61,"losses":96,"wins":77},"claude-opus-4-8":{"draws":35,"losses":62,"wins":35},"claude-opus-5":{"draws":23,"losses":185,"wins":38},"claude-opus-5-5":{"draws":9,"losses":137,"wins":10},"claude-sonnet-5":{"draws":43,"losses":51,"wins":50},"claude-sonnet-5-5":{"draws":22,"losses":83,"wins":39},"cohere/north-mini-code":{"draws":10,"losses":16,"wins":28},"deepseek/deepseek-v4-flash":{"draws":67,"losses":53,"wins":96},"deepseek/deepseek-v4-pro":{"draws":33,"losses":53,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":54,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":53,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":19,"losses":53,"wins":18},"elorian/glimpse":{"draws":9,"losses":19,"wins":14},"fireworks/ember-1":{"draws":40,"losses":64,"wins":40},"gemini-3.1-pro-preview":{"draws":26,"losses":35,"wins":35},"gemini-4-argon":{"draws":4,"losses":46,"wins":4},"google/gemini-3.1-flash-lite":{"draws":22,"losses":20,"wins":54},"google/gemini-3.5-flash":{"draws":42,"losses":79,"wins":59},"google/gemini-3.5-flash-lite":{"draws":83,"losses":64,"wins":105},"google/gemini-3.6-flash":{"draws":64,"losses":125,"wins":87},"google/gemini-3.8-flash":{"draws":28,"losses":82,"wins":34},"google/gemma-4-31b-it":{"draws":30,"losses":15,"wins":39},"gpt-4.1":{"draws":15,"losses":15,"wins":18},"gpt-4.1-nano":{"draws":11,"losses":3,"wins":4},"gpt-5":{"draws":41,"losses":35,"wins":50},"gpt-5.4":{"draws":30,"losses":66,"wins":42},"gpt-5.4-mini":{"draws":37,"losses":25,"wins":34},"gpt-5.4-nano":{"draws":36,"losses":40,"wins":68},"gpt-5.5":{"draws":38,"losses":62,"wins":32},"gpt-5.6-luna":{"draws":42,"losses":46,"wins":56},"gpt-5.6-sol":{"draws":18,"losses":96,"wins":30},"gpt-5.6-terra":{"draws":47,"losses":44,"wins":47},"gpt-6-astra":{"draws":10,"losses":130,"wins":4},"gpt-6-luna":{"draws":36,"losses":46,"wins":62},"gpt-6-sol":{"draws":18,"losses":99,"wins":27},"gpt-6.1-sol":{"draws":8,"losses":126,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":40,"losses":22,"wins":40},"inception/mercury-3":{"draws":20,"losses":28,"wins":12},"inclusionai/ling-3.0-flash":{"draws":39,"losses":10,"wins":53},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":37,"losses":45,"wins":74},"meta/muse-glimmer-30b":{"draws":49,"losses":16,"wins":61},"meta/muse-spark-1.2":{"draws":33,"losses":58,"wins":47},"meta/muse-spark-1.3":{"draws":26,"losses":78,"wins":40},"meta/muse-spark-open":{"draws":9,"losses":25,"wins":20},"meta/muse-wonder":{"draws":26,"losses":94,"wins":24},"minimax/minimax-m3":{"draws":19,"losses":22,"wins":37},"minimax/minimax-m3.1-flash":{"draws":25,"losses":19,"wins":28},"mistralai/mistral-large-4-0":{"draws":21,"losses":35,"wins":34},"mistralai/mistral-medium-3-5":{"draws":32,"losses":11,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":17},"moonshotai/kimi-k3":{"draws":36,"losses":61,"wins":41},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":41},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":29,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":13,"wins":14},"o3":{"draws":31,"losses":91,"wins":76},"openai/gpt-oss-120b":{"draws":42,"losses":30,"wins":54},"poolside/laguna-s-2.1":{"draws":47,"losses":32,"wins":59},"qwen/qwen3.7-max":{"draws":26,"losses":29,"wins":29},"qwen/qwen3.7-plus":{"draws":23,"losses":14,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":63,"wins":45},"qwen/qwen3.8-27b":{"draws":23,"losses":47,"wins":32},"qwen/qwen3.8-flash":{"draws":36,"losses":30,"wins":30},"qwen/qwen3.8-max":{"draws":43,"losses":56,"wins":45},"qwen/qwen3.8-max-0902":{"draws":40,"losses":65,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":18,"wins":18},"stealth/ox-alpha":{"draws":105,"losses":224,"wins":145},"stealth/space-bunny-alpha":{"draws":35,"losses":35,"wins":44},"stepfun/step-3.7-flash":{"draws":21,"losses":32,"wins":49},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":22,"losses":22,"wins":34},"tencent/hy4-preview":{"draws":33,"losses":65,"wins":40},"thinkingmachines/inkling":{"draws":57,"losses":48,"wins":87},"thinkingmachines/inkling-small":{"draws":45,"losses":28,"wins":71},"unbiased/pareto-26.10":{"draws":3,"losses":20,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":13,"wins":18},"x-ai/grok-4.5":{"draws":31,"losses":73,"wins":40},"x-ai/grok-4.6":{"draws":40,"losses":76,"wins":28},"x-ai/grok-4.7":{"draws":13,"losses":90,"wins":23},"x-ai/grok-build-0.1":{"draws":17,"losses":12,"wins":19},"xiaomi/mimo-v2.5":{"draws":73,"losses":49,"wins":100},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":25,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":42,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":56,"wins":24},"z-ai/glm-5.2":{"draws":85,"losses":94,"wins":109},"z-ai/glm-5.3":{"draws":25,"losses":83,"wins":30},"z-ai/glm-5.3-flash":{"draws":36,"losses":66,"wins":42},"z-ai/glm-5.3-flashx":{"draws":34,"losses":73,"wins":37}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":60},"claude-fable-5":{"draws":10,"losses":15,"wins":53},"claude-fable-5-1":{"draws":6,"losses":45,"wins":27},"claude-haiku-5-5":{"draws":9,"losses":10,"wins":35},"claude-opus-4-5":{"draws":8,"losses":10,"wins":108},"claude-opus-4-8":{"draws":3,"losses":11,"wins":48},"claude-opus-5":{"draws":16,"losses":38,"wins":46},"claude-opus-5-5":{"draws":3,"losses":44,"wins":29},"claude-sonnet-5":{"draws":4,"losses":2,"wins":60},"claude-sonnet-5-5":{"draws":9,"losses":25,"wins":48},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":24},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":97},"deepseek/deepseek-v4-pro":{"draws":7,"losses":5,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":1,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":7,"wins":55},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":16,"wins":100},"elorian/glimpse":{"draws":8,"losses":11,"wins":59},"fireworks/ember-1":{"draws":7,"losses":2,"wins":41},"gemini-3.1-pro-preview":{"draws":4,"losses":4,"wins":46},"gemini-4-argon":{"draws":14,"losses":41,"wins":41},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":39},"google/gemini-3.5-flash":{"draws":8,"losses":2,"wins":102},"google/gemini-3.5-flash-lite":{"draws":6,"losses":5,"wins":119},"google/gemini-3.6-flash":{"draws":11,"losses":16,"wins":103},"google/gemini-3.8-flash":{"draws":2,"losses":10,"wins":54},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":41},"gpt-4.1":{"draws":2,"losses":0,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":14},"gpt-5":{"draws":4,"losses":5,"wins":51},"gpt-5.4":{"draws":3,"losses":10,"wins":43},"gpt-5.4-mini":{"draws":8,"losses":0,"wins":40},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":67},"gpt-5.5":{"draws":6,"losses":8,"wins":42},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":46},"gpt-5.6-sol":{"draws":7,"losses":19,"wins":52},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":51},"gpt-6-astra":{"draws":9,"losses":43,"wins":18},"gpt-6-luna":{"draws":4,"losses":6,"wins":70},"gpt-6-sol":{"draws":7,"losses":25,"wins":34},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":24},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":45},"inception/mercury-3":{"draws":11,"losses":8,"wins":75},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":44},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":64},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":58},"meta/muse-spark-1.2":{"draws":9,"losses":6,"wins":45},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":56},"meta/muse-spark-open":{"draws":11,"losses":19,"wins":104},"meta/muse-wonder":{"draws":3,"losses":7,"wins":46},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":40},"minimax/minimax-m3.1-flash":{"draws":13,"losses":10,"wins":97},"mistralai/mistral-large-4-0":{"draws":2,"losses":4,"wins":24},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":49},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":53},"o3":{"draws":0,"losses":5,"wins":81},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":51},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":57},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":41},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":8,"wins":52},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":37},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":24},"qwen/qwen3.8-max":{"draws":3,"losses":6,"wins":47},"qwen/qwen3.8-max-0902":{"draws":4,"losses":5,"wins":43},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":13,"wins":112},"stealth/ox-alpha":{"draws":27,"losses":23,"wins":148},"stealth/space-bunny-alpha":{"draws":4,"losses":4,"wins":44},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":38},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":40},"tencent/hy4-preview":{"draws":8,"losses":9,"wins":47},"thinkingmachines/inkling":{"draws":7,"losses":5,"wins":68},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":64},"unbiased/pareto-26.10":{"draws":4,"losses":31,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":5},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":48},"x-ai/grok-4.6":{"draws":14,"losses":12,"wins":54},"x-ai/grok-4.7":{"draws":10,"losses":12,"wins":34},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":27},"xiaomi/mimo-v2.5":{"draws":5,"losses":1,"wins":84},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":10,"wins":40},"z-ai/glm-5.2":{"draws":10,"losses":9,"wins":115},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":39},"z-ai/glm-5.3-flash":{"draws":8,"losses":10,"wins":46},"z-ai/glm-5.3-flashx":{"draws":5,"losses":8,"wins":57}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":40,"wins":19},"claude-fable-5":{"draws":12,"losses":81,"wins":3},"claude-fable-5-1":{"draws":5,"losses":101,"wins":0},"claude-haiku-5-5":{"draws":22,"losses":66,"wins":8},"claude-opus-4-5":{"draws":38,"losses":115,"wins":7},"claude-opus-4-8":{"draws":20,"losses":71,"wins":5},"claude-opus-5":{"draws":16,"losses":126,"wins":8},"claude-opus-5-5":{"draws":8,"losses":96,"wins":0},"claude-sonnet-5":{"draws":29,"losses":60,"wins":7},"claude-sonnet-5-5":{"draws":15,"losses":69,"wins":12},"cohere/north-mini-code":{"draws":11,"losses":16,"wins":15},"deepseek/deepseek-v4-flash":{"draws":46,"losses":74,"wins":26},"deepseek/deepseek-v4-pro":{"draws":25,"losses":56,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":53,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":53,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":39,"wins":2},"elorian/glimpse":{"draws":10,"losses":14,"wins":4},"fireworks/ember-1":{"draws":22,"losses":69,"wins":5},"gemini-3.1-pro-preview":{"draws":22,"losses":54,"wins":20},"gemini-4-argon":{"draws":1,"losses":39,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":22,"wins":22},"google/gemini-3.5-flash":{"draws":32,"losses":81,"wins":13},"google/gemini-3.5-flash-lite":{"draws":48,"losses":92,"wins":34},"google/gemini-3.6-flash":{"draws":41,"losses":130,"wins":15},"google/gemini-3.8-flash":{"draws":24,"losses":70,"wins":2},"google/gemma-4-31b-it":{"draws":19,"losses":26,"wins":15},"gpt-4.1":{"draws":11,"losses":17,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":5},"gpt-5":{"draws":25,"losses":56,"wins":3},"gpt-5.4":{"draws":19,"losses":67,"wins":8},"gpt-5.4-mini":{"draws":21,"losses":37,"wins":6},"gpt-5.4-nano":{"draws":24,"losses":62,"wins":22},"gpt-5.5":{"draws":25,"losses":58,"wins":5},"gpt-5.6-luna":{"draws":26,"losses":50,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":83,"wins":5},"gpt-5.6-terra":{"draws":28,"losses":55,"wins":7},"gpt-6-astra":{"draws":2,"losses":94,"wins":0},"gpt-6-luna":{"draws":26,"losses":59,"wins":11},"gpt-6-sol":{"draws":13,"losses":82,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":92,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":27,"losses":28,"wins":17},"inception/mercury-3":{"draws":6,"losses":14,"wins":0},"inclusionai/ling-3.0-flash":{"draws":25,"losses":22,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":62,"wins":27},"meta/muse-glimmer-30b":{"draws":33,"losses":30,"wins":19},"meta/muse-spark-1.2":{"draws":21,"losses":60,"wins":9},"meta/muse-spark-1.3":{"draws":16,"losses":75,"wins":5},"meta/muse-spark-open":{"draws":8,"losses":34,"wins":4},"meta/muse-wonder":{"draws":9,"losses":84,"wins":3},"minimax/minimax-m3":{"draws":13,"losses":25,"wins":16},"minimax/minimax-m3.1-flash":{"draws":12,"losses":39,"wins":7},"mistralai/mistral-large-4-0":{"draws":17,"losses":39,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":24,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":20,"wins":2},"moonshotai/kimi-k3":{"draws":23,"losses":56,"wins":11},"nex-agi/nex-n2-pro":{"draws":10,"losses":27,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":8,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":42,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":12,"wins":0},"o3":{"draws":23,"losses":124,"wins":11},"openai/gpt-oss-120b":{"draws":24,"losses":40,"wins":18},"poolside/laguna-s-2.1":{"draws":26,"losses":44,"wins":16},"qwen/qwen3.7-max":{"draws":19,"losses":34,"wins":7},"qwen/qwen3.7-plus":{"draws":13,"losses":30,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":68,"wins":3},"qwen/qwen3.8-27b":{"draws":14,"losses":45,"wins":11},"qwen/qwen3.8-flash":{"draws":21,"losses":33,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":66,"wins":1},"qwen/qwen3.8-max-0902":{"draws":28,"losses":66,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":31,"wins":5},"stealth/ox-alpha":{"draws":52,"losses":192,"wins":28},"stealth/space-bunny-alpha":{"draws":21,"losses":47,"wins":12},"stepfun/step-3.7-flash":{"draws":15,"losses":49,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":17,"losses":24,"wins":11},"tencent/hy4-preview":{"draws":23,"losses":68,"wins":3},"thinkingmachines/inkling":{"draws":34,"losses":58,"wins":34},"thinkingmachines/inkling-small":{"draws":34,"losses":33,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":27,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":31,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":19,"wins":7},"x-ai/grok-4.5":{"draws":19,"losses":75,"wins":2},"x-ai/grok-4.6":{"draws":18,"losses":72,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":78,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":18,"wins":4},"xiaomi/mimo-v2.5":{"draws":58,"losses":68,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":45,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":44,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":50,"wins":5},"z-ai/glm-5.2":{"draws":42,"losses":126,"wins":24},"z-ai/glm-5.3":{"draws":15,"losses":76,"wins":1},"z-ai/glm-5.3-flash":{"draws":21,"losses":63,"wins":12},"z-ai/glm-5.3-flashx":{"draws":25,"losses":64,"wins":7}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":47,"wins":82},"claude-fable-5":{"draws":34,"losses":113,"wins":33},"claude-fable-5-1":{"draws":11,"losses":183,"wins":8},"claude-haiku-5-5":{"draws":39,"losses":77,"wins":58},"claude-opus-4-5":{"draws":85,"losses":98,"wins":111},"claude-opus-4-8":{"draws":37,"losses":82,"wins":49},"claude-opus-5":{"draws":37,"losses":237,"wins":30},"claude-opus-5-5":{"draws":10,"losses":177,"wins":9},"claude-sonnet-5":{"draws":50,"losses":56,"wins":74},"claude-sonnet-5-5":{"draws":30,"losses":104,"wins":46},"cohere/north-mini-code":{"draws":14,"losses":12,"wins":44},"deepseek/deepseek-v4-flash":{"draws":67,"losses":58,"wins":145},"deepseek/deepseek-v4-pro":{"draws":41,"losses":55,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":51,"wins":72},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":74,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":53,"wins":28},"elorian/glimpse":{"draws":11,"losses":17,"wins":24},"fireworks/ember-1":{"draws":51,"losses":69,"wins":60},"gemini-3.1-pro-preview":{"draws":42,"losses":59,"wins":79},"gemini-4-argon":{"draws":8,"losses":102,"wins":2},"google/gemini-3.1-flash-lite":{"draws":32,"losses":13,"wins":81},"google/gemini-3.5-flash":{"draws":36,"losses":66,"wins":66},"google/gemini-3.5-flash-lite":{"draws":75,"losses":82,"wins":161},"google/gemini-3.6-flash":{"draws":77,"losses":138,"wins":131},"google/gemini-3.8-flash":{"draws":36,"losses":99,"wins":45},"google/gemma-4-31b-it":{"draws":31,"losses":22,"wins":53},"gpt-4.1":{"draws":14,"losses":17,"wins":29},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":11},"gpt-5":{"draws":38,"losses":51,"wins":69},"gpt-5.4":{"draws":29,"losses":96,"wins":49},"gpt-5.4-mini":{"draws":42,"losses":28,"wins":50},"gpt-5.4-nano":{"draws":34,"losses":48,"wins":102},"gpt-5.5":{"draws":49,"losses":69,"wins":48},"gpt-5.6-luna":{"draws":50,"losses":49,"wins":81},"gpt-5.6-sol":{"draws":18,"losses":121,"wins":41},"gpt-5.6-terra":{"draws":54,"losses":65,"wins":53},"gpt-6-astra":{"draws":11,"losses":162,"wins":7},"gpt-6-luna":{"draws":50,"losses":60,"wins":70},"gpt-6-sol":{"draws":28,"losses":126,"wins":26},"gpt-6.1-sol":{"draws":11,"losses":151,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":47,"losses":16,"wins":65},"inception/mercury-3":{"draws":17,"losses":31,"wins":20},"inclusionai/ling-3.0-flash":{"draws":39,"losses":12,"wins":77},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":37,"losses":39,"wins":122},"meta/muse-glimmer-30b":{"draws":52,"losses":25,"wins":81},"meta/muse-spark-1.2":{"draws":35,"losses":78,"wins":59},"meta/muse-spark-1.3":{"draws":34,"losses":99,"wins":47},"meta/muse-spark-open":{"draws":12,"losses":30,"wins":24},"meta/muse-wonder":{"draws":30,"losses":121,"wins":29},"minimax/minimax-m3":{"draws":23,"losses":23,"wins":52},"minimax/minimax-m3.1-flash":{"draws":21,"losses":26,"wins":35},"mistralai/mistral-large-4-0":{"draws":38,"losses":39,"wins":35},"mistralai/mistral-medium-3-5":{"draws":31,"losses":15,"wins":58},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":16,"wins":19},"moonshotai/kimi-k3":{"draws":53,"losses":59,"wins":60},"nex-agi/nex-n2-pro":{"draws":24,"losses":17,"wins":49},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":33,"wins":78},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":15,"wins":17},"o3":{"draws":36,"losses":85,"wins":137},"openai/gpt-oss-120b":{"draws":45,"losses":34,"wins":77},"poolside/laguna-s-2.1":{"draws":43,"losses":34,"wins":93},"qwen/qwen3.7-max":{"draws":32,"losses":33,"wins":41},"qwen/qwen3.7-plus":{"draws":22,"losses":19,"wins":51},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":76,"wins":56},"qwen/qwen3.8-27b":{"draws":22,"losses":49,"wins":57},"qwen/qwen3.8-flash":{"draws":37,"losses":35,"wins":48},"qwen/qwen3.8-max":{"draws":57,"losses":61,"wins":62},"qwen/qwen3.8-max-0902":{"draws":48,"losses":86,"wins":46},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":34,"wins":30},"stealth/ox-alpha":{"draws":114,"losses":260,"wins":202},"stealth/space-bunny-alpha":{"draws":44,"losses":33,"wins":67},"stepfun/step-3.7-flash":{"draws":21,"losses":27,"wins":82},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":29,"wins":41},"tencent/hy4-preview":{"draws":39,"losses":89,"wins":46},"thinkingmachines/inkling":{"draws":57,"losses":48,"wins":135},"thinkingmachines/inkling-small":{"draws":52,"losses":31,"wins":97},"unbiased/pareto-26.10":{"draws":5,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":55,"wins":5},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":29},"x-ai/grok-4.5":{"draws":31,"losses":86,"wins":63},"x-ai/grok-4.6":{"draws":48,"losses":97,"wins":35},"x-ai/grok-4.7":{"draws":15,"losses":119,"wins":24},"x-ai/grok-build-0.1":{"draws":20,"losses":9,"wins":31},"xiaomi/mimo-v2.5":{"draws":84,"losses":50,"wins":150},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":30,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":52,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":62,"wins":37},"z-ai/glm-5.2":{"draws":102,"losses":109,"wins":149},"z-ai/glm-5.3":{"draws":30,"losses":106,"wins":36},"z-ai/glm-5.3-flash":{"draws":24,"losses":96,"wins":60},"z-ai/glm-5.3-flashx":{"draws":47,"losses":89,"wins":44}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":78,"losses":82,"wins":74},"claude-fable-5":{"draws":46,"losses":178,"wins":28},"claude-fable-5-1":{"draws":21,"losses":261,"wins":2},"claude-haiku-5-5":{"draws":53,"losses":149,"wins":40},"claude-opus-4-5":{"draws":132,"losses":183,"wins":95},"claude-opus-4-8":{"draws":63,"losses":147,"wins":22},"claude-opus-5":{"draws":55,"losses":339,"wins":30},"claude-opus-5-5":{"draws":18,"losses":253,"wins":1},"claude-sonnet-5":{"draws":71,"losses":129,"wins":52},"claude-sonnet-5-5":{"draws":49,"losses":164,"wins":39},"cohere/north-mini-code":{"draws":32,"losses":32,"wins":34},"deepseek/deepseek-v4-flash":{"draws":116,"losses":124,"wins":134},"deepseek/deepseek-v4-pro":{"draws":61,"losses":106,"wins":65},"deepseek/deepseek-v4-pro-0813":{"draws":71,"losses":112,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":76,"losses":125,"wins":51},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":115,"wins":12},"elorian/glimpse":{"draws":13,"losses":31,"wins":16},"fireworks/ember-1":{"draws":93,"losses":113,"wins":46},"gemini-3.1-pro-preview":{"draws":83,"losses":105,"wins":64},"gemini-4-argon":{"draws":6,"losses":119,"wins":5},"google/gemini-3.1-flash-lite":{"draws":48,"losses":34,"wins":92},"google/gemini-3.5-flash":{"draws":75,"losses":161,"wins":82},"google/gemini-3.5-flash-lite":{"draws":118,"losses":123,"wins":123},"google/gemini-3.6-flash":{"draws":139,"losses":254,"wins":93},"google/gemini-3.8-flash":{"draws":47,"losses":185,"wins":20},"google/gemma-4-31b-it":{"draws":55,"losses":35,"wins":58},"gpt-4.1":{"draws":28,"losses":29,"wins":27},"gpt-4.1-nano":{"draws":18,"losses":3,"wins":9},"gpt-5":{"draws":65,"losses":97,"wins":58},"gpt-5.4":{"draws":56,"losses":149,"wins":39},"gpt-5.4-mini":{"draws":58,"losses":58,"wins":52},"gpt-5.4-nano":{"draws":51,"losses":95,"wins":106},"gpt-5.5":{"draws":89,"losses":109,"wins":34},"gpt-5.6-luna":{"draws":83,"losses":96,"wins":73},"gpt-5.6-sol":{"draws":36,"losses":194,"wins":22},"gpt-5.6-terra":{"draws":74,"losses":117,"wins":49},"gpt-6-astra":{"draws":14,"losses":237,"wins":1},"gpt-6-luna":{"draws":79,"losses":112,"wins":61},"gpt-6-sol":{"draws":39,"losses":190,"wins":23},"gpt-6.1-sol":{"draws":16,"losses":235,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":74,"losses":37,"wins":69},"inception/mercury-3":{"draws":26,"losses":38,"wins":8},"inclusionai/ling-3.0-flash":{"draws":63,"losses":35,"wins":78},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":73,"losses":84,"wins":121},"meta/muse-glimmer-30b":{"draws":89,"losses":52,"wins":79},"meta/muse-spark-1.2":{"draws":60,"losses":134,"wins":46},"meta/muse-spark-1.3":{"draws":50,"losses":167,"wins":35},"meta/muse-spark-open":{"draws":22,"losses":80,"wins":17},"meta/muse-wonder":{"draws":43,"losses":182,"wins":27},"minimax/minimax-m3":{"draws":36,"losses":46,"wins":52},"minimax/minimax-m3.1-flash":{"draws":36,"losses":51,"wins":33},"mistralai/mistral-large-4-0":{"draws":52,"losses":75,"wins":29},"mistralai/mistral-medium-3-5":{"draws":52,"losses":32,"wins":64},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":33,"wins":14},"moonshotai/kimi-k3":{"draws":77,"losses":119,"wins":44},"nex-agi/nex-n2-pro":{"draws":32,"losses":38,"wins":58},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":83,"losses":68,"wins":69},"nvidia/nemotron-3.5-super-vl":{"draws":28,"losses":31,"wins":5},"o3":{"draws":58,"losses":201,"wins":97},"openai/gpt-oss-120b":{"draws":68,"losses":74,"wins":76},"poolside/laguna-s-2.1":{"draws":75,"losses":97,"wins":66},"qwen/qwen3.7-max":{"draws":41,"losses":63,"wins":42},"qwen/qwen3.7-plus":{"draws":35,"losses":40,"wins":51},"qwen/qwen3.8-2.4t-a95b":{"draws":80,"losses":130,"wins":42},"qwen/qwen3.8-27b":{"draws":36,"losses":101,"wins":43},"qwen/qwen3.8-flash":{"draws":55,"losses":83,"wins":30},"qwen/qwen3.8-max":{"draws":82,"losses":123,"wins":47},"qwen/qwen3.8-max-0902":{"draws":72,"losses":143,"wins":37},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":56,"wins":31},"stealth/ox-alpha":{"draws":174,"losses":485,"wins":167},"stealth/space-bunny-alpha":{"draws":58,"losses":83,"wins":61},"stepfun/step-3.7-flash":{"draws":49,"losses":60,"wins":71},"stepfun/step-5-preview":{"draws":10,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":48,"losses":58,"wins":30},"tencent/hy4-preview":{"draws":62,"losses":134,"wins":48},"thinkingmachines/inkling":{"draws":93,"losses":113,"wins":132},"thinkingmachines/inkling-small":{"draws":83,"losses":74,"wins":95},"unbiased/pareto-26.10":{"draws":4,"losses":46,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":81,"wins":1},"upstage/solar-mini4":{"draws":20,"losses":25,"wins":23},"x-ai/grok-4.5":{"draws":64,"losses":142,"wins":46},"x-ai/grok-4.6":{"draws":59,"losses":162,"wins":31},"x-ai/grok-4.7":{"draws":21,"losses":169,"wins":28},"x-ai/grok-build-0.1":{"draws":34,"losses":24,"wins":26},"xiaomi/mimo-v2.5":{"draws":119,"losses":131,"wins":142},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":49,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":105,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":118,"wins":29},"z-ai/glm-5.2":{"draws":166,"losses":199,"wins":139},"z-ai/glm-5.3":{"draws":41,"losses":184,"wins":17},"z-ai/glm-5.3-flash":{"draws":52,"losses":153,"wins":47},"z-ai/glm-5.3-flashx":{"draws":63,"losses":141,"wins":48}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":67,"losses":51,"wins":136},"claude-fable-5":{"draws":48,"losses":146,"wins":82},"claude-fable-5-1":{"draws":25,"losses":270,"wins":17},"claude-haiku-5-5":{"draws":65,"losses":100,"wins":99},"claude-opus-4-5":{"draws":132,"losses":115,"wins":201},"claude-opus-4-8":{"draws":56,"losses":94,"wins":102},"claude-opus-5":{"draws":65,"losses":322,"wins":81},"claude-opus-5-5":{"draws":23,"losses":253,"wins":20},"claude-sonnet-5":{"draws":65,"losses":88,"wins":123},"claude-sonnet-5-5":{"draws":52,"losses":126,"wins":98},"cohere/north-mini-code":{"draws":20,"losses":9,"wins":75},"deepseek/deepseek-v4-flash":{"draws":99,"losses":57,"wins":256},"deepseek/deepseek-v4-pro":{"draws":64,"losses":84,"wins":106},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":78,"wins":118},"deepseek/deepseek-v4.1-flash":{"draws":76,"losses":88,"wins":112},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":73,"wins":54},"elorian/glimpse":{"draws":15,"losses":26,"wins":31},"fireworks/ember-1":{"draws":79,"losses":101,"wins":96},"gemini-3.1-pro-preview":{"draws":64,"losses":87,"wins":125},"gemini-4-argon":{"draws":11,"losses":103,"wins":16},"google/gemini-3.1-flash-lite":{"draws":41,"losses":15,"wins":130},"google/gemini-3.5-flash":{"draws":77,"losses":131,"wins":138},"google/gemini-3.5-flash-lite":{"draws":139,"losses":93,"wins":254},"google/gemini-3.6-flash":{"draws":90,"losses":175,"wins":175},"google/gemini-3.8-flash":{"draws":61,"losses":132,"wins":83},"google/gemma-4-31b-it":{"draws":51,"losses":20,"wins":89},"gpt-4.1":{"draws":25,"losses":20,"wins":47},"gpt-4.1-nano":{"draws":14,"losses":2,"wins":18},"gpt-5":{"draws":51,"losses":75,"wins":116},"gpt-5.4":{"draws":59,"losses":117,"wins":90},"gpt-5.4-mini":{"draws":55,"losses":30,"wins":99},"gpt-5.4-nano":{"draws":50,"losses":58,"wins":166},"gpt-5.5":{"draws":74,"losses":93,"wins":87},"gpt-5.6-luna":{"draws":79,"losses":59,"wins":138},"gpt-5.6-sol":{"draws":41,"losses":159,"wins":76},"gpt-5.6-terra":{"draws":82,"losses":68,"wins":114},"gpt-6-astra":{"draws":20,"losses":239,"wins":17},"gpt-6-luna":{"draws":81,"losses":69,"wins":126},"gpt-6-sol":{"draws":35,"losses":181,"wins":60},"gpt-6.1-sol":{"draws":18,"losses":230,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":68,"losses":12,"wins":114},"inception/mercury-3":{"draws":26,"losses":22,"wins":46},"inclusionai/ling-3.0-flash":{"draws":68,"losses":18,"wins":108},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":66,"losses":46,"wins":188},"meta/muse-glimmer-30b":{"draws":77,"losses":35,"wins":130},"meta/muse-spark-1.2":{"draws":51,"losses":107,"wins":106},"meta/muse-spark-1.3":{"draws":48,"losses":133,"wins":95},"meta/muse-spark-open":{"draws":22,"losses":56,"wins":48},"meta/muse-wonder":{"draws":50,"losses":155,"wins":71},"minimax/minimax-m3":{"draws":30,"losses":25,"wins":93},"minimax/minimax-m3.1-flash":{"draws":34,"losses":39,"wins":75},"mistralai/mistral-large-4-0":{"draws":41,"losses":59,"wins":72},"mistralai/mistral-medium-3-5":{"draws":57,"losses":14,"wins":89},"moonshotai/kimi-k2.7-code":{"draws":19,"losses":16,"wins":33},"moonshotai/kimi-k3":{"draws":71,"losses":90,"wins":103},"nex-agi/nex-n2-pro":{"draws":25,"losses":17,"wins":96},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":77,"losses":34,"wins":127},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":13,"wins":29},"o3":{"draws":54,"losses":124,"wins":206},"openai/gpt-oss-120b":{"draws":72,"losses":32,"wins":136},"poolside/laguna-s-2.1":{"draws":79,"losses":48,"wins":135},"qwen/qwen3.7-max":{"draws":47,"losses":38,"wins":75},"qwen/qwen3.7-plus":{"draws":39,"losses":22,"wins":77},"qwen/qwen3.8-2.4t-a95b":{"draws":73,"losses":95,"wins":108},"qwen/qwen3.8-27b":{"draws":44,"losses":64,"wins":90},"qwen/qwen3.8-flash":{"draws":60,"losses":45,"wins":79},"qwen/qwen3.8-max":{"draws":72,"losses":89,"wins":115},"qwen/qwen3.8-max-0902":{"draws":76,"losses":104,"wins":96},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":45,"wins":57},"stealth/ox-alpha":{"draws":196,"losses":358,"wins":362},"stealth/space-bunny-alpha":{"draws":57,"losses":45,"wins":118},"stepfun/step-3.7-flash":{"draws":35,"losses":32,"wins":131},"stepfun/step-5-preview":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":47,"losses":31,"wins":70},"tencent/hy4-preview":{"draws":59,"losses":105,"wins":102},"thinkingmachines/inkling":{"draws":103,"losses":56,"wins":213},"thinkingmachines/inkling-small":{"draws":84,"losses":45,"wins":147},"unbiased/pareto-26.10":{"draws":7,"losses":44,"wins":3},"unbiased/pareto-26.10-preview":{"draws":5,"losses":78,"wins":9},"upstage/solar-mini4":{"draws":14,"losses":9,"wins":49},"x-ai/grok-4.5":{"draws":59,"losses":116,"wins":101},"x-ai/grok-4.6":{"draws":71,"losses":123,"wins":82},"x-ai/grok-4.7":{"draws":14,"losses":172,"wins":54},"x-ai/grok-build-0.1":{"draws":30,"losses":5,"wins":57},"xiaomi/mimo-v2.5":{"draws":129,"losses":49,"wins":246},"xiaomi/mimo-v2.5-pro":{"draws":33,"losses":29,"wins":88},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":71,"wins":76},"xiaomi/mimo-v2.6-pro":{"draws":38,"losses":86,"wins":60},"z-ai/glm-5.2":{"draws":152,"losses":152,"wins":248},"z-ai/glm-5.3":{"draws":52,"losses":153,"wins":59},"z-ai/glm-5.3-flash":{"draws":43,"losses":142,"wins":91},"z-ai/glm-5.3-flashx":{"draws":67,"losses":113,"wins":96}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":23,"wins":79},"claude-fable-5":{"draws":23,"losses":68,"wins":53},"claude-fable-5-1":{"draws":8,"losses":140,"wins":14},"claude-haiku-5-5":{"draws":33,"losses":43,"wins":62},"claude-opus-4-5":{"draws":72,"losses":42,"wins":120},"claude-opus-4-8":{"draws":28,"losses":43,"wins":61},"claude-opus-5":{"draws":28,"losses":164,"wins":54},"claude-opus-5-5":{"draws":15,"losses":122,"wins":19},"claude-sonnet-5":{"draws":33,"losses":33,"wins":78},"claude-sonnet-5-5":{"draws":20,"losses":68,"wins":56},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":40},"deepseek/deepseek-v4-flash":{"draws":37,"losses":24,"wins":155},"deepseek/deepseek-v4-pro":{"draws":27,"losses":33,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":34,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":46,"wins":62},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":43,"wins":24},"elorian/glimpse":{"draws":10,"losses":15,"wins":27},"fireworks/ember-1":{"draws":35,"losses":48,"wins":61},"gemini-3.1-pro-preview":{"draws":28,"losses":34,"wins":82},"gemini-4-argon":{"draws":2,"losses":54,"wins":10},"google/gemini-3.1-flash-lite":{"draws":24,"losses":2,"wins":70},"google/gemini-3.5-flash":{"draws":36,"losses":45,"wins":99},"google/gemini-3.5-flash-lite":{"draws":47,"losses":20,"wins":185},"google/gemini-3.6-flash":{"draws":61,"losses":83,"wins":132},"google/gemini-3.8-flash":{"draws":22,"losses":37,"wins":37},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":52},"gpt-4.1":{"draws":14,"losses":8,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":25,"losses":30,"wins":71},"gpt-5.4":{"draws":28,"losses":52,"wins":58},"gpt-5.4-mini":{"draws":23,"losses":13,"wins":60},"gpt-5.4-nano":{"draws":29,"losses":24,"wins":91},"gpt-5.5":{"draws":44,"losses":44,"wins":44},"gpt-5.6-luna":{"draws":32,"losses":25,"wins":87},"gpt-5.6-sol":{"draws":19,"losses":72,"wins":53},"gpt-5.6-terra":{"draws":40,"losses":36,"wins":62},"gpt-6-astra":{"draws":14,"losses":121,"wins":9},"gpt-6-luna":{"draws":41,"losses":34,"wins":69},"gpt-6-sol":{"draws":22,"losses":91,"wins":31},"gpt-6.1-sol":{"draws":20,"losses":107,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":4,"wins":67},"inception/mercury-3":{"draws":13,"losses":12,"wins":19},"inclusionai/ling-3.0-flash":{"draws":30,"losses":2,"wins":70},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":28,"losses":19,"wins":109},"meta/muse-glimmer-30b":{"draws":33,"losses":15,"wins":78},"meta/muse-spark-1.2":{"draws":25,"losses":56,"wins":57},"meta/muse-spark-1.3":{"draws":32,"losses":51,"wins":61},"meta/muse-spark-open":{"draws":12,"losses":19,"wins":31},"meta/muse-wonder":{"draws":36,"losses":68,"wins":40},"minimax/minimax-m3":{"draws":16,"losses":6,"wins":56},"minimax/minimax-m3.1-flash":{"draws":15,"losses":17,"wins":48},"mistralai/mistral-large-4-0":{"draws":28,"losses":26,"wins":36},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":17,"wins":13},"moonshotai/kimi-k3":{"draws":34,"losses":33,"wins":71},"nex-agi/nex-n2-pro":{"draws":13,"losses":7,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":9,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":16,"wins":21},"o3":{"draws":23,"losses":44,"wins":131},"openai/gpt-oss-120b":{"draws":26,"losses":8,"wins":92},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":93},"qwen/qwen3.7-max":{"draws":27,"losses":20,"wins":37},"qwen/qwen3.7-plus":{"draws":17,"losses":7,"wins":48},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":41,"wins":68},"qwen/qwen3.8-27b":{"draws":16,"losses":22,"wins":64},"qwen/qwen3.8-flash":{"draws":23,"losses":26,"wins":47},"qwen/qwen3.8-max":{"draws":36,"losses":46,"wins":62},"qwen/qwen3.8-max-0902":{"draws":37,"losses":47,"wins":60},"reflection/beam-1.0-501b-a23b":{"draws":20,"losses":14,"wins":30},"stealth/ox-alpha":{"draws":100,"losses":149,"wins":225},"stealth/space-bunny-alpha":{"draws":27,"losses":17,"wins":70},"stepfun/step-3.7-flash":{"draws":16,"losses":9,"wins":77},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":31,"losses":8,"wins":39},"tencent/hy4-preview":{"draws":31,"losses":54,"wins":53},"thinkingmachines/inkling":{"draws":50,"losses":19,"wins":123},"thinkingmachines/inkling-small":{"draws":39,"losses":17,"wins":88},"unbiased/pareto-26.10":{"draws":4,"losses":26,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":25,"losses":68,"wins":51},"x-ai/grok-4.6":{"draws":40,"losses":53,"wins":51},"x-ai/grok-4.7":{"draws":13,"losses":86,"wins":27},"x-ai/grok-build-0.1":{"draws":13,"losses":3,"wins":32},"xiaomi/mimo-v2.5":{"draws":61,"losses":20,"wins":141},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":12,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":28,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":48,"wins":28},"z-ai/glm-5.2":{"draws":76,"losses":59,"wins":153},"z-ai/glm-5.3":{"draws":29,"losses":71,"wins":38},"z-ai/glm-5.3-flash":{"draws":20,"losses":57,"wins":67},"z-ai/glm-5.3-flashx":{"draws":26,"losses":52,"wins":66}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":24},"claude-fable-5":{"draws":18,"losses":58,"wins":8},"claude-fable-5-1":{"draws":4,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":23,"losses":50,"wins":9},"claude-opus-4-5":{"draws":46,"losses":77,"wins":15},"claude-opus-4-8":{"draws":23,"losses":47,"wins":10},"claude-opus-5":{"draws":21,"losses":109,"wins":10},"claude-opus-5-5":{"draws":5,"losses":87,"wins":0},"claude-sonnet-5":{"draws":27,"losses":45,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":54,"wins":16},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":58,"losses":46,"wins":22},"deepseek/deepseek-v4-pro":{"draws":28,"losses":34,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":38,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":38,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":31,"wins":3},"elorian/glimpse":{"draws":11,"losses":7,"wins":2},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":30,"losses":39,"wins":15},"gemini-4-argon":{"draws":1,"losses":41,"wins":0},"google/gemini-3.1-flash-lite":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash":{"draws":31,"losses":53,"wins":22},"google/gemini-3.5-flash-lite":{"draws":55,"losses":58,"wins":35},"google/gemini-3.6-flash":{"draws":51,"losses":89,"wins":20},"google/gemini-3.8-flash":{"draws":23,"losses":52,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":7},"gpt-4.1":{"draws":11,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":31,"losses":32,"wins":9},"gpt-5.4":{"draws":28,"losses":43,"wins":9},"gpt-5.4-mini":{"draws":22,"losses":24,"wins":10},"gpt-5.4-nano":{"draws":26,"losses":43,"wins":17},"gpt-5.5":{"draws":30,"losses":40,"wins":6},"gpt-5.6-luna":{"draws":34,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":11,"losses":67,"wins":6},"gpt-5.6-terra":{"draws":32,"losses":39,"wins":9},"gpt-6-astra":{"draws":4,"losses":80,"wins":0},"gpt-6-luna":{"draws":28,"losses":38,"wins":18},"gpt-6-sol":{"draws":9,"losses":73,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":80,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":16,"wins":18},"inception/mercury-3":{"draws":12,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":32,"losses":13,"wins":13},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":35,"wins":26},"meta/muse-glimmer-30b":{"draws":38,"losses":17,"wins":17},"meta/muse-spark-1.2":{"draws":23,"losses":40,"wins":17},"meta/muse-spark-1.3":{"draws":23,"losses":53,"wins":8},"meta/muse-spark-open":{"draws":11,"losses":28,"wins":5},"meta/muse-wonder":{"draws":17,"losses":60,"wins":7},"minimax/minimax-m3":{"draws":19,"losses":16,"wins":11},"minimax/minimax-m3.1-flash":{"draws":12,"losses":17,"wins":7},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":22,"losses":7,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":29,"losses":38,"wins":13},"nex-agi/nex-n2-pro":{"draws":17,"losses":11,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":8,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":18,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":9,"wins":3},"o3":{"draws":26,"losses":71,"wins":21},"openai/gpt-oss-120b":{"draws":31,"losses":33,"wins":10},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":20},"qwen/qwen3.7-max":{"draws":17,"losses":20,"wins":13},"qwen/qwen3.7-plus":{"draws":16,"losses":15,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":45,"wins":10},"qwen/qwen3.8-27b":{"draws":19,"losses":29,"wins":10},"qwen/qwen3.8-flash":{"draws":27,"losses":23,"wins":6},"qwen/qwen3.8-max":{"draws":33,"losses":43,"wins":8},"qwen/qwen3.8-max-0902":{"draws":29,"losses":46,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":27,"wins":3},"stealth/ox-alpha":{"draws":60,"losses":160,"wins":40},"stealth/space-bunny-alpha":{"draws":26,"losses":26,"wins":16},"stepfun/step-3.7-flash":{"draws":18,"losses":27,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":16,"wins":9},"tencent/hy4-preview":{"draws":26,"losses":43,"wins":11},"thinkingmachines/inkling":{"draws":40,"losses":36,"wins":32},"thinkingmachines/inkling-small":{"draws":35,"losses":25,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":27,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":19,"losses":55,"wins":10},"x-ai/grok-4.6":{"draws":24,"losses":54,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":62,"wins":4},"x-ai/grok-build-0.1":{"draws":11,"losses":9,"wins":8},"xiaomi/mimo-v2.5":{"draws":61,"losses":41,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":32,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":41,"wins":4},"z-ai/glm-5.2":{"draws":69,"losses":70,"wins":29},"z-ai/glm-5.3":{"draws":22,"losses":53,"wins":7},"z-ai/glm-5.3-flash":{"draws":25,"losses":45,"wins":14},"z-ai/glm-5.3-flashx":{"draws":28,"losses":45,"wins":11}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":32,"losses":29,"wins":17},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":17,"wins":14},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":16,"wins":34},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":20,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":17,"wins":2},"elorian/glimpse":{"draws":4,"losses":11,"wins":3},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"gemini-4-argon":{"draws":2,"losses":18,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":28,"losses":27,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":47,"wins":20},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":15,"wins":16},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":20},"gpt-5.5":{"draws":10,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":8,"wins":11},"inception/mercury-3":{"draws":4,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":9,"wins":25},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":15,"losses":23,"wins":8},"meta/muse-spark-1.3":{"draws":16,"losses":28,"wins":4},"meta/muse-spark-open":{"draws":3,"losses":16,"wins":8},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":15},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":21,"wins":12},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":7},"o3":{"draws":13,"losses":26,"wins":27},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":13,"wins":17},"qwen/qwen3.7-max":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":12,"wins":9},"stealth/ox-alpha":{"draws":43,"losses":79,"wins":36},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":24,"wins":9},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":27},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":18},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":28,"wins":9},"x-ai/grok-4.6":{"draws":19,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":17,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":35,"losses":38,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":28,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":5,"wins":0},"elorian/glimpse":{"draws":2,"losses":2,"wins":0},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"gemini-4-argon":{"draws":0,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inception/mercury-3":{"draws":6,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-spark-open":{"draws":4,"losses":2,"wins":0},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"minimax/minimax-m3.1-flash":{"draws":2,"losses":4,"wins":0},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":0},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":33,"losses":34,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":38,"wins":43},"claude-fable-5":{"draws":24,"losses":81,"wins":21},"claude-fable-5-1":{"draws":7,"losses":134,"wins":1},"claude-haiku-5-5":{"draws":31,"losses":62,"wins":27},"claude-opus-4-5":{"draws":64,"losses":74,"wins":66},"claude-opus-4-8":{"draws":30,"losses":54,"wins":30},"claude-opus-5":{"draws":23,"losses":179,"wins":18},"claude-opus-5-5":{"draws":9,"losses":124,"wins":5},"claude-sonnet-5":{"draws":37,"losses":54,"wins":35},"claude-sonnet-5-5":{"draws":27,"losses":73,"wins":26},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":34},"deepseek/deepseek-v4-flash":{"draws":58,"losses":41,"wins":91},"deepseek/deepseek-v4-pro":{"draws":30,"losses":53,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":45,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":56,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":40,"wins":14},"elorian/glimpse":{"draws":13,"losses":17,"wins":10},"fireworks/ember-1":{"draws":36,"losses":60,"wins":30},"gemini-3.1-pro-preview":{"draws":41,"losses":50,"wins":35},"gemini-4-argon":{"draws":4,"losses":51,"wins":5},"google/gemini-3.1-flash-lite":{"draws":25,"losses":3,"wins":56},"google/gemini-3.5-flash":{"draws":38,"losses":69,"wins":51},"google/gemini-3.5-flash-lite":{"draws":65,"losses":58,"wins":97},"google/gemini-3.6-flash":{"draws":51,"losses":116,"wins":75},"google/gemini-3.8-flash":{"draws":25,"losses":71,"wins":30},"google/gemma-4-31b-it":{"draws":31,"losses":9,"wins":32},"gpt-4.1":{"draws":11,"losses":16,"wins":15},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":16,"losses":28,"wins":28},"gpt-5.4":{"draws":22,"losses":69,"wins":31},"gpt-5.4-mini":{"draws":27,"losses":27,"wins":30},"gpt-5.4-nano":{"draws":20,"losses":43,"wins":65},"gpt-5.5":{"draws":42,"losses":49,"wins":27},"gpt-5.6-luna":{"draws":40,"losses":35,"wins":51},"gpt-5.6-sol":{"draws":17,"losses":92,"wins":17},"gpt-5.6-terra":{"draws":31,"losses":51,"wins":38},"gpt-6-astra":{"draws":9,"losses":115,"wins":2},"gpt-6-luna":{"draws":39,"losses":45,"wins":42},"gpt-6-sol":{"draws":15,"losses":95,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":115,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":9,"wins":41},"inception/mercury-3":{"draws":7,"losses":18,"wins":17},"inclusionai/ling-3.0-flash":{"draws":31,"losses":22,"wins":35},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":35,"losses":32,"wins":71},"meta/muse-glimmer-30b":{"draws":40,"losses":24,"wins":50},"meta/muse-spark-1.2":{"draws":24,"losses":67,"wins":31},"meta/muse-spark-1.3":{"draws":26,"losses":73,"wins":27},"meta/muse-spark-open":{"draws":11,"losses":28,"wins":13},"meta/muse-wonder":{"draws":23,"losses":80,"wins":23},"minimax/minimax-m3":{"draws":17,"losses":17,"wins":36},"minimax/minimax-m3.1-flash":{"draws":17,"losses":21,"wins":30},"mistralai/mistral-large-4-0":{"draws":30,"losses":34,"wins":16},"mistralai/mistral-medium-3-5":{"draws":22,"losses":16,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":32,"losses":49,"wins":41},"nex-agi/nex-n2-pro":{"draws":15,"losses":17,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":21,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":15,"wins":9},"o3":{"draws":24,"losses":69,"wins":87},"openai/gpt-oss-120b":{"draws":35,"losses":21,"wins":56},"poolside/laguna-s-2.1":{"draws":43,"losses":36,"wins":47},"qwen/qwen3.7-max":{"draws":31,"losses":15,"wins":28},"qwen/qwen3.7-plus":{"draws":16,"losses":10,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":56,"wins":33},"qwen/qwen3.8-27b":{"draws":17,"losses":41,"wins":30},"qwen/qwen3.8-flash":{"draws":21,"losses":32,"wins":31},"qwen/qwen3.8-max":{"draws":39,"losses":58,"wins":29},"qwen/qwen3.8-max-0902":{"draws":36,"losses":59,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":24,"wins":14},"stealth/ox-alpha":{"draws":98,"losses":199,"wins":127},"stealth/space-bunny-alpha":{"draws":25,"losses":37,"wins":38},"stepfun/step-3.7-flash":{"draws":21,"losses":18,"wins":53},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":27,"wins":21},"tencent/hy4-preview":{"draws":35,"losses":50,"wins":37},"thinkingmachines/inkling":{"draws":40,"losses":39,"wins":93},"thinkingmachines/inkling-small":{"draws":48,"losses":20,"wins":58},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":40,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":23},"x-ai/grok-4.5":{"draws":25,"losses":67,"wins":34},"x-ai/grok-4.6":{"draws":36,"losses":71,"wins":19},"x-ai/grok-4.7":{"draws":10,"losses":84,"wins":18},"x-ai/grok-build-0.1":{"draws":15,"losses":9,"wins":18},"xiaomi/mimo-v2.5":{"draws":58,"losses":39,"wins":93},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":21,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":37,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":22},"z-ai/glm-5.2":{"draws":82,"losses":76,"wins":94},"z-ai/glm-5.3":{"draws":18,"losses":80,"wins":22},"z-ai/glm-5.3-flash":{"draws":21,"losses":74,"wins":31},"z-ai/glm-5.3-flashx":{"draws":36,"losses":57,"wins":33}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":27,"wins":70},"claude-fable-5":{"draws":33,"losses":63,"wins":42},"claude-fable-5-1":{"draws":10,"losses":130,"wins":16},"claude-haiku-5-5":{"draws":31,"losses":51,"wins":50},"claude-opus-4-5":{"draws":66,"losses":47,"wins":111},"claude-opus-4-8":{"draws":29,"losses":43,"wins":54},"claude-opus-5":{"draws":29,"losses":169,"wins":36},"claude-opus-5-5":{"draws":11,"losses":126,"wins":13},"claude-sonnet-5":{"draws":37,"losses":31,"wins":70},"claude-sonnet-5-5":{"draws":36,"losses":59,"wins":43},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":35},"deepseek/deepseek-v4-flash":{"draws":54,"losses":31,"wins":121},"deepseek/deepseek-v4-pro":{"draws":29,"losses":38,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":37,"wins":65},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":43,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":33,"wins":27},"elorian/glimpse":{"draws":6,"losses":12,"wins":18},"fireworks/ember-1":{"draws":40,"losses":38,"wins":60},"gemini-3.1-pro-preview":{"draws":30,"losses":42,"wins":66},"gemini-4-argon":{"draws":3,"losses":43,"wins":10},"google/gemini-3.1-flash-lite":{"draws":19,"losses":8,"wins":67},"google/gemini-3.5-flash":{"draws":29,"losses":49,"wins":96},"google/gemini-3.5-flash-lite":{"draws":56,"losses":39,"wins":149},"google/gemini-3.6-flash":{"draws":59,"losses":90,"wins":117},"google/gemini-3.8-flash":{"draws":28,"losses":58,"wins":52},"google/gemma-4-31b-it":{"draws":28,"losses":9,"wins":43},"gpt-4.1":{"draws":13,"losses":9,"wins":24},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":6},"gpt-5":{"draws":22,"losses":31,"wins":69},"gpt-5.4":{"draws":20,"losses":34,"wins":34},"gpt-5.4-mini":{"draws":30,"losses":6,"wins":56},"gpt-5.4-nano":{"draws":19,"losses":32,"wins":87},"gpt-5.5":{"draws":40,"losses":42,"wins":46},"gpt-5.6-luna":{"draws":46,"losses":21,"wins":71},"gpt-5.6-sol":{"draws":23,"losses":68,"wins":47},"gpt-5.6-terra":{"draws":37,"losses":35,"wins":60},"gpt-6-astra":{"draws":6,"losses":116,"wins":16},"gpt-6-luna":{"draws":43,"losses":34,"wins":61},"gpt-6-sol":{"draws":15,"losses":101,"wins":22},"gpt-6.1-sol":{"draws":9,"losses":109,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":41,"losses":3,"wins":52},"inception/mercury-3":{"draws":7,"losses":15,"wins":10},"inclusionai/ling-3.0-flash":{"draws":27,"losses":14,"wins":57},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":34,"losses":23,"wins":95},"meta/muse-glimmer-30b":{"draws":31,"losses":17,"wins":74},"meta/muse-spark-1.2":{"draws":26,"losses":47,"wins":59},"meta/muse-spark-1.3":{"draws":29,"losses":55,"wins":54},"meta/muse-spark-open":{"draws":16,"losses":31,"wins":27},"meta/muse-wonder":{"draws":29,"losses":66,"wins":43},"minimax/minimax-m3":{"draws":15,"losses":16,"wins":43},"minimax/minimax-m3.1-flash":{"draws":15,"losses":10,"wins":49},"mistralai/mistral-large-4-0":{"draws":30,"losses":16,"wins":40},"mistralai/mistral-medium-3-5":{"draws":23,"losses":12,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":20},"moonshotai/kimi-k3":{"draws":27,"losses":37,"wins":68},"nex-agi/nex-n2-pro":{"draws":18,"losses":15,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":8,"wins":70},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":20},"o3":{"draws":21,"losses":48,"wins":127},"openai/gpt-oss-120b":{"draws":33,"losses":20,"wins":67},"poolside/laguna-s-2.1":{"draws":36,"losses":15,"wins":81},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":43},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":53,"wins":56},"qwen/qwen3.8-27b":{"draws":22,"losses":20,"wins":56},"qwen/qwen3.8-flash":{"draws":21,"losses":28,"wins":43},"qwen/qwen3.8-max":{"draws":38,"losses":49,"wins":51},"qwen/qwen3.8-max-0902":{"draws":31,"losses":45,"wins":62},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":22,"wins":21},"stealth/ox-alpha":{"draws":124,"losses":155,"wins":179},"stealth/space-bunny-alpha":{"draws":33,"losses":16,"wins":61},"stepfun/step-3.7-flash":{"draws":18,"losses":16,"wins":66},"stepfun/step-5-preview":{"draws":5,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":28,"losses":13,"wins":33},"tencent/hy4-preview":{"draws":30,"losses":48,"wins":56},"thinkingmachines/inkling":{"draws":49,"losses":29,"wins":108},"thinkingmachines/inkling-small":{"draws":43,"losses":15,"wins":80},"unbiased/pareto-26.10":{"draws":4,"losses":28,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":38,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":33,"losses":46,"wins":59},"x-ai/grok-4.6":{"draws":40,"losses":51,"wins":47},"x-ai/grok-4.7":{"draws":13,"losses":79,"wins":28},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":28},"xiaomi/mimo-v2.5":{"draws":57,"losses":21,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":13,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":27,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":38,"wins":37},"z-ai/glm-5.2":{"draws":81,"losses":59,"wins":136},"z-ai/glm-5.3":{"draws":25,"losses":69,"wins":38},"z-ai/glm-5.3-flash":{"draws":18,"losses":57,"wins":63},"z-ai/glm-5.3-flashx":{"draws":34,"losses":54,"wins":50}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":28,"wins":25},"claude-fable-5":{"draws":23,"losses":62,"wins":11},"claude-fable-5-1":{"draws":4,"losses":104,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":53,"wins":12},"claude-opus-4-5":{"draws":57,"losses":64,"wins":35},"claude-opus-4-8":{"draws":23,"losses":44,"wins":21},"claude-opus-5":{"draws":32,"losses":120,"wins":12},"claude-opus-5-5":{"draws":5,"losses":97,"wins":2},"claude-sonnet-5":{"draws":38,"losses":30,"wins":28},"claude-sonnet-5-5":{"draws":17,"losses":62,"wins":17},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":56,"losses":38,"wins":50},"deepseek/deepseek-v4-pro":{"draws":32,"losses":33,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":38,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":39,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":34,"wins":6},"elorian/glimpse":{"draws":7,"losses":4,"wins":9},"fireworks/ember-1":{"draws":36,"losses":45,"wins":15},"gemini-3.1-pro-preview":{"draws":37,"losses":34,"wins":25},"gemini-4-argon":{"draws":8,"losses":40,"wins":0},"google/gemini-3.1-flash-lite":{"draws":21,"losses":6,"wins":37},"google/gemini-3.5-flash":{"draws":42,"losses":50,"wins":28},"google/gemini-3.5-flash-lite":{"draws":58,"losses":52,"wins":58},"google/gemini-3.6-flash":{"draws":55,"losses":99,"wins":30},"google/gemini-3.8-flash":{"draws":23,"losses":60,"wins":13},"google/gemma-4-31b-it":{"draws":22,"losses":10,"wins":24},"gpt-4.1":{"draws":12,"losses":7,"wins":13},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":3},"gpt-5":{"draws":27,"losses":30,"wins":27},"gpt-5.4":{"draws":30,"losses":56,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":26,"losses":41,"wins":29},"gpt-5.5":{"draws":40,"losses":33,"wins":15},"gpt-5.6-luna":{"draws":38,"losses":31,"wins":27},"gpt-5.6-sol":{"draws":19,"losses":65,"wins":12},"gpt-5.6-terra":{"draws":39,"losses":32,"wins":21},"gpt-6-astra":{"draws":6,"losses":90,"wins":0},"gpt-6-luna":{"draws":43,"losses":40,"wins":13},"gpt-6-sol":{"draws":13,"losses":72,"wins":11},"gpt-6.1-sol":{"draws":5,"losses":87,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":14,"wins":23},"inception/mercury-3":{"draws":11,"losses":19,"wins":2},"inclusionai/ling-3.0-flash":{"draws":31,"losses":12,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":28,"wins":36},"meta/muse-glimmer-30b":{"draws":43,"losses":11,"wins":30},"meta/muse-spark-1.2":{"draws":27,"losses":45,"wins":20},"meta/muse-spark-1.3":{"draws":19,"losses":66,"wins":11},"meta/muse-spark-open":{"draws":10,"losses":20,"wins":2},"meta/muse-wonder":{"draws":24,"losses":62,"wins":10},"minimax/minimax-m3":{"draws":18,"losses":17,"wins":17},"minimax/minimax-m3.1-flash":{"draws":24,"losses":25,"wins":9},"mistralai/mistral-large-4-0":{"draws":28,"losses":20,"wins":12},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":32,"losses":38,"wins":22},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":21,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":17,"wins":3},"o3":{"draws":26,"losses":71,"wins":35},"openai/gpt-oss-120b":{"draws":32,"losses":21,"wins":31},"poolside/laguna-s-2.1":{"draws":39,"losses":22,"wins":31},"qwen/qwen3.7-max":{"draws":19,"losses":22,"wins":15},"qwen/qwen3.7-plus":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":49,"wins":13},"qwen/qwen3.8-27b":{"draws":17,"losses":32,"wins":19},"qwen/qwen3.8-flash":{"draws":25,"losses":25,"wins":14},"qwen/qwen3.8-max":{"draws":41,"losses":37,"wins":18},"qwen/qwen3.8-max-0902":{"draws":38,"losses":44,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":22,"wins":6},"stealth/ox-alpha":{"draws":94,"losses":162,"wins":60},"stealth/space-bunny-alpha":{"draws":28,"losses":33,"wins":15},"stepfun/step-3.7-flash":{"draws":22,"losses":22,"wins":24},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":21,"losses":17,"wins":14},"tencent/hy4-preview":{"draws":34,"losses":47,"wins":11},"thinkingmachines/inkling":{"draws":48,"losses":37,"wins":43},"thinkingmachines/inkling-small":{"draws":44,"losses":22,"wins":30},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":31,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":11},"x-ai/grok-4.5":{"draws":30,"losses":52,"wins":14},"x-ai/grok-4.6":{"draws":32,"losses":50,"wins":14},"x-ai/grok-4.7":{"draws":14,"losses":66,"wins":4},"x-ai/grok-build-0.1":{"draws":12,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":57,"losses":40,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":17,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":32,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":40,"wins":9},"z-ai/glm-5.2":{"draws":87,"losses":70,"wins":35},"z-ai/glm-5.3":{"draws":21,"losses":62,"wins":9},"z-ai/glm-5.3-flash":{"draws":27,"losses":53,"wins":16},"z-ai/glm-5.3-flashx":{"draws":27,"losses":56,"wins":13}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":54,"wins":48},"claude-fable-5":{"draws":19,"losses":112,"wins":13},"claude-fable-5-1":{"draws":1,"losses":153,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":76,"wins":39},"claude-opus-4-5":{"draws":64,"losses":110,"wins":64},"claude-opus-4-8":{"draws":25,"losses":84,"wins":31},"claude-opus-5":{"draws":21,"losses":198,"wins":17},"claude-opus-5-5":{"draws":7,"losses":151,"wins":2},"claude-sonnet-5":{"draws":33,"losses":71,"wins":40},"claude-sonnet-5-5":{"draws":20,"losses":105,"wins":19},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":36},"deepseek/deepseek-v4-flash":{"draws":51,"losses":81,"wins":94},"deepseek/deepseek-v4-pro":{"draws":18,"losses":67,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":63,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":72,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":55,"wins":15},"elorian/glimpse":{"draws":7,"losses":18,"wins":11},"fireworks/ember-1":{"draws":35,"losses":78,"wins":31},"gemini-3.1-pro-preview":{"draws":36,"losses":68,"wins":40},"gemini-4-argon":{"draws":1,"losses":67,"wins":0},"google/gemini-3.1-flash-lite":{"draws":24,"losses":22,"wins":62},"google/gemini-3.5-flash":{"draws":34,"losses":102,"wins":48},"google/gemini-3.5-flash-lite":{"draws":51,"losses":106,"wins":95},"google/gemini-3.6-flash":{"draws":50,"losses":166,"wins":58},"google/gemini-3.8-flash":{"draws":29,"losses":91,"wins":24},"google/gemma-4-31b-it":{"draws":26,"losses":17,"wins":43},"gpt-4.1":{"draws":10,"losses":20,"wins":18},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":7},"gpt-5":{"draws":20,"losses":65,"wins":43},"gpt-5.4":{"draws":19,"losses":87,"wins":32},"gpt-5.4-mini":{"draws":26,"losses":29,"wins":41},"gpt-5.4-nano":{"draws":20,"losses":50,"wins":50},"gpt-5.5":{"draws":33,"losses":64,"wins":33},"gpt-5.6-luna":{"draws":35,"losses":60,"wins":49},"gpt-5.6-sol":{"draws":11,"losses":117,"wins":16},"gpt-5.6-terra":{"draws":26,"losses":72,"wins":38},"gpt-6-astra":{"draws":2,"losses":140,"wins":2},"gpt-6-luna":{"draws":30,"losses":72,"wins":42},"gpt-6-sol":{"draws":20,"losses":112,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":132,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":14,"wins":56},"inception/mercury-3":{"draws":15,"losses":22,"wins":13},"inclusionai/ling-3.0-flash":{"draws":30,"losses":26,"wins":48},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":27,"losses":50,"wins":83},"meta/muse-glimmer-30b":{"draws":31,"losses":42,"wins":49},"meta/muse-spark-1.2":{"draws":22,"losses":69,"wins":45},"meta/muse-spark-1.3":{"draws":26,"losses":90,"wins":28},"meta/muse-spark-open":{"draws":4,"losses":43,"wins":9},"meta/muse-wonder":{"draws":12,"losses":110,"wins":22},"minimax/minimax-m3":{"draws":18,"losses":27,"wins":39},"minimax/minimax-m3.1-flash":{"draws":10,"losses":31,"wins":35},"mistralai/mistral-large-4-0":{"draws":16,"losses":48,"wins":24},"mistralai/mistral-medium-3-5":{"draws":19,"losses":16,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":16,"wins":14},"moonshotai/kimi-k3":{"draws":34,"losses":68,"wins":34},"nex-agi/nex-n2-pro":{"draws":16,"losses":22,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":9,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":45,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":22,"wins":16},"o3":{"draws":20,"losses":103,"wins":103},"openai/gpt-oss-120b":{"draws":35,"losses":47,"wins":44},"poolside/laguna-s-2.1":{"draws":40,"losses":54,"wins":50},"qwen/qwen3.7-max":{"draws":27,"losses":36,"wins":29},"qwen/qwen3.7-plus":{"draws":19,"losses":30,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":79,"wins":28},"qwen/qwen3.8-27b":{"draws":22,"losses":48,"wins":34},"qwen/qwen3.8-flash":{"draws":25,"losses":45,"wins":26},"qwen/qwen3.8-max":{"draws":33,"losses":74,"wins":37},"qwen/qwen3.8-max-0902":{"draws":37,"losses":72,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":35,"wins":13},"stealth/ox-alpha":{"draws":83,"losses":223,"wins":118},"stealth/space-bunny-alpha":{"draws":26,"losses":47,"wins":39},"stepfun/step-3.7-flash":{"draws":16,"losses":34,"wins":60},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":4},"tencent/hy3-preview":{"draws":20,"losses":37,"wins":23},"tencent/hy4-preview":{"draws":23,"losses":87,"wins":28},"thinkingmachines/inkling":{"draws":42,"losses":69,"wins":77},"thinkingmachines/inkling-small":{"draws":49,"losses":39,"wins":56},"unbiased/pareto-26.10":{"draws":3,"losses":22,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":47,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":15,"wins":22},"x-ai/grok-4.5":{"draws":30,"losses":84,"wins":30},"x-ai/grok-4.6":{"draws":23,"losses":97,"wins":24},"x-ai/grok-4.7":{"draws":16,"losses":105,"wins":11},"x-ai/grok-build-0.1":{"draws":11,"losses":14,"wins":23},"xiaomi/mimo-v2.5":{"draws":55,"losses":74,"wins":107},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":37,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":50,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":66,"wins":17},"z-ai/glm-5.2":{"draws":71,"losses":121,"wins":96},"z-ai/glm-5.3":{"draws":20,"losses":95,"wins":21},"z-ai/glm-5.3-flash":{"draws":21,"losses":85,"wins":38},"z-ai/glm-5.3-flashx":{"draws":30,"losses":80,"wins":34}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":21,"wins":54},"claude-fable-5":{"draws":31,"losses":63,"wins":38},"claude-fable-5-1":{"draws":5,"losses":127,"wins":18},"claude-haiku-5-5":{"draws":46,"losses":45,"wins":35},"claude-opus-4-5":{"draws":88,"losses":47,"wins":79},"claude-opus-4-8":{"draws":38,"losses":35,"wins":47},"claude-opus-5":{"draws":31,"losses":156,"wins":45},"claude-opus-5-5":{"draws":14,"losses":115,"wins":15},"claude-sonnet-5":{"draws":49,"losses":25,"wins":58},"claude-sonnet-5-5":{"draws":29,"losses":61,"wins":42},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":36},"deepseek/deepseek-v4-flash":{"draws":69,"losses":21,"wins":106},"deepseek/deepseek-v4-pro":{"draws":36,"losses":28,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":36,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":45,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":25,"wins":26},"elorian/glimpse":{"draws":7,"losses":13,"wins":28},"fireworks/ember-1":{"draws":42,"losses":41,"wins":49},"gemini-3.1-pro-preview":{"draws":38,"losses":32,"wins":62},"gemini-4-argon":{"draws":6,"losses":42,"wins":8},"google/gemini-3.1-flash-lite":{"draws":25,"losses":5,"wins":58},"google/gemini-3.5-flash":{"draws":49,"losses":48,"wins":69},"google/gemini-3.5-flash-lite":{"draws":89,"losses":34,"wins":109},"google/gemini-3.6-flash":{"draws":74,"losses":87,"wins":93},"google/gemini-3.8-flash":{"draws":44,"losses":44,"wins":44},"google/gemma-4-31b-it":{"draws":30,"losses":6,"wins":40},"gpt-4.1":{"draws":10,"losses":9,"wins":25},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":4},"gpt-5":{"draws":42,"losses":27,"wins":49},"gpt-5.4":{"draws":40,"losses":46,"wins":42},"gpt-5.4-mini":{"draws":40,"losses":15,"wins":33},"gpt-5.4-nano":{"draws":33,"losses":33,"wins":64},"gpt-5.5":{"draws":36,"losses":22,"wins":22},"gpt-5.6-luna":{"draws":49,"losses":22,"wins":61},"gpt-5.6-sol":{"draws":25,"losses":61,"wins":46},"gpt-5.6-terra":{"draws":48,"losses":29,"wins":49},"gpt-6-astra":{"draws":4,"losses":118,"wins":10},"gpt-6-luna":{"draws":52,"losses":27,"wins":53},"gpt-6-sol":{"draws":20,"losses":83,"wins":29},"gpt-6.1-sol":{"draws":8,"losses":103,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":40,"losses":8,"wins":42},"inception/mercury-3":{"draws":17,"losses":9,"wins":14},"inclusionai/ling-3.0-flash":{"draws":41,"losses":7,"wins":44},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":46,"losses":26,"wins":72},"meta/muse-glimmer-30b":{"draws":48,"losses":16,"wins":56},"meta/muse-spark-1.2":{"draws":26,"losses":44,"wins":58},"meta/muse-spark-1.3":{"draws":31,"losses":52,"wins":49},"meta/muse-spark-open":{"draws":17,"losses":30,"wins":17},"meta/muse-wonder":{"draws":37,"losses":59,"wins":36},"minimax/minimax-m3":{"draws":24,"losses":11,"wins":37},"minimax/minimax-m3.1-flash":{"draws":25,"losses":13,"wins":24},"mistralai/mistral-large-4-0":{"draws":29,"losses":22,"wins":33},"mistralai/mistral-medium-3-5":{"draws":26,"losses":8,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":10,"wins":11},"moonshotai/kimi-k3":{"draws":37,"losses":46,"wins":45},"nex-agi/nex-n2-pro":{"draws":18,"losses":5,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":8,"wins":54},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":4,"wins":18},"o3":{"draws":36,"losses":44,"wins":104},"openai/gpt-oss-120b":{"draws":44,"losses":16,"wins":56},"poolside/laguna-s-2.1":{"draws":52,"losses":21,"wins":55},"qwen/qwen3.7-max":{"draws":27,"losses":14,"wins":35},"qwen/qwen3.7-plus":{"draws":26,"losses":6,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":45,"wins":47},"qwen/qwen3.8-27b":{"draws":29,"losses":26,"wins":37},"qwen/qwen3.8-flash":{"draws":34,"losses":18,"wins":36},"qwen/qwen3.8-max":{"draws":44,"losses":40,"wins":48},"qwen/qwen3.8-max-0902":{"draws":47,"losses":43,"wins":42},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":15,"wins":28},"stealth/ox-alpha":{"draws":123,"losses":164,"wins":155},"stealth/space-bunny-alpha":{"draws":41,"losses":19,"wins":46},"stepfun/step-3.7-flash":{"draws":26,"losses":14,"wins":54},"stepfun/step-5-preview":{"draws":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":33,"losses":9,"wins":30},"tencent/hy4-preview":{"draws":44,"losses":44,"wins":40},"thinkingmachines/inkling":{"draws":55,"losses":27,"wins":98},"thinkingmachines/inkling-small":{"draws":50,"losses":18,"wins":64},"unbiased/pareto-26.10":{"draws":2,"losses":20,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":39,"wins":4},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":20},"x-ai/grok-4.5":{"draws":35,"losses":51,"wins":46},"x-ai/grok-4.6":{"draws":41,"losses":55,"wins":36},"x-ai/grok-4.7":{"draws":11,"losses":69,"wins":36},"x-ai/grok-build-0.1":{"draws":23,"losses":7,"wins":14},"xiaomi/mimo-v2.5":{"draws":85,"losses":20,"wins":97},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":12,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":26,"losses":23,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":37,"wins":31},"z-ai/glm-5.2":{"draws":101,"losses":48,"wins":115},"z-ai/glm-5.3":{"draws":31,"losses":72,"wins":23},"z-ai/glm-5.3-flash":{"draws":24,"losses":58,"wins":50},"z-ai/glm-5.3-flashx":{"draws":42,"losses":47,"wins":43}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":47,"wins":42},"claude-fable-5":{"draws":34,"losses":92,"wins":18},"claude-fable-5-1":{"draws":9,"losses":148,"wins":5},"claude-haiku-5-5":{"draws":40,"losses":74,"wins":24},"claude-opus-4-5":{"draws":84,"losses":91,"wins":59},"claude-opus-4-8":{"draws":42,"losses":62,"wins":28},"claude-opus-5":{"draws":26,"losses":195,"wins":25},"claude-opus-5-5":{"draws":17,"losses":134,"wins":5},"claude-sonnet-5":{"draws":45,"losses":61,"wins":38},"claude-sonnet-5-5":{"draws":33,"losses":84,"wins":27},"cohere/north-mini-code":{"draws":16,"losses":10,"wins":28},"deepseek/deepseek-v4-flash":{"draws":83,"losses":50,"wins":83},"deepseek/deepseek-v4-pro":{"draws":43,"losses":52,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":51,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":64,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":54,"wins":6},"elorian/glimpse":{"draws":12,"losses":23,"wins":13},"fireworks/ember-1":{"draws":50,"losses":54,"wins":40},"gemini-3.1-pro-preview":{"draws":42,"losses":56,"wins":46},"gemini-4-argon":{"draws":7,"losses":46,"wins":3},"google/gemini-3.1-flash-lite":{"draws":26,"losses":20,"wins":50},"google/gemini-3.5-flash":{"draws":50,"losses":81,"wins":49},"google/gemini-3.5-flash-lite":{"draws":83,"losses":73,"wins":96},"google/gemini-3.6-flash":{"draws":79,"losses":138,"wins":59},"google/gemini-3.8-flash":{"draws":32,"losses":87,"wins":25},"google/gemma-4-31b-it":{"draws":34,"losses":20,"wins":30},"gpt-4.1":{"draws":17,"losses":16,"wins":15},"gpt-4.1-nano":{"draws":11,"losses":1,"wins":6},"gpt-5":{"draws":40,"losses":51,"wins":35},"gpt-5.4":{"draws":46,"losses":71,"wins":21},"gpt-5.4-mini":{"draws":38,"losses":27,"wins":31},"gpt-5.4-nano":{"draws":35,"losses":49,"wins":60},"gpt-5.5":{"draws":49,"losses":61,"wins":22},"gpt-5.6-luna":{"draws":40,"losses":28,"wins":28},"gpt-5.6-sol":{"draws":21,"losses":99,"wins":24},"gpt-5.6-terra":{"draws":45,"losses":49,"wins":44},"gpt-6-astra":{"draws":15,"losses":127,"wins":2},"gpt-6-luna":{"draws":48,"losses":58,"wins":38},"gpt-6-sol":{"draws":24,"losses":106,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":125,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":51,"losses":17,"wins":34},"inception/mercury-3":{"draws":17,"losses":20,"wins":15},"inclusionai/ling-3.0-flash":{"draws":48,"losses":19,"wins":35},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":48,"losses":47,"wins":61},"meta/muse-glimmer-30b":{"draws":52,"losses":32,"wins":42},"meta/muse-spark-1.2":{"draws":36,"losses":66,"wins":36},"meta/muse-spark-1.3":{"draws":36,"losses":79,"wins":29},"meta/muse-spark-open":{"draws":25,"losses":37,"wins":16},"meta/muse-wonder":{"draws":28,"losses":91,"wins":25},"minimax/minimax-m3":{"draws":26,"losses":21,"wins":31},"minimax/minimax-m3.1-flash":{"draws":19,"losses":27,"wins":26},"mistralai/mistral-large-4-0":{"draws":32,"losses":43,"wins":15},"mistralai/mistral-medium-3-5":{"draws":34,"losses":12,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":15,"wins":9},"moonshotai/kimi-k3":{"draws":46,"losses":61,"wins":31},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":41},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":33,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":14,"wins":12},"o3":{"draws":40,"losses":88,"wins":70},"openai/gpt-oss-120b":{"draws":57,"losses":27,"wins":42},"poolside/laguna-s-2.1":{"draws":51,"losses":41,"wins":46},"qwen/qwen3.7-max":{"draws":31,"losses":32,"wins":21},"qwen/qwen3.7-plus":{"draws":26,"losses":18,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":66,"wins":27},"qwen/qwen3.8-27b":{"draws":32,"losses":45,"wins":25},"qwen/qwen3.8-flash":{"draws":31,"losses":37,"wins":28},"qwen/qwen3.8-max":{"draws":48,"losses":65,"wins":31},"qwen/qwen3.8-max-0902":{"draws":51,"losses":61,"wins":32},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":22,"wins":17},"stealth/ox-alpha":{"draws":146,"losses":228,"wins":100},"stealth/space-bunny-alpha":{"draws":43,"losses":40,"wins":31},"stepfun/step-3.7-flash":{"draws":27,"losses":31,"wins":44},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":29,"losses":28,"wins":21},"tencent/hy4-preview":{"draws":43,"losses":69,"wins":26},"thinkingmachines/inkling":{"draws":63,"losses":44,"wins":85},"thinkingmachines/inkling-small":{"draws":58,"losses":37,"wins":49},"unbiased/pareto-26.10":{"draws":3,"losses":24,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":17},"x-ai/grok-4.5":{"draws":37,"losses":72,"wins":35},"x-ai/grok-4.6":{"draws":37,"losses":84,"wins":23},"x-ai/grok-4.7":{"draws":13,"losses":96,"wins":17},"x-ai/grok-build-0.1":{"draws":19,"losses":11,"wins":18},"xiaomi/mimo-v2.5":{"draws":91,"losses":47,"wins":84},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":28,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":62,"wins":17},"z-ai/glm-5.2":{"draws":108,"losses":110,"wins":70},"z-ai/glm-5.3":{"draws":28,"losses":95,"wins":15},"z-ai/glm-5.3-flash":{"draws":37,"losses":78,"wins":29},"z-ai/glm-5.3-flashx":{"draws":42,"losses":73,"wins":29}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":15,"wins":95},"claude-fable-5":{"draws":17,"losses":69,"wins":58},"claude-fable-5-1":{"draws":12,"losses":129,"wins":21},"claude-haiku-5-5":{"draws":21,"losses":41,"wins":76},"claude-opus-4-5":{"draws":44,"losses":41,"wins":149},"claude-opus-4-8":{"draws":17,"losses":43,"wins":72},"claude-opus-5":{"draws":29,"losses":157,"wins":60},"claude-opus-5-5":{"draws":12,"losses":123,"wins":21},"claude-sonnet-5":{"draws":20,"losses":19,"wins":105},"claude-sonnet-5-5":{"draws":15,"losses":58,"wins":71},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":47},"deepseek/deepseek-v4-flash":{"draws":29,"losses":20,"wins":167},"deepseek/deepseek-v4-pro":{"draws":16,"losses":30,"wins":86},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":27,"wins":88},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":43,"wins":75},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":25,"wins":37},"elorian/glimpse":{"draws":5,"losses":12,"wins":19},"fireworks/ember-1":{"draws":23,"losses":38,"wins":83},"gemini-3.1-pro-preview":{"draws":18,"losses":30,"wins":96},"gemini-4-argon":{"draws":7,"losses":52,"wins":19},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":83},"google/gemini-3.5-flash":{"draws":18,"losses":41,"wins":121},"google/gemini-3.5-flash-lite":{"draws":36,"losses":22,"wins":194},"google/gemini-3.6-flash":{"draws":41,"losses":76,"wins":159},"google/gemini-3.8-flash":{"draws":19,"losses":53,"wins":72},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":67},"gpt-4.1":{"draws":8,"losses":5,"wins":35},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":14},"gpt-5":{"draws":17,"losses":17,"wins":92},"gpt-5.4":{"draws":23,"losses":47,"wins":68},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":65},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":117},"gpt-5.5":{"draws":25,"losses":46,"wins":61},"gpt-5.6-luna":{"draws":21,"losses":24,"wins":99},"gpt-5.6-sol":{"draws":8,"losses":44,"wins":44},"gpt-5.6-terra":{"draws":28,"losses":26,"wins":84},"gpt-6-astra":{"draws":15,"losses":117,"wins":12},"gpt-6-luna":{"draws":28,"losses":24,"wins":92},"gpt-6-sol":{"draws":13,"losses":85,"wins":46},"gpt-6.1-sol":{"draws":13,"losses":109,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":83},"inception/mercury-3":{"draws":10,"losses":7,"wins":29},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":86},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":20,"losses":14,"wins":122},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":99},"meta/muse-spark-1.2":{"draws":17,"losses":33,"wins":88},"meta/muse-spark-1.3":{"draws":21,"losses":48,"wins":75},"meta/muse-spark-open":{"draws":10,"losses":24,"wins":40},"meta/muse-wonder":{"draws":22,"losses":65,"wins":57},"minimax/minimax-m3":{"draws":13,"losses":4,"wins":61},"minimax/minimax-m3.1-flash":{"draws":10,"losses":12,"wins":54},"mistralai/mistral-large-4-0":{"draws":19,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":23},"moonshotai/kimi-k3":{"draws":22,"losses":32,"wins":84},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":59},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":100},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":29},"o3":{"draws":14,"losses":31,"wins":153},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":104},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":111},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":59},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":37,"wins":84},"qwen/qwen3.8-27b":{"draws":16,"losses":18,"wins":68},"qwen/qwen3.8-flash":{"draws":17,"losses":18,"wins":61},"qwen/qwen3.8-max":{"draws":26,"losses":30,"wins":88},"qwen/qwen3.8-max-0902":{"draws":23,"losses":34,"wins":87},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":7,"wins":30},"stealth/ox-alpha":{"draws":72,"losses":116,"wins":286},"stealth/space-bunny-alpha":{"draws":20,"losses":14,"wins":80},"stepfun/step-3.7-flash":{"draws":11,"losses":6,"wins":85},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":55},"tencent/hy4-preview":{"draws":20,"losses":48,"wins":70},"thinkingmachines/inkling":{"draws":28,"losses":17,"wins":147},"thinkingmachines/inkling-small":{"draws":22,"losses":13,"wins":109},"unbiased/pareto-26.10":{"draws":2,"losses":31,"wins":3},"unbiased/pareto-26.10-preview":{"draws":3,"losses":43,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":32},"x-ai/grok-4.5":{"draws":19,"losses":43,"wins":82},"x-ai/grok-4.6":{"draws":28,"losses":56,"wins":60},"x-ai/grok-4.7":{"draws":16,"losses":68,"wins":42},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":34},"xiaomi/mimo-v2.5":{"draws":36,"losses":12,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":19,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":35,"wins":44},"z-ai/glm-5.2":{"draws":37,"losses":45,"wins":206},"z-ai/glm-5.3":{"draws":23,"losses":55,"wins":60},"z-ai/glm-5.3-flash":{"draws":25,"losses":47,"wins":72},"z-ai/glm-5.3-flashx":{"draws":23,"losses":41,"wins":80}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":24,"wins":65},"claude-fable-5":{"draws":38,"losses":81,"wins":19},"claude-fable-5-1":{"draws":11,"losses":142,"wins":3},"claude-haiku-5-5":{"draws":39,"losses":56,"wins":37},"claude-opus-4-5":{"draws":80,"losses":77,"wins":67},"claude-opus-4-8":{"draws":32,"losses":59,"wins":35},"claude-opus-5":{"draws":29,"losses":184,"wins":21},"claude-opus-5-5":{"draws":9,"losses":138,"wins":3},"claude-sonnet-5":{"draws":53,"losses":41,"wins":44},"claude-sonnet-5-5":{"draws":33,"losses":74,"wins":31},"cohere/north-mini-code":{"draws":11,"losses":6,"wins":33},"deepseek/deepseek-v4-flash":{"draws":67,"losses":32,"wins":109},"deepseek/deepseek-v4-pro":{"draws":40,"losses":44,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":40,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":55,"losses":49,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":41,"wins":17},"elorian/glimpse":{"draws":8,"losses":15,"wins":11},"fireworks/ember-1":{"draws":44,"losses":58,"wins":36},"gemini-3.1-pro-preview":{"draws":47,"losses":47,"wins":44},"gemini-4-argon":{"draws":7,"losses":51,"wins":2},"google/gemini-3.1-flash-lite":{"draws":28,"losses":7,"wins":55},"google/gemini-3.5-flash":{"draws":54,"losses":53,"wins":65},"google/gemini-3.5-flash-lite":{"draws":74,"losses":49,"wins":117},"google/gemini-3.6-flash":{"draws":82,"losses":114,"wins":68},"google/gemini-3.8-flash":{"draws":40,"losses":62,"wins":36},"google/gemma-4-31b-it":{"draws":32,"losses":9,"wins":39},"gpt-4.1":{"draws":19,"losses":15,"wins":12},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":31,"losses":38,"wins":51},"gpt-5.4":{"draws":37,"losses":60,"wins":35},"gpt-5.4-mini":{"draws":39,"losses":21,"wins":32},"gpt-5.4-nano":{"draws":26,"losses":38,"wins":72},"gpt-5.5":{"draws":48,"losses":49,"wins":29},"gpt-5.6-luna":{"draws":45,"losses":44,"wins":49},"gpt-5.6-sol":{"draws":28,"losses":84,"wins":26},"gpt-5.6-terra":{"draws":32,"losses":28,"wins":28},"gpt-6-astra":{"draws":12,"losses":122,"wins":4},"gpt-6-luna":{"draws":40,"losses":57,"wins":41},"gpt-6-sol":{"draws":24,"losses":98,"wins":16},"gpt-6.1-sol":{"draws":9,"losses":122,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":42,"losses":7,"wins":49},"inception/mercury-3":{"draws":21,"losses":18,"wins":21},"inclusionai/ling-3.0-flash":{"draws":35,"losses":7,"wins":60},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":43,"losses":33,"wins":72},"meta/muse-glimmer-30b":{"draws":47,"losses":16,"wins":57},"meta/muse-spark-1.2":{"draws":40,"losses":54,"wins":38},"meta/muse-spark-1.3":{"draws":33,"losses":66,"wins":39},"meta/muse-spark-open":{"draws":24,"losses":25,"wins":17},"meta/muse-wonder":{"draws":31,"losses":77,"wins":30},"minimax/minimax-m3":{"draws":19,"losses":13,"wins":42},"minimax/minimax-m3.1-flash":{"draws":17,"losses":22,"wins":29},"mistralai/mistral-large-4-0":{"draws":41,"losses":26,"wins":19},"mistralai/mistral-medium-3-5":{"draws":26,"losses":8,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":38,"losses":51,"wins":43},"nex-agi/nex-n2-pro":{"draws":19,"losses":8,"wins":41},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":19,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":12,"wins":10},"o3":{"draws":37,"losses":67,"wins":82},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":66},"poolside/laguna-s-2.1":{"draws":52,"losses":16,"wins":62},"qwen/qwen3.7-max":{"draws":24,"losses":16,"wins":40},"qwen/qwen3.7-plus":{"draws":27,"losses":11,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":49,"losses":60,"wins":29},"qwen/qwen3.8-27b":{"draws":36,"losses":29,"wins":33},"qwen/qwen3.8-flash":{"draws":30,"losses":29,"wins":33},"qwen/qwen3.8-max":{"draws":58,"losses":44,"wins":36},"qwen/qwen3.8-max-0902":{"draws":48,"losses":53,"wins":37},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":14,"wins":15},"stealth/ox-alpha":{"draws":135,"losses":195,"wins":126},"stealth/space-bunny-alpha":{"draws":37,"losses":32,"wins":39},"stepfun/step-3.7-flash":{"draws":24,"losses":21,"wins":53},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":31,"losses":15,"wins":28},"tencent/hy4-preview":{"draws":37,"losses":59,"wins":36},"thinkingmachines/inkling":{"draws":55,"losses":36,"wins":91},"thinkingmachines/inkling-small":{"draws":46,"losses":22,"wins":70},"unbiased/pareto-26.10":{"draws":3,"losses":26,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":39,"wins":4},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":25},"x-ai/grok-4.5":{"draws":39,"losses":69,"wins":30},"x-ai/grok-4.6":{"draws":46,"losses":71,"wins":21},"x-ai/grok-4.7":{"draws":13,"losses":86,"wins":21},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":24},"xiaomi/mimo-v2.5":{"draws":79,"losses":15,"wins":118},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":12,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":32,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":44,"wins":24},"z-ai/glm-5.2":{"draws":117,"losses":63,"wins":96},"z-ai/glm-5.3":{"draws":36,"losses":75,"wins":21},"z-ai/glm-5.3-flash":{"draws":33,"losses":65,"wins":40},"z-ai/glm-5.3-flashx":{"draws":38,"losses":63,"wins":37}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":118},"claude-fable-5":{"draws":8,"losses":24,"wins":112},"claude-fable-5-1":{"draws":15,"losses":58,"wins":89},"claude-haiku-5-5":{"draws":10,"losses":7,"wins":121},"claude-opus-4-5":{"draws":15,"losses":15,"wins":204},"claude-opus-4-8":{"draws":8,"losses":11,"wins":113},"claude-opus-5":{"draws":23,"losses":57,"wins":166},"claude-opus-5-5":{"draws":16,"losses":67,"wins":73},"claude-sonnet-5":{"draws":6,"losses":8,"wins":130},"claude-sonnet-5-5":{"draws":13,"losses":28,"wins":103},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":200},"deepseek/deepseek-v4-pro":{"draws":11,"losses":8,"wins":113},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":1,"wins":123},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":6,"wins":122},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":4,"wins":68},"elorian/glimpse":{"draws":1,"losses":3,"wins":32},"fireworks/ember-1":{"draws":10,"losses":6,"wins":128},"gemini-3.1-pro-preview":{"draws":10,"losses":4,"wins":130},"gemini-4-argon":{"draws":9,"losses":18,"wins":43},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":94},"google/gemini-3.5-flash":{"draws":11,"losses":7,"wins":162},"google/gemini-3.5-flash-lite":{"draws":14,"losses":1,"wins":237},"google/gemini-3.6-flash":{"draws":20,"losses":17,"wins":239},"google/gemini-3.8-flash":{"draws":14,"losses":9,"wins":121},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":80},"gpt-4.1":{"draws":3,"losses":0,"wins":45},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":2,"wins":115},"gpt-5.4":{"draws":6,"losses":16,"wins":116},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":90},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":140},"gpt-5.5":{"draws":4,"losses":10,"wins":118},"gpt-5.6-luna":{"draws":15,"losses":2,"wins":127},"gpt-5.6-sol":{"draws":15,"losses":12,"wins":117},"gpt-5.6-terra":{"draws":12,"losses":4,"wins":122},"gpt-6-astra":{"draws":8,"losses":44,"wins":44},"gpt-6-luna":{"draws":15,"losses":9,"wins":120},"gpt-6-sol":{"draws":15,"losses":26,"wins":103},"gpt-6.1-sol":{"draws":18,"losses":50,"wins":76},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":95},"inception/mercury-3":{"draws":4,"losses":0,"wins":42},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":96},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":146},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":120},"meta/muse-spark-1.2":{"draws":7,"losses":4,"wins":127},"meta/muse-spark-1.3":{"draws":14,"losses":13,"wins":117},"meta/muse-spark-open":{"draws":5,"losses":1,"wins":58},"meta/muse-wonder":{"draws":14,"losses":16,"wins":114},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":75},"minimax/minimax-m3.1-flash":{"draws":6,"losses":0,"wins":68},"mistralai/mistral-large-4-0":{"draws":9,"losses":5,"wins":76},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":33},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":119},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":68},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":116},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":48},"o3":{"draws":7,"losses":2,"wins":189},"openai/gpt-oss-120b":{"draws":12,"losses":0,"wins":114},"poolside/laguna-s-2.1":{"draws":7,"losses":0,"wins":131},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":77},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":69},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":6,"wins":133},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":97},"qwen/qwen3.8-flash":{"draws":13,"losses":3,"wins":80},"qwen/qwen3.8-max":{"draws":13,"losses":2,"wins":129},"qwen/qwen3.8-max-0902":{"draws":9,"losses":6,"wins":129},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":1,"wins":60},"stealth/ox-alpha":{"draws":36,"losses":20,"wins":418},"stealth/space-bunny-alpha":{"draws":6,"losses":0,"wins":108},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":96},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":0,"wins":67},"tencent/hy4-preview":{"draws":9,"losses":5,"wins":124},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":178},"thinkingmachines/inkling-small":{"draws":9,"losses":0,"wins":135},"unbiased/pareto-26.10":{"draws":5,"losses":8,"wins":11},"unbiased/pareto-26.10-preview":{"draws":6,"losses":20,"wins":22},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":121},"x-ai/grok-4.6":{"draws":11,"losses":14,"wins":119},"x-ai/grok-4.7":{"draws":12,"losses":22,"wins":92},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":45},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":207},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":74},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":81},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":80},"z-ai/glm-5.2":{"draws":19,"losses":11,"wins":258},"z-ai/glm-5.3":{"draws":18,"losses":11,"wins":109},"z-ai/glm-5.3-flash":{"draws":11,"losses":8,"wins":125},"z-ai/glm-5.3-flashx":{"draws":14,"losses":9,"wins":121}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":39,"wins":54},"claude-fable-5":{"draws":30,"losses":86,"wins":28},"claude-fable-5-1":{"draws":10,"losses":146,"wins":6},"claude-haiku-5-5":{"draws":36,"losses":63,"wins":39},"claude-opus-4-5":{"draws":79,"losses":80,"wins":75},"claude-opus-4-8":{"draws":35,"losses":61,"wins":36},"claude-opus-5":{"draws":45,"losses":179,"wins":22},"claude-opus-5-5":{"draws":14,"losses":140,"wins":2},"claude-sonnet-5":{"draws":38,"losses":50,"wins":56},"claude-sonnet-5-5":{"draws":32,"losses":68,"wins":44},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":66,"losses":45,"wins":105},"deepseek/deepseek-v4-pro":{"draws":34,"losses":42,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":47,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":60,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":46,"wins":17},"elorian/glimpse":{"draws":8,"losses":18,"wins":16},"fireworks/ember-1":{"draws":39,"losses":64,"wins":41},"gemini-3.1-pro-preview":{"draws":36,"losses":62,"wins":46},"gemini-4-argon":{"draws":4,"losses":70,"wins":6},"google/gemini-3.1-flash-lite":{"draws":26,"losses":11,"wins":59},"google/gemini-3.5-flash":{"draws":50,"losses":70,"wins":60},"google/gemini-3.5-flash-lite":{"draws":79,"losses":61,"wins":112},"google/gemini-3.6-flash":{"draws":81,"losses":126,"wins":69},"google/gemini-3.8-flash":{"draws":41,"losses":69,"wins":34},"google/gemma-4-31b-it":{"draws":28,"losses":18,"wins":38},"gpt-4.1":{"draws":10,"losses":19,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":7},"gpt-5":{"draws":39,"losses":42,"wins":45},"gpt-5.4":{"draws":43,"losses":61,"wins":34},"gpt-5.4-mini":{"draws":43,"losses":13,"wins":40},"gpt-5.4-nano":{"draws":30,"losses":42,"wins":72},"gpt-5.5":{"draws":52,"losses":53,"wins":27},"gpt-5.6-luna":{"draws":48,"losses":38,"wins":58},"gpt-5.6-sol":{"draws":28,"losses":92,"wins":24},"gpt-5.6-terra":{"draws":40,"losses":41,"wins":57},"gpt-6-astra":{"draws":15,"losses":120,"wins":9},"gpt-6-luna":{"draws":24,"losses":36,"wins":36},"gpt-6-sol":{"draws":24,"losses":101,"wins":19},"gpt-6.1-sol":{"draws":13,"losses":125,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":41,"losses":9,"wins":52},"inception/mercury-3":{"draws":12,"losses":13,"wins":19},"inclusionai/ling-3.0-flash":{"draws":35,"losses":13,"wins":54},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":38,"losses":34,"wins":84},"meta/muse-glimmer-30b":{"draws":45,"losses":18,"wins":63},"meta/muse-spark-1.2":{"draws":37,"losses":63,"wins":38},"meta/muse-spark-1.3":{"draws":25,"losses":83,"wins":36},"meta/muse-spark-open":{"draws":15,"losses":26,"wins":21},"meta/muse-wonder":{"draws":34,"losses":77,"wins":33},"minimax/minimax-m3":{"draws":22,"losses":14,"wins":42},"minimax/minimax-m3.1-flash":{"draws":15,"losses":25,"wins":32},"mistralai/mistral-large-4-0":{"draws":27,"losses":31,"wins":32},"mistralai/mistral-medium-3-5":{"draws":30,"losses":7,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":10,"wins":14},"moonshotai/kimi-k3":{"draws":45,"losses":51,"wins":42},"nex-agi/nex-n2-pro":{"draws":15,"losses":11,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":25,"wins":59},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":5,"wins":21},"o3":{"draws":34,"losses":64,"wins":100},"openai/gpt-oss-120b":{"draws":41,"losses":27,"wins":58},"poolside/laguna-s-2.1":{"draws":45,"losses":34,"wins":59},"qwen/qwen3.7-max":{"draws":22,"losses":27,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":12,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":59,"wins":48},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":41},"qwen/qwen3.8-flash":{"draws":28,"losses":33,"wins":35},"qwen/qwen3.8-max":{"draws":37,"losses":57,"wins":50},"qwen/qwen3.8-max-0902":{"draws":41,"losses":56,"wins":47},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":25,"wins":20},"stealth/ox-alpha":{"draws":112,"losses":208,"wins":154},"stealth/space-bunny-alpha":{"draws":41,"losses":23,"wins":50},"stepfun/step-3.7-flash":{"draws":21,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":26,"losses":20,"wins":32},"tencent/hy4-preview":{"draws":39,"losses":64,"wins":35},"thinkingmachines/inkling":{"draws":56,"losses":40,"wins":96},"thinkingmachines/inkling-small":{"draws":40,"losses":32,"wins":72},"unbiased/pareto-26.10":{"draws":2,"losses":22,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":10,"wins":25},"x-ai/grok-4.5":{"draws":34,"losses":65,"wins":45},"x-ai/grok-4.6":{"draws":39,"losses":81,"wins":24},"x-ai/grok-4.7":{"draws":10,"losses":96,"wins":20},"x-ai/grok-build-0.1":{"draws":20,"losses":4,"wins":24},"xiaomi/mimo-v2.5":{"draws":79,"losses":29,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":18,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":50,"wins":27},"z-ai/glm-5.2":{"draws":102,"losses":73,"wins":113},"z-ai/glm-5.3":{"draws":26,"losses":85,"wins":27},"z-ai/glm-5.3-flash":{"draws":38,"losses":71,"wins":35},"z-ai/glm-5.3-flashx":{"draws":30,"losses":72,"wins":42}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":102},"claude-fable-5":{"draws":20,"losses":41,"wins":83},"claude-fable-5-1":{"draws":15,"losses":110,"wins":37},"claude-haiku-5-5":{"draws":27,"losses":27,"wins":84},"claude-opus-4-5":{"draws":36,"losses":25,"wins":173},"claude-opus-4-8":{"draws":20,"losses":33,"wins":79},"claude-opus-5":{"draws":33,"losses":120,"wins":93},"claude-opus-5-5":{"draws":15,"losses":102,"wins":39},"claude-sonnet-5":{"draws":24,"losses":19,"wins":101},"claude-sonnet-5-5":{"draws":14,"losses":48,"wins":82},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":49},"deepseek/deepseek-v4-flash":{"draws":32,"losses":16,"wins":168},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":20,"wins":99},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":32,"wins":86},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":19,"wins":45},"elorian/glimpse":{"draws":6,"losses":11,"wins":23},"fireworks/ember-1":{"draws":21,"losses":23,"wins":100},"gemini-3.1-pro-preview":{"draws":18,"losses":27,"wins":99},"gemini-4-argon":{"draws":7,"losses":34,"wins":25},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":82},"google/gemini-3.5-flash":{"draws":28,"losses":26,"wins":126},"google/gemini-3.5-flash-lite":{"draws":39,"losses":23,"wins":190},"google/gemini-3.6-flash":{"draws":35,"losses":60,"wins":181},"google/gemini-3.8-flash":{"draws":22,"losses":31,"wins":91},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":73},"gpt-4.1":{"draws":7,"losses":7,"wins":34},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":15,"losses":16,"wins":95},"gpt-5.4":{"draws":15,"losses":22,"wins":101},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":72},"gpt-5.4-nano":{"draws":20,"losses":12,"wins":112},"gpt-5.5":{"draws":20,"losses":29,"wins":83},"gpt-5.6-luna":{"draws":24,"losses":14,"wins":106},"gpt-5.6-sol":{"draws":13,"losses":46,"wins":85},"gpt-5.6-terra":{"draws":24,"losses":16,"wins":98},"gpt-6-astra":{"draws":15,"losses":103,"wins":26},"gpt-6-luna":{"draws":24,"losses":19,"wins":101},"gpt-6-sol":{"draws":14,"losses":41,"wins":41},"gpt-6.1-sol":{"draws":17,"losses":91,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":82},"inception/mercury-3":{"draws":9,"losses":6,"wins":41},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":79},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":132},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":97},"meta/muse-spark-1.2":{"draws":18,"losses":24,"wins":96},"meta/muse-spark-1.3":{"draws":23,"losses":22,"wins":99},"meta/muse-spark-open":{"draws":6,"losses":7,"wins":55},"meta/muse-wonder":{"draws":18,"losses":45,"wins":81},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":62},"minimax/minimax-m3.1-flash":{"draws":13,"losses":4,"wins":55},"mistralai/mistral-large-4-0":{"draws":15,"losses":14,"wins":61},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":73},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":2,"wins":27},"moonshotai/kimi-k3":{"draws":15,"losses":26,"wins":97},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":61},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":106},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":16},"o3":{"draws":10,"losses":17,"wins":171},"openai/gpt-oss-120b":{"draws":19,"losses":6,"wins":101},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":105},"qwen/qwen3.7-max":{"draws":16,"losses":10,"wins":58},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":32,"wins":93},"qwen/qwen3.8-27b":{"draws":17,"losses":14,"wins":71},"qwen/qwen3.8-flash":{"draws":9,"losses":18,"wins":69},"qwen/qwen3.8-max":{"draws":17,"losses":28,"wins":99},"qwen/qwen3.8-max-0902":{"draws":16,"losses":28,"wins":100},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":9,"wins":49},"stealth/ox-alpha":{"draws":61,"losses":73,"wins":340},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":87},"stepfun/step-3.7-flash":{"draws":13,"losses":4,"wins":85},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":15,"losses":5,"wins":58},"tencent/hy4-preview":{"draws":19,"losses":26,"wins":93},"thinkingmachines/inkling":{"draws":25,"losses":13,"wins":154},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":118},"unbiased/pareto-26.10":{"draws":3,"losses":34,"wins":3},"unbiased/pareto-26.10-preview":{"draws":5,"losses":34,"wins":9},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":32},"x-ai/grok-4.5":{"draws":19,"losses":32,"wins":93},"x-ai/grok-4.6":{"draws":21,"losses":31,"wins":92},"x-ai/grok-4.7":{"draws":13,"losses":60,"wins":53},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":38},"xiaomi/mimo-v2.5":{"draws":35,"losses":17,"wins":170},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":64},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":18,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":24,"wins":54},"z-ai/glm-5.2":{"draws":43,"losses":34,"wins":211},"z-ai/glm-5.3":{"draws":21,"losses":47,"wins":70},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":90},"z-ai/glm-5.3-flashx":{"draws":20,"losses":37,"wins":87}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":114},"claude-fable-5":{"draws":11,"losses":32,"wins":101},"claude-fable-5-1":{"draws":13,"losses":74,"wins":75},"claude-haiku-5-5":{"draws":15,"losses":10,"wins":113},"claude-opus-4-5":{"draws":20,"losses":16,"wins":198},"claude-opus-4-8":{"draws":7,"losses":15,"wins":110},"claude-opus-5":{"draws":32,"losses":75,"wins":139},"claude-opus-5-5":{"draws":18,"losses":75,"wins":63},"claude-sonnet-5":{"draws":6,"losses":9,"wins":129},"claude-sonnet-5-5":{"draws":4,"losses":36,"wins":104},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":197},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":116},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":3,"wins":121},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":15,"wins":115},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":17,"wins":54},"elorian/glimpse":{"draws":3,"losses":4,"wins":27},"fireworks/ember-1":{"draws":9,"losses":17,"wins":118},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":126},"gemini-4-argon":{"draws":5,"losses":24,"wins":39},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":92},"google/gemini-3.5-flash":{"draws":11,"losses":18,"wins":151},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":235},"google/gemini-3.6-flash":{"draws":18,"losses":28,"wins":230},"google/gemini-3.8-flash":{"draws":20,"losses":17,"wins":107},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":80},"gpt-4.1":{"draws":4,"losses":1,"wins":43},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":17},"gpt-5":{"draws":6,"losses":5,"wins":115},"gpt-5.4":{"draws":9,"losses":20,"wins":109},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":87},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":132},"gpt-5.5":{"draws":8,"losses":21,"wins":103},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":125},"gpt-5.6-sol":{"draws":13,"losses":22,"wins":109},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":122},"gpt-6-astra":{"draws":18,"losses":76,"wins":50},"gpt-6-luna":{"draws":13,"losses":6,"wins":125},"gpt-6-sol":{"draws":17,"losses":36,"wins":91},"gpt-6.1-sol":{"draws":6,"losses":45,"wins":45},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":93},"inception/mercury-3":{"draws":2,"losses":1,"wins":31},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":98},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":139},"meta/muse-glimmer-30b":{"draws":8,"losses":1,"wins":117},"meta/muse-spark-1.2":{"draws":9,"losses":18,"wins":111},"meta/muse-spark-1.3":{"draws":13,"losses":14,"wins":117},"meta/muse-spark-open":{"draws":5,"losses":8,"wins":53},"meta/muse-wonder":{"draws":19,"losses":29,"wins":96},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":70},"minimax/minimax-m3.1-flash":{"draws":8,"losses":1,"wins":55},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":70},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":31},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":114},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":68},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":112},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":2,"wins":27},"o3":{"draws":3,"losses":9,"wins":186},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":118},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":128},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":75},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":66},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":113},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":91},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":82},"qwen/qwen3.8-max":{"draws":11,"losses":9,"wins":124},"qwen/qwen3.8-max-0902":{"draws":12,"losses":11,"wins":121},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":74},"stealth/ox-alpha":{"draws":43,"losses":30,"wins":401},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":100},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":99},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":68},"tencent/hy4-preview":{"draws":7,"losses":13,"wins":118},"thinkingmachines/inkling":{"draws":13,"losses":6,"wins":173},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":138},"unbiased/pareto-26.10":{"draws":6,"losses":16,"wins":10},"unbiased/pareto-26.10-preview":{"draws":2,"losses":28,"wins":18},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":35},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":118},"x-ai/grok-4.6":{"draws":16,"losses":14,"wins":114},"x-ai/grok-4.7":{"draws":6,"losses":41,"wins":79},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":48},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":195},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":70},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":79},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":20,"wins":62},"z-ai/glm-5.2":{"draws":30,"losses":10,"wins":248},"z-ai/glm-5.3":{"draws":21,"losses":25,"wins":92},"z-ai/glm-5.3-flash":{"draws":13,"losses":16,"wins":115},"z-ai/glm-5.3-flashx":{"draws":19,"losses":18,"wins":107}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"elorian/glimpse":{"draws":2,"losses":0,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":1,"losses":3,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inception/mercury-3":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":1},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":2},"meta/muse-spark-open":{"draws":1,"losses":1,"wins":0},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":9,"losses":8,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":1,"losses":1,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":0},"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":12,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":32,"wins":24},"claude-fable-5":{"draws":25,"losses":72,"wins":5},"claude-fable-5-1":{"draws":9,"losses":105,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":68,"wins":4},"claude-opus-4-5":{"draws":72,"losses":88,"wins":8},"claude-opus-4-8":{"draws":32,"losses":56,"wins":10},"claude-opus-5":{"draws":31,"losses":129,"wins":6},"claude-opus-5-5":{"draws":8,"losses":102,"wins":0},"claude-sonnet-5":{"draws":38,"losses":54,"wins":10},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":13,"wins":15},"deepseek/deepseek-v4-flash":{"draws":64,"losses":60,"wins":28},"deepseek/deepseek-v4-pro":{"draws":37,"losses":45,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":46,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":48,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":28,"wins":3},"elorian/glimpse":{"draws":6,"losses":14,"wins":4},"fireworks/ember-1":{"draws":44,"losses":52,"wins":6},"gemini-3.1-pro-preview":{"draws":40,"losses":40,"wins":22},"gemini-4-argon":{"draws":3,"losses":45,"wins":0},"google/gemini-3.1-flash-lite":{"draws":27,"losses":17,"wins":28},"google/gemini-3.5-flash":{"draws":47,"losses":65,"wins":16},"google/gemini-3.5-flash-lite":{"draws":74,"losses":69,"wins":37},"google/gemini-3.6-flash":{"draws":68,"losses":114,"wins":12},"google/gemini-3.8-flash":{"draws":31,"losses":67,"wins":4},"google/gemma-4-31b-it":{"draws":30,"losses":18,"wins":16},"gpt-4.1":{"draws":15,"losses":11,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":5,"wins":3},"gpt-5":{"draws":34,"losses":41,"wins":9},"gpt-5.4":{"draws":41,"losses":52,"wins":3},"gpt-5.4-mini":{"draws":31,"losses":23,"wins":14},"gpt-5.4-nano":{"draws":32,"losses":56,"wins":14},"gpt-5.5":{"draws":40,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":51,"losses":34,"wins":17},"gpt-5.6-sol":{"draws":19,"losses":83,"wins":0},"gpt-5.6-terra":{"draws":42,"losses":49,"wins":7},"gpt-6-astra":{"draws":7,"losses":95,"wins":0},"gpt-6-luna":{"draws":41,"losses":52,"wins":9},"gpt-6-sol":{"draws":16,"losses":82,"wins":4},"gpt-6.1-sol":{"draws":9,"losses":93,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":10,"wins":10},"inception/mercury-3":{"draws":18,"losses":12,"wins":4},"inclusionai/ling-3.0-flash":{"draws":35,"losses":19,"wins":18},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":42,"wins":26},"meta/muse-glimmer-30b":{"draws":44,"losses":23,"wins":17},"meta/muse-spark-1.2":{"draws":34,"losses":51,"wins":11},"meta/muse-spark-1.3":{"draws":29,"losses":65,"wins":8},"meta/muse-spark-open":{"draws":12,"losses":30,"wins":4},"meta/muse-wonder":{"draws":28,"losses":70,"wins":4},"minimax/minimax-m3":{"draws":26,"losses":19,"wins":9},"minimax/minimax-m3.1-flash":{"draws":21,"losses":29,"wins":8},"mistralai/mistral-large-4-0":{"draws":26,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":29,"losses":16,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":14,"wins":2},"moonshotai/kimi-k3":{"draws":44,"losses":44,"wins":8},"nex-agi/nex-n2-pro":{"draws":20,"losses":16,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":26,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":21,"wins":4},"o3":{"draws":31,"losses":88,"wins":17},"openai/gpt-oss-120b":{"draws":38,"losses":29,"wins":21},"poolside/laguna-s-2.1":{"draws":40,"losses":28,"wins":22},"qwen/qwen3.7-max":{"draws":25,"losses":23,"wins":12},"qwen/qwen3.7-plus":{"draws":22,"losses":22,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":56,"wins":6},"qwen/qwen3.8-27b":{"draws":22,"losses":43,"wins":7},"qwen/qwen3.8-flash":{"draws":31,"losses":31,"wins":6},"qwen/qwen3.8-max":{"draws":43,"losses":51,"wins":8},"qwen/qwen3.8-max-0902":{"draws":44,"losses":48,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":33,"wins":1},"stealth/ox-alpha":{"draws":102,"losses":176,"wins":32},"stealth/space-bunny-alpha":{"draws":37,"losses":35,"wins":10},"stepfun/step-3.7-flash":{"draws":20,"losses":38,"wins":10},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":39,"losses":49,"wins":8},"thinkingmachines/inkling":{"draws":52,"losses":44,"wins":32},"thinkingmachines/inkling-small":{"draws":49,"losses":31,"wins":22},"unbiased/pareto-26.10":{"draws":1,"losses":19,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":11},"x-ai/grok-4.5":{"draws":34,"losses":64,"wins":4},"x-ai/grok-4.6":{"draws":31,"losses":64,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":72,"wins":3},"x-ai/grok-build-0.1":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":78,"losses":67,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":25,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":41,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":48,"wins":1},"z-ai/glm-5.2":{"draws":87,"losses":98,"wins":19},"z-ai/glm-5.3":{"draws":28,"losses":69,"wins":3},"z-ai/glm-5.3-flash":{"draws":24,"losses":65,"wins":13},"z-ai/glm-5.3-flashx":{"draws":29,"losses":68,"wins":5}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":9,"wins":20},"claude-fable-5":{"draws":18,"losses":26,"wins":4},"claude-fable-5-1":{"draws":3,"losses":59,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":21,"wins":12},"claude-opus-4-5":{"draws":35,"losses":19,"wins":28},"claude-opus-4-8":{"draws":12,"losses":18,"wins":6},"claude-opus-5":{"draws":11,"losses":65,"wins":8},"claude-opus-5-5":{"draws":1,"losses":50,"wins":1},"claude-sonnet-5":{"draws":23,"losses":9,"wins":18},"claude-sonnet-5-5":{"draws":6,"losses":28,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":28,"losses":16,"wins":34},"deepseek/deepseek-v4-pro":{"draws":17,"losses":16,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":17,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":27,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":22,"losses":55,"wins":15},"elorian/glimpse":{"draws":6,"losses":23,"wins":19},"fireworks/ember-1":{"draws":18,"losses":14,"wins":20},"gemini-3.1-pro-preview":{"draws":20,"losses":12,"wins":28},"gemini-4-argon":{"draws":11,"losses":75,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":17,"losses":20,"wins":31},"google/gemini-3.5-flash-lite":{"draws":26,"losses":8,"wins":38},"google/gemini-3.6-flash":{"draws":26,"losses":46,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":12},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":9},"gpt-4.1":{"draws":4,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":17,"wins":18},"gpt-5.4":{"draws":7,"losses":10,"wins":15},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":15,"losses":13,"wins":22},"gpt-5.5":{"draws":17,"losses":14,"wins":9},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":20},"gpt-5.6-sol":{"draws":10,"losses":29,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":21,"wins":18},"gpt-6-astra":{"draws":4,"losses":42,"wins":0},"gpt-6-luna":{"draws":12,"losses":19,"wins":13},"gpt-6-sol":{"draws":9,"losses":41,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":12},"inception/mercury-3":{"draws":10,"losses":13,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":17},"meituan/longcat-2.0":{"draws":17,"losses":12,"wins":27},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":18,"losses":27,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":26,"wins":8},"meta/muse-spark-open":{"draws":16,"losses":48,"wins":22},"meta/muse-wonder":{"draws":16,"losses":23,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":4,"wins":17},"minimax/minimax-m3.1-flash":{"draws":16,"losses":20,"wins":34},"mistralai/mistral-large-4-0":{"draws":14,"losses":11,"wins":11},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":16},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":9,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":10,"wins":19},"o3":{"draws":8,"losses":15,"wins":31},"openai/gpt-oss-120b":{"draws":16,"losses":9,"wins":17},"poolside/laguna-s-2.1":{"draws":22,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.7-plus":{"draws":12,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":14,"wins":13},"qwen/qwen3.8-27b":{"draws":15,"losses":15,"wins":14},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-max-0902":{"draws":23,"losses":20,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":31,"wins":29},"stealth/ox-alpha":{"draws":42,"losses":68,"wins":40},"stealth/space-bunny-alpha":{"draws":5,"losses":9,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":13,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":12,"losses":21,"wins":13},"thinkingmachines/inkling":{"draws":13,"losses":13,"wins":22},"thinkingmachines/inkling-small":{"draws":16,"losses":3,"wins":21},"unbiased/pareto-26.10":{"draws":2,"losses":27,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":22,"losses":25,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":23,"wins":8},"x-ai/grok-4.7":{"draws":6,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":27,"losses":6,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":10,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":6},"z-ai/glm-5.2":{"draws":30,"losses":24,"wins":32},"z-ai/glm-5.3":{"draws":17,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":19,"losses":21,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":18,"wins":10}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":39,"wins":16},"claude-fable-5":{"draws":18,"losses":80,"wins":4},"claude-fable-5-1":{"draws":7,"losses":107,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":61,"wins":5},"claude-opus-4-5":{"draws":59,"losses":88,"wins":19},"claude-opus-4-8":{"draws":29,"losses":65,"wins":0},"claude-opus-5":{"draws":26,"losses":132,"wins":8},"claude-opus-5-5":{"draws":7,"losses":107,"wins":0},"claude-sonnet-5":{"draws":36,"losses":58,"wins":8},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":7},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":13},"deepseek/deepseek-v4-flash":{"draws":63,"losses":53,"wins":42},"deepseek/deepseek-v4-pro":{"draws":34,"losses":44,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":44,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":44,"losses":49,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":44,"wins":3},"elorian/glimpse":{"draws":7,"losses":14,"wins":7},"fireworks/ember-1":{"draws":44,"losses":54,"wins":4},"gemini-3.1-pro-preview":{"draws":39,"losses":53,"wins":10},"gemini-4-argon":{"draws":6,"losses":44,"wins":2},"google/gemini-3.1-flash-lite":{"draws":25,"losses":19,"wins":22},"google/gemini-3.5-flash":{"draws":39,"losses":77,"wins":12},"google/gemini-3.5-flash-lite":{"draws":63,"losses":78,"wins":35},"google/gemini-3.6-flash":{"draws":68,"losses":108,"wins":18},"google/gemini-3.8-flash":{"draws":30,"losses":70,"wins":2},"google/gemma-4-31b-it":{"draws":32,"losses":13,"wins":13},"gpt-4.1":{"draws":13,"losses":20,"wins":1},"gpt-4.1-nano":{"draws":6,"losses":6,"wins":2},"gpt-5":{"draws":31,"losses":35,"wins":22},"gpt-5.4":{"draws":27,"losses":57,"wins":14},"gpt-5.4-mini":{"draws":31,"losses":25,"wins":12},"gpt-5.4-nano":{"draws":30,"losses":48,"wins":26},"gpt-5.5":{"draws":41,"losses":44,"wins":7},"gpt-5.6-luna":{"draws":48,"losses":35,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":86,"wins":4},"gpt-5.6-terra":{"draws":35,"losses":60,"wins":7},"gpt-6-astra":{"draws":5,"losses":96,"wins":1},"gpt-6-luna":{"draws":35,"losses":54,"wins":13},"gpt-6-sol":{"draws":15,"losses":79,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":98,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":35,"losses":18,"wins":19},"inception/mercury-3":{"draws":8,"losses":17,"wins":7},"inclusionai/ling-3.0-flash":{"draws":22,"losses":15,"wins":15},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":49,"losses":39,"wins":20},"meta/muse-glimmer-30b":{"draws":50,"losses":22,"wins":14},"meta/muse-spark-1.2":{"draws":27,"losses":58,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":76,"wins":10},"meta/muse-spark-open":{"draws":10,"losses":34,"wins":4},"meta/muse-wonder":{"draws":18,"losses":79,"wins":5},"minimax/minimax-m3":{"draws":21,"losses":23,"wins":10},"minimax/minimax-m3.1-flash":{"draws":11,"losses":33,"wins":4},"mistralai/mistral-large-4-0":{"draws":28,"losses":25,"wins":9},"mistralai/mistral-medium-3-5":{"draws":25,"losses":18,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":31,"losses":53,"wins":12},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":26,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":9,"wins":5},"o3":{"draws":29,"losses":90,"wins":21},"openai/gpt-oss-120b":{"draws":38,"losses":40,"wins":8},"poolside/laguna-s-2.1":{"draws":45,"losses":36,"wins":13},"qwen/qwen3.7-max":{"draws":29,"losses":24,"wins":7},"qwen/qwen3.7-plus":{"draws":20,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":57,"wins":4},"qwen/qwen3.8-27b":{"draws":15,"losses":46,"wins":13},"qwen/qwen3.8-flash":{"draws":27,"losses":36,"wins":5},"qwen/qwen3.8-max":{"draws":41,"losses":47,"wins":14},"qwen/qwen3.8-max-0902":{"draws":39,"losses":54,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":23,"wins":1},"stealth/ox-alpha":{"draws":94,"losses":208,"wins":26},"stealth/space-bunny-alpha":{"draws":34,"losses":31,"wins":11},"stepfun/step-3.7-flash":{"draws":26,"losses":30,"wins":20},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":25,"wins":7},"tencent/hy4-preview":{"draws":37,"losses":56,"wins":5},"thinkingmachines/inkling":{"draws":51,"losses":52,"wins":27},"thinkingmachines/inkling-small":{"draws":50,"losses":33,"wins":19},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":10,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":24,"losses":72,"wins":6},"x-ai/grok-4.6":{"draws":35,"losses":62,"wins":5},"x-ai/grok-4.7":{"draws":9,"losses":74,"wins":5},"x-ai/grok-build-0.1":{"draws":13,"losses":18,"wins":3},"xiaomi/mimo-v2.5":{"draws":71,"losses":55,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":27,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":41,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":49,"wins":5},"z-ai/glm-5.2":{"draws":101,"losses":78,"wins":25},"z-ai/glm-5.3":{"draws":22,"losses":71,"wins":3},"z-ai/glm-5.3-flash":{"draws":32,"losses":58,"wins":12},"z-ai/glm-5.3-flashx":{"draws":34,"losses":60,"wins":8}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":4,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":2,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":0},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":1},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":62,"wins":41},"claude-fable-5":{"draws":21,"losses":115,"wins":20},"claude-fable-5-1":{"draws":5,"losses":164,"wins":6},"claude-haiku-5-5":{"draws":33,"losses":96,"wins":21},"claude-opus-4-5":{"draws":67,"losses":151,"wins":36},"claude-opus-4-8":{"draws":33,"losses":90,"wins":21},"claude-opus-5":{"draws":26,"losses":208,"wins":22},"claude-opus-5-5":{"draws":10,"losses":156,"wins":6},"claude-sonnet-5":{"draws":43,"losses":83,"wins":30},"claude-sonnet-5-5":{"draws":20,"losses":105,"wins":31},"cohere/north-mini-code":{"draws":14,"losses":15,"wins":39},"deepseek/deepseek-v4-flash":{"draws":66,"losses":92,"wins":76},"deepseek/deepseek-v4-pro":{"draws":31,"losses":85,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":69,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":85,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":58,"wins":13},"elorian/glimpse":{"draws":8,"losses":16,"wins":12},"fireworks/ember-1":{"draws":45,"losses":89,"wins":22},"gemini-3.1-pro-preview":{"draws":37,"losses":74,"wins":45},"gemini-4-argon":{"draws":4,"losses":64,"wins":4},"google/gemini-3.1-flash-lite":{"draws":23,"losses":27,"wins":62},"google/gemini-3.5-flash":{"draws":37,"losses":122,"wins":39},"google/gemini-3.5-flash-lite":{"draws":73,"losses":121,"wins":84},"google/gemini-3.6-flash":{"draws":66,"losses":188,"wins":46},"google/gemini-3.8-flash":{"draws":28,"losses":109,"wins":19},"google/gemma-4-31b-it":{"draws":33,"losses":26,"wins":35},"gpt-4.1":{"draws":18,"losses":25,"wins":9},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":35,"losses":71,"wins":32},"gpt-5.4":{"draws":34,"losses":95,"wins":23},"gpt-5.4-mini":{"draws":40,"losses":36,"wins":28},"gpt-5.4-nano":{"draws":27,"losses":83,"wins":50},"gpt-5.5":{"draws":46,"losses":72,"wins":26},"gpt-5.6-luna":{"draws":48,"losses":61,"wins":47},"gpt-5.6-sol":{"draws":20,"losses":122,"wins":14},"gpt-5.6-terra":{"draws":43,"losses":72,"wins":33},"gpt-6-astra":{"draws":8,"losses":146,"wins":2},"gpt-6-luna":{"draws":38,"losses":84,"wins":34},"gpt-6-sol":{"draws":11,"losses":132,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":139,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":44,"losses":26,"wins":42},"inception/mercury-3":{"draws":17,"losses":27,"wins":12},"inclusionai/ling-3.0-flash":{"draws":49,"losses":20,"wins":39},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":42,"losses":43,"wins":43},"meta/muse-glimmer-30b":{"draws":51,"losses":44,"wins":41},"meta/muse-spark-1.2":{"draws":28,"losses":93,"wins":27},"meta/muse-spark-1.3":{"draws":29,"losses":102,"wins":25},"meta/muse-spark-open":{"draws":15,"losses":48,"wins":7},"meta/muse-wonder":{"draws":31,"losses":105,"wins":20},"minimax/minimax-m3":{"draws":19,"losses":30,"wins":35},"minimax/minimax-m3.1-flash":{"draws":18,"losses":35,"wins":25},"mistralai/mistral-large-4-0":{"draws":34,"losses":46,"wins":16},"mistralai/mistral-medium-3-5":{"draws":36,"losses":22,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":24,"wins":7},"moonshotai/kimi-k3":{"draws":43,"losses":79,"wins":26},"nex-agi/nex-n2-pro":{"draws":18,"losses":26,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":43,"wins":45},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":17,"wins":7},"o3":{"draws":35,"losses":137,"wins":60},"openai/gpt-oss-120b":{"draws":43,"losses":38,"wins":57},"poolside/laguna-s-2.1":{"draws":51,"losses":53,"wins":46},"qwen/qwen3.7-max":{"draws":30,"losses":44,"wins":18},"qwen/qwen3.7-plus":{"draws":17,"losses":29,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":91,"wins":23},"qwen/qwen3.8-27b":{"draws":22,"losses":68,"wins":18},"qwen/qwen3.8-flash":{"draws":34,"losses":47,"wins":23},"qwen/qwen3.8-max":{"draws":48,"losses":80,"wins":28},"qwen/qwen3.8-max-0902":{"draws":30,"losses":102,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":37,"wins":17},"stealth/ox-alpha":{"draws":114,"losses":317,"wins":79},"stealth/space-bunny-alpha":{"draws":40,"losses":57,"wins":29},"stepfun/step-3.7-flash":{"draws":20,"losses":49,"wins":45},"stepfun/step-5-preview":{"draws":7,"losses":8,"wins":1},"tencent/hy3-preview":{"draws":25,"losses":32,"wins":25},"tencent/hy4-preview":{"draws":39,"losses":91,"wins":22},"thinkingmachines/inkling":{"draws":54,"losses":77,"wins":75},"thinkingmachines/inkling-small":{"draws":53,"losses":47,"wins":56},"unbiased/pareto-26.10":{"draws":1,"losses":39,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":49,"wins":2},"upstage/solar-mini4":{"draws":9,"losses":16,"wins":17},"x-ai/grok-4.5":{"draws":30,"losses":102,"wins":24},"x-ai/grok-4.6":{"draws":40,"losses":95,"wins":21},"x-ai/grok-4.7":{"draws":8,"losses":120,"wins":8},"x-ai/grok-build-0.1":{"draws":19,"losses":17,"wins":16},"xiaomi/mimo-v2.5":{"draws":77,"losses":79,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":41,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":24,"losses":56,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":74,"wins":11},"z-ai/glm-5.2":{"draws":93,"losses":146,"wins":73},"z-ai/glm-5.3":{"draws":26,"losses":115,"wins":11},"z-ai/glm-5.3-flash":{"draws":27,"losses":97,"wins":32},"z-ai/glm-5.3-flashx":{"draws":34,"losses":102,"wins":20}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":46,"losses":37,"wins":33},"claude-fable-5":{"draws":27,"losses":92,"wins":7},"claude-fable-5-1":{"draws":9,"losses":133,"wins":1},"claude-haiku-5-5":{"draws":37,"losses":68,"wins":15},"claude-opus-4-5":{"draws":74,"losses":101,"wins":29},"claude-opus-4-8":{"draws":32,"losses":66,"wins":16},"claude-opus-5":{"draws":15,"losses":192,"wins":23},"claude-opus-5-5":{"draws":7,"losses":131,"wins":0},"claude-sonnet-5":{"draws":43,"losses":64,"wins":19},"claude-sonnet-5-5":{"draws":21,"losses":84,"wins":21},"cohere/north-mini-code":{"draws":18,"losses":15,"wins":17},"deepseek/deepseek-v4-flash":{"draws":82,"losses":58,"wins":46},"deepseek/deepseek-v4-pro":{"draws":37,"losses":56,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":58,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":60,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":46,"wins":8},"elorian/glimpse":{"draws":8,"losses":13,"wins":13},"fireworks/ember-1":{"draws":44,"losses":67,"wins":15},"gemini-3.1-pro-preview":{"draws":49,"losses":61,"wins":16},"gemini-4-argon":{"draws":3,"losses":58,"wins":1},"google/gemini-3.1-flash-lite":{"draws":33,"losses":19,"wins":30},"google/gemini-3.5-flash":{"draws":52,"losses":81,"wins":25},"google/gemini-3.5-flash-lite":{"draws":89,"losses":79,"wins":52},"google/gemini-3.6-flash":{"draws":77,"losses":130,"wins":35},"google/gemini-3.8-flash":{"draws":33,"losses":78,"wins":15},"google/gemma-4-31b-it":{"draws":38,"losses":17,"wins":17},"gpt-4.1":{"draws":19,"losses":13,"wins":10},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":2},"gpt-5":{"draws":40,"losses":50,"wins":24},"gpt-5.4":{"draws":31,"losses":74,"wins":17},"gpt-5.4-mini":{"draws":43,"losses":30,"wins":11},"gpt-5.4-nano":{"draws":31,"losses":49,"wins":42},"gpt-5.5":{"draws":48,"losses":56,"wins":16},"gpt-5.6-luna":{"draws":52,"losses":42,"wins":32},"gpt-5.6-sol":{"draws":19,"losses":99,"wins":8},"gpt-5.6-terra":{"draws":47,"losses":57,"wins":16},"gpt-6-astra":{"draws":6,"losses":120,"wins":0},"gpt-6-luna":{"draws":45,"losses":63,"wins":18},"gpt-6-sol":{"draws":19,"losses":97,"wins":10},"gpt-6.1-sol":{"draws":8,"losses":117,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":44,"losses":17,"wins":23},"inception/mercury-3":{"draws":9,"losses":19,"wins":6},"inclusionai/ling-3.0-flash":{"draws":50,"losses":14,"wins":22},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":51,"losses":41,"wins":44},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":18},"meta/muse-spark-1.2":{"draws":32,"losses":73,"wins":19},"meta/muse-spark-1.3":{"draws":36,"losses":74,"wins":16},"meta/muse-spark-open":{"draws":19,"losses":35,"wins":12},"meta/muse-wonder":{"draws":26,"losses":85,"wins":15},"minimax/minimax-m3":{"draws":25,"losses":25,"wins":20},"minimax/minimax-m3.1-flash":{"draws":20,"losses":27,"wins":17},"mistralai/mistral-large-4-0":{"draws":27,"losses":36,"wins":19},"mistralai/mistral-medium-3-5":{"draws":35,"losses":10,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":17,"wins":10},"moonshotai/kimi-k3":{"draws":38,"losses":67,"wins":19},"nex-agi/nex-n2-pro":{"draws":25,"losses":14,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":55,"losses":27,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":19,"wins":4},"o3":{"draws":34,"losses":103,"wins":35},"openai/gpt-oss-120b":{"draws":47,"losses":38,"wins":27},"poolside/laguna-s-2.1":{"draws":54,"losses":41,"wins":29},"qwen/qwen3.7-max":{"draws":29,"losses":27,"wins":16},"qwen/qwen3.7-plus":{"draws":25,"losses":15,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":64,"wins":15},"qwen/qwen3.8-27b":{"draws":25,"losses":47,"wins":14},"qwen/qwen3.8-flash":{"draws":37,"losses":26,"wins":21},"qwen/qwen3.8-max":{"draws":41,"losses":61,"wins":24},"qwen/qwen3.8-max-0902":{"draws":46,"losses":68,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":31,"wins":8},"stealth/ox-alpha":{"draws":104,"losses":266,"wins":56},"stealth/space-bunny-alpha":{"draws":39,"losses":36,"wins":27},"stepfun/step-3.7-flash":{"draws":20,"losses":27,"wins":41},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":31,"wins":13},"tencent/hy4-preview":{"draws":43,"losses":69,"wins":10},"thinkingmachines/inkling":{"draws":60,"losses":56,"wins":58},"thinkingmachines/inkling-small":{"draws":60,"losses":24,"wins":42},"unbiased/pareto-26.10":{"draws":2,"losses":24,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":9},"x-ai/grok-4.5":{"draws":31,"losses":81,"wins":14},"x-ai/grok-4.6":{"draws":40,"losses":78,"wins":8},"x-ai/grok-4.7":{"draws":6,"losses":93,"wins":13},"x-ai/grok-build-0.1":{"draws":18,"losses":14,"wins":10},"xiaomi/mimo-v2.5":{"draws":80,"losses":50,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":28,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":43,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":56,"wins":13},"z-ai/glm-5.2":{"draws":114,"losses":95,"wins":43},"z-ai/glm-5.3":{"draws":25,"losses":83,"wins":12},"z-ai/glm-5.3-flash":{"draws":28,"losses":82,"wins":16},"z-ai/glm-5.3-flashx":{"draws":36,"losses":71,"wins":19}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":30,"wins":64},"claude-fable-5":{"draws":22,"losses":85,"wins":31},"claude-fable-5-1":{"draws":8,"losses":140,"wins":8},"claude-haiku-5-5":{"draws":26,"losses":65,"wins":41},"claude-opus-4-5":{"draws":61,"losses":60,"wins":103},"claude-opus-4-8":{"draws":29,"losses":53,"wins":44},"claude-opus-5":{"draws":30,"losses":179,"wins":35},"claude-opus-5-5":{"draws":12,"losses":129,"wins":9},"claude-sonnet-5":{"draws":38,"losses":36,"wins":64},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":43},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":40},"deepseek/deepseek-v4-flash":{"draws":52,"losses":34,"wins":120},"deepseek/deepseek-v4-pro":{"draws":24,"losses":45,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":40,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":53,"wins":52},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":35,"wins":22},"elorian/glimpse":{"draws":5,"losses":12,"wins":15},"fireworks/ember-1":{"draws":37,"losses":53,"wins":48},"gemini-3.1-pro-preview":{"draws":33,"losses":47,"wins":58},"gemini-4-argon":{"draws":9,"losses":45,"wins":6},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":60},"google/gemini-3.5-flash":{"draws":35,"losses":59,"wins":78},"google/gemini-3.5-flash-lite":{"draws":60,"losses":46,"wins":134},"google/gemini-3.6-flash":{"draws":51,"losses":106,"wins":107},"google/gemini-3.8-flash":{"draws":25,"losses":57,"wins":56},"google/gemma-4-31b-it":{"draws":23,"losses":17,"wins":40},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":5},"gpt-5":{"draws":24,"losses":31,"wins":67},"gpt-5.4":{"draws":26,"losses":59,"wins":47},"gpt-5.4-mini":{"draws":27,"losses":20,"wins":45},"gpt-5.4-nano":{"draws":22,"losses":45,"wins":69},"gpt-5.5":{"draws":26,"losses":58,"wins":44},"gpt-5.6-luna":{"draws":36,"losses":36,"wins":66},"gpt-5.6-sol":{"draws":17,"losses":88,"wins":33},"gpt-5.6-terra":{"draws":40,"losses":38,"wins":54},"gpt-6-astra":{"draws":7,"losses":127,"wins":4},"gpt-6-luna":{"draws":37,"losses":38,"wins":63},"gpt-6-sol":{"draws":18,"losses":96,"wins":24},"gpt-6.1-sol":{"draws":9,"losses":111,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":34,"losses":11,"wins":51},"inception/mercury-3":{"draws":18,"losses":17,"wins":27},"inclusionai/ling-3.0-flash":{"draws":27,"losses":11,"wins":58},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":28,"losses":27,"wins":93},"meta/muse-glimmer-30b":{"draws":32,"losses":19,"wins":73},"meta/muse-spark-1.2":{"draws":20,"losses":34,"wins":34},"meta/muse-spark-1.3":{"draws":25,"losses":61,"wins":52},"meta/muse-spark-open":{"draws":11,"losses":27,"wins":20},"meta/muse-wonder":{"draws":26,"losses":71,"wins":41},"minimax/minimax-m3":{"draws":14,"losses":10,"wins":52},"minimax/minimax-m3.1-flash":{"draws":16,"losses":23,"wins":33},"mistralai/mistral-large-4-0":{"draws":16,"losses":27,"wins":45},"mistralai/mistral-medium-3-5":{"draws":21,"losses":11,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":26,"losses":52,"wins":56},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":19,"wins":68},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":5,"wins":16},"o3":{"draws":22,"losses":69,"wins":95},"openai/gpt-oss-120b":{"draws":32,"losses":14,"wins":76},"poolside/laguna-s-2.1":{"draws":29,"losses":19,"wins":86},"qwen/qwen3.7-max":{"draws":11,"losses":19,"wins":50},"qwen/qwen3.7-plus":{"draws":16,"losses":12,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":54,"wins":48},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":36},"qwen/qwen3.8-flash":{"draws":22,"losses":28,"wins":42},"qwen/qwen3.8-max":{"draws":35,"losses":52,"wins":51},"qwen/qwen3.8-max-0902":{"draws":31,"losses":55,"wins":52},"reflection/beam-1.0-501b-a23b":{"draws":20,"losses":19,"wins":21},"stealth/ox-alpha":{"draws":105,"losses":205,"wins":148},"stealth/space-bunny-alpha":{"draws":31,"losses":26,"wins":53},"stepfun/step-3.7-flash":{"draws":15,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":21,"losses":13,"wins":42},"tencent/hy4-preview":{"draws":19,"losses":60,"wins":53},"thinkingmachines/inkling":{"draws":50,"losses":35,"wins":101},"thinkingmachines/inkling-small":{"draws":36,"losses":27,"wins":75},"unbiased/pareto-26.10":{"draws":2,"losses":30,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":22},"x-ai/grok-4.5":{"draws":33,"losses":69,"wins":36},"x-ai/grok-4.6":{"draws":30,"losses":76,"wins":32},"x-ai/grok-4.7":{"draws":9,"losses":85,"wins":28},"x-ai/grok-build-0.1":{"draws":10,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":62,"losses":27,"wins":123},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":21,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":28,"wins":47},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":54,"wins":27},"z-ai/glm-5.2":{"draws":65,"losses":75,"wins":136},"z-ai/glm-5.3":{"draws":22,"losses":68,"wins":42},"z-ai/glm-5.3-flash":{"draws":19,"losses":61,"wins":58},"z-ai/glm-5.3-flashx":{"draws":29,"losses":60,"wins":49}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":22,"wins":81},"claude-fable-5":{"draws":25,"losses":77,"wins":42},"claude-fable-5-1":{"draws":11,"losses":134,"wins":17},"claude-haiku-5-5":{"draws":26,"losses":61,"wins":51},"claude-opus-4-5":{"draws":54,"losses":54,"wins":126},"claude-opus-4-8":{"draws":26,"losses":51,"wins":55},"claude-opus-5":{"draws":30,"losses":166,"wins":50},"claude-opus-5-5":{"draws":8,"losses":134,"wins":14},"claude-sonnet-5":{"draws":37,"losses":33,"wins":74},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":54},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":48},"deepseek/deepseek-v4-flash":{"draws":41,"losses":24,"wins":151},"deepseek/deepseek-v4-pro":{"draws":20,"losses":36,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":39,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":52,"wins":62},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":43,"wins":36},"elorian/glimpse":{"draws":12,"losses":9,"wins":21},"fireworks/ember-1":{"draws":39,"losses":42,"wins":63},"gemini-3.1-pro-preview":{"draws":26,"losses":40,"wins":78},"gemini-4-argon":{"draws":7,"losses":56,"wins":11},"google/gemini-3.1-flash-lite":{"draws":16,"losses":5,"wins":75},"google/gemini-3.5-flash":{"draws":34,"losses":47,"wins":99},"google/gemini-3.5-flash-lite":{"draws":50,"losses":35,"wins":167},"google/gemini-3.6-flash":{"draws":48,"losses":95,"wins":133},"google/gemini-3.8-flash":{"draws":32,"losses":61,"wins":51},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":53},"gpt-4.1":{"draws":16,"losses":4,"wins":28},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":26,"losses":27,"wins":73},"gpt-5.4":{"draws":29,"losses":54,"wins":55},"gpt-5.4-mini":{"draws":19,"losses":11,"wins":66},"gpt-5.4-nano":{"draws":26,"losses":28,"wins":90},"gpt-5.5":{"draws":31,"losses":49,"wins":52},"gpt-5.6-luna":{"draws":36,"losses":29,"wins":79},"gpt-5.6-sol":{"draws":21,"losses":75,"wins":48},"gpt-5.6-terra":{"draws":33,"losses":39,"wins":66},"gpt-6-astra":{"draws":14,"losses":117,"wins":13},"gpt-6-luna":{"draws":25,"losses":36,"wins":83},"gpt-6-sol":{"draws":23,"losses":99,"wins":22},"gpt-6.1-sol":{"draws":13,"losses":117,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":29,"losses":8,"wins":65},"inception/mercury-3":{"draws":14,"losses":8,"wins":26},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":76},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":29,"losses":25,"wins":102},"meta/muse-glimmer-30b":{"draws":36,"losses":16,"wins":74},"meta/muse-spark-1.2":{"draws":25,"losses":52,"wins":61},"meta/muse-spark-1.3":{"draws":16,"losses":40,"wins":40},"meta/muse-spark-open":{"draws":10,"losses":22,"wins":24},"meta/muse-wonder":{"draws":28,"losses":74,"wins":42},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":60},"minimax/minimax-m3.1-flash":{"draws":11,"losses":17,"wins":46},"mistralai/mistral-large-4-0":{"draws":24,"losses":22,"wins":44},"mistralai/mistral-medium-3-5":{"draws":18,"losses":4,"wins":62},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":31,"losses":42,"wins":65},"nex-agi/nex-n2-pro":{"draws":11,"losses":6,"wins":55},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":12,"wins":84},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":12,"wins":23},"o3":{"draws":20,"losses":53,"wins":125},"openai/gpt-oss-120b":{"draws":32,"losses":12,"wins":82},"poolside/laguna-s-2.1":{"draws":31,"losses":26,"wins":81},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":47},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":44},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":51,"wins":59},"qwen/qwen3.8-27b":{"draws":19,"losses":31,"wins":52},"qwen/qwen3.8-flash":{"draws":23,"losses":26,"wins":47},"qwen/qwen3.8-max":{"draws":33,"losses":40,"wins":71},"qwen/qwen3.8-max-0902":{"draws":39,"losses":53,"wins":52},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":14,"wins":32},"stealth/ox-alpha":{"draws":87,"losses":167,"wins":220},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":69},"stepfun/step-3.7-flash":{"draws":10,"losses":13,"wins":79},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":15,"losses":14,"wins":49},"tencent/hy4-preview":{"draws":28,"losses":50,"wins":60},"thinkingmachines/inkling":{"draws":33,"losses":18,"wins":141},"thinkingmachines/inkling-small":{"draws":37,"losses":13,"wins":94},"unbiased/pareto-26.10":{"draws":3,"losses":21,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":26},"x-ai/grok-4.5":{"draws":23,"losses":60,"wins":61},"x-ai/grok-4.6":{"draws":32,"losses":59,"wins":53},"x-ai/grok-4.7":{"draws":11,"losses":83,"wins":32},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":55,"losses":19,"wins":148},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":52},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":49,"wins":32},"z-ai/glm-5.2":{"draws":58,"losses":68,"wins":162},"z-ai/glm-5.3":{"draws":25,"losses":73,"wins":40},"z-ai/glm-5.3-flash":{"draws":26,"losses":67,"wins":51},"z-ai/glm-5.3-flashx":{"draws":28,"losses":57,"wins":59}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":13,"wins":40},"claude-fable-5":{"draws":6,"losses":39,"wins":17},"claude-fable-5-1":{"draws":4,"losses":68,"wins":10},"claude-haiku-5-5":{"draws":12,"losses":13,"wins":33},"claude-opus-4-5":{"draws":31,"losses":24,"wins":49},"claude-opus-4-8":{"draws":19,"losses":20,"wins":19},"claude-opus-5":{"draws":14,"losses":99,"wins":17},"claude-opus-5-5":{"draws":6,"losses":66,"wins":4},"claude-sonnet-5":{"draws":21,"losses":12,"wins":41},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":23},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":27},"deepseek/deepseek-v4-flash":{"draws":20,"losses":12,"wins":74},"deepseek/deepseek-v4-pro":{"draws":19,"losses":19,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":20,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":22,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":64,"wins":37},"elorian/glimpse":{"draws":13,"losses":34,"wins":25},"fireworks/ember-1":{"draws":16,"losses":21,"wins":31},"gemini-3.1-pro-preview":{"draws":9,"losses":20,"wins":25},"gemini-4-argon":{"draws":11,"losses":104,"wins":19},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":34},"google/gemini-3.5-flash":{"draws":12,"losses":24,"wins":30},"google/gemini-3.5-flash-lite":{"draws":22,"losses":17,"wins":80},"google/gemini-3.6-flash":{"draws":22,"losses":48,"wins":56},"google/gemini-3.8-flash":{"draws":12,"losses":31,"wins":19},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":28},"gpt-4.1":{"draws":3,"losses":8,"wins":16},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":13,"wins":28},"gpt-5.4":{"draws":16,"losses":27,"wins":31},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":20},"gpt-5.4-nano":{"draws":4,"losses":9,"wins":43},"gpt-5.5":{"draws":17,"losses":17,"wins":30},"gpt-5.6-luna":{"draws":25,"losses":16,"wins":37},"gpt-5.6-sol":{"draws":10,"losses":40,"wins":24},"gpt-5.6-terra":{"draws":24,"losses":17,"wins":25},"gpt-6-astra":{"draws":5,"losses":58,"wins":1},"gpt-6-luna":{"draws":15,"losses":21,"wins":26},"gpt-6-sol":{"draws":6,"losses":55,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":53,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":30},"inception/mercury-3":{"draws":16,"losses":22,"wins":48},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":15,"losses":7,"wins":48},"meta/muse-glimmer-30b":{"draws":19,"losses":12,"wins":35},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":27},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":22},"meta/muse-spark-open":{"draws":16,"losses":32,"wins":32},"meta/muse-wonder":{"draws":15,"losses":36,"wins":21},"minimax/minimax-m3":{"draws":9,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":20,"losses":33,"wins":61},"mistralai/mistral-large-4-0":{"draws":5,"losses":14,"wins":21},"mistralai/mistral-medium-3-5":{"draws":9,"losses":8,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":15},"moonshotai/kimi-k3":{"draws":19,"losses":20,"wins":29},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":11,"wins":38},"o3":{"draws":11,"losses":24,"wins":69},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":32},"poolside/laguna-s-2.1":{"draws":21,"losses":5,"wins":42},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":25},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":31},"qwen/qwen3.8-27b":{"draws":9,"losses":16,"wins":33},"qwen/qwen3.8-flash":{"draws":13,"losses":20,"wins":19},"qwen/qwen3.8-max":{"draws":13,"losses":27,"wins":30},"qwen/qwen3.8-max-0902":{"draws":14,"losses":29,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":27,"losses":34,"wins":59},"stealth/ox-alpha":{"draws":36,"losses":65,"wins":91},"stealth/space-bunny-alpha":{"draws":14,"losses":16,"wins":30},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":39},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":14,"losses":5,"wins":17},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":42},"thinkingmachines/inkling":{"draws":27,"losses":11,"wins":60},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":48},"unbiased/pareto-26.10":{"draws":2,"losses":40,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":20,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":19},"x-ai/grok-4.5":{"draws":11,"losses":34,"wins":31},"x-ai/grok-4.6":{"draws":13,"losses":30,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":39,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":17},"xiaomi/mimo-v2.5":{"draws":32,"losses":9,"wins":91},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":20,"wins":17},"z-ai/glm-5.2":{"draws":36,"losses":30,"wins":84},"z-ai/glm-5.3":{"draws":11,"losses":42,"wins":17},"z-ai/glm-5.3-flash":{"draws":15,"losses":28,"wins":33},"z-ai/glm-5.3-flashx":{"draws":11,"losses":33,"wins":26}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":16,"wins":86},"claude-fable-5":{"draws":25,"losses":62,"wins":57},"claude-fable-5-1":{"draws":13,"losses":118,"wins":31},"claude-haiku-5-5":{"draws":30,"losses":29,"wins":79},"claude-opus-4-5":{"draws":47,"losses":48,"wins":139},"claude-opus-4-8":{"draws":26,"losses":44,"wins":62},"claude-opus-5":{"draws":29,"losses":141,"wins":76},"claude-opus-5-5":{"draws":9,"losses":116,"wins":31},"claude-sonnet-5":{"draws":31,"losses":28,"wins":85},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":54},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":47},"deepseek/deepseek-v4-flash":{"draws":37,"losses":31,"wins":148},"deepseek/deepseek-v4-pro":{"draws":23,"losses":30,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":27,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":71},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":31,"wins":27},"elorian/glimpse":{"draws":12,"losses":13,"wins":19},"fireworks/ember-1":{"draws":38,"losses":30,"wins":76},"gemini-3.1-pro-preview":{"draws":26,"losses":24,"wins":94},"gemini-4-argon":{"draws":3,"losses":46,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":84},"google/gemini-3.5-flash":{"draws":30,"losses":29,"wins":121},"google/gemini-3.5-flash-lite":{"draws":43,"losses":27,"wins":182},"google/gemini-3.6-flash":{"draws":50,"losses":71,"wins":155},"google/gemini-3.8-flash":{"draws":36,"losses":40,"wins":68},"google/gemma-4-31b-it":{"draws":17,"losses":7,"wins":60},"gpt-4.1":{"draws":7,"losses":6,"wins":35},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":23,"losses":23,"wins":80},"gpt-5.4":{"draws":29,"losses":43,"wins":66},"gpt-5.4-mini":{"draws":24,"losses":10,"wins":62},"gpt-5.4-nano":{"draws":12,"losses":22,"wins":110},"gpt-5.5":{"draws":37,"losses":36,"wins":59},"gpt-5.6-luna":{"draws":28,"losses":25,"wins":91},"gpt-5.6-sol":{"draws":22,"losses":57,"wins":65},"gpt-5.6-terra":{"draws":31,"losses":30,"wins":77},"gpt-6-astra":{"draws":14,"losses":114,"wins":16},"gpt-6-luna":{"draws":34,"losses":33,"wins":77},"gpt-6-sol":{"draws":18,"losses":81,"wins":45},"gpt-6.1-sol":{"draws":19,"losses":96,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":70},"inception/mercury-3":{"draws":16,"losses":12,"wins":23},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":79},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":31,"losses":20,"wins":105},"meta/muse-glimmer-30b":{"draws":26,"losses":15,"wins":85},"meta/muse-spark-1.2":{"draws":26,"losses":41,"wins":71},"meta/muse-spark-1.3":{"draws":28,"losses":42,"wins":74},"meta/muse-spark-open":{"draws":15,"losses":21,"wins":36},"meta/muse-wonder":{"draws":18,"losses":39,"wins":39},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":53},"minimax/minimax-m3.1-flash":{"draws":6,"losses":12,"wins":46},"mistralai/mistral-large-4-0":{"draws":19,"losses":23,"wins":48},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":62},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":8,"wins":21},"moonshotai/kimi-k3":{"draws":26,"losses":27,"wins":85},"nex-agi/nex-n2-pro":{"draws":13,"losses":6,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":8,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":4,"wins":17},"o3":{"draws":13,"losses":34,"wins":151},"openai/gpt-oss-120b":{"draws":23,"losses":10,"wins":93},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":105},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":61},"qwen/qwen3.7-plus":{"draws":15,"losses":2,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":44,"wins":73},"qwen/qwen3.8-27b":{"draws":19,"losses":14,"wins":69},"qwen/qwen3.8-flash":{"draws":24,"losses":12,"wins":60},"qwen/qwen3.8-max":{"draws":31,"losses":32,"wins":81},"qwen/qwen3.8-max-0902":{"draws":33,"losses":33,"wins":78},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":9,"wins":43},"stealth/ox-alpha":{"draws":93,"losses":128,"wins":253},"stealth/space-bunny-alpha":{"draws":28,"losses":18,"wins":68},"stepfun/step-3.7-flash":{"draws":12,"losses":10,"wins":80},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":15,"losses":12,"wins":51},"tencent/hy4-preview":{"draws":28,"losses":39,"wins":71},"thinkingmachines/inkling":{"draws":44,"losses":22,"wins":126},"thinkingmachines/inkling-small":{"draws":33,"losses":15,"wins":96},"unbiased/pareto-26.10":{"draws":6,"losses":28,"wins":6},"unbiased/pareto-26.10-preview":{"draws":4,"losses":35,"wins":9},"upstage/solar-mini4":{"draws":3,"losses":1,"wins":32},"x-ai/grok-4.5":{"draws":29,"losses":36,"wins":79},"x-ai/grok-4.6":{"draws":41,"losses":41,"wins":62},"x-ai/grok-4.7":{"draws":16,"losses":72,"wins":38},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":33},"xiaomi/mimo-v2.5":{"draws":45,"losses":17,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":15,"wins":56},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":22,"wins":63},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":36,"wins":43},"z-ai/glm-5.2":{"draws":65,"losses":45,"wins":178},"z-ai/glm-5.3":{"draws":17,"losses":59,"wins":62},"z-ai/glm-5.3-flash":{"draws":30,"losses":43,"wins":71},"z-ai/glm-5.3-flashx":{"draws":34,"losses":37,"wins":73}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":35,"wins":15},"claude-fable-5":{"draws":20,"losses":52,"wins":6},"claude-fable-5-1":{"draws":1,"losses":84,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":53,"wins":15},"claude-opus-4-5":{"draws":39,"losses":77,"wins":12},"claude-opus-4-8":{"draws":16,"losses":48,"wins":10},"claude-opus-5":{"draws":14,"losses":117,"wins":7},"claude-opus-5-5":{"draws":2,"losses":83,"wins":1},"claude-sonnet-5":{"draws":21,"losses":42,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":52,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":36,"losses":42,"wins":42},"deepseek/deepseek-v4-pro":{"draws":13,"losses":48,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":40,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":42,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":32,"wins":3},"elorian/glimpse":{"draws":7,"losses":13,"wins":8},"fireworks/ember-1":{"draws":19,"losses":54,"wins":5},"gemini-3.1-pro-preview":{"draws":19,"losses":37,"wins":22},"gemini-4-argon":{"draws":0,"losses":40,"wins":0},"google/gemini-3.1-flash-lite":{"draws":13,"losses":16,"wins":25},"google/gemini-3.5-flash":{"draws":23,"losses":52,"wins":23},"google/gemini-3.5-flash-lite":{"draws":36,"losses":52,"wins":46},"google/gemini-3.6-flash":{"draws":30,"losses":93,"wins":25},"google/gemini-3.8-flash":{"draws":16,"losses":56,"wins":6},"google/gemma-4-31b-it":{"draws":19,"losses":11,"wins":16},"gpt-4.1":{"draws":8,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":5,"losses":1,"wins":2},"gpt-5":{"draws":17,"losses":36,"wins":17},"gpt-5.4":{"draws":15,"losses":43,"wins":16},"gpt-5.4-mini":{"draws":18,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":18,"losses":39,"wins":27},"gpt-5.5":{"draws":24,"losses":37,"wins":11},"gpt-5.6-luna":{"draws":26,"losses":31,"wins":21},"gpt-5.6-sol":{"draws":13,"losses":61,"wins":4},"gpt-5.6-terra":{"draws":19,"losses":42,"wins":13},"gpt-6-astra":{"draws":1,"losses":75,"wins":2},"gpt-6-luna":{"draws":22,"losses":42,"wins":14},"gpt-6-sol":{"draws":9,"losses":62,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":70,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":9,"wins":19},"inception/mercury-3":{"draws":13,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":21,"losses":10,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":35,"wins":30},"meta/muse-glimmer-30b":{"draws":25,"losses":20,"wins":25},"meta/muse-spark-1.2":{"draws":14,"losses":52,"wins":10},"meta/muse-spark-1.3":{"draws":11,"losses":60,"wins":7},"meta/muse-spark-open":{"draws":9,"losses":22,"wins":1},"meta/muse-wonder":{"draws":13,"losses":53,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":27,"wins":11},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":13},"mistralai/mistral-medium-3-5":{"draws":14,"losses":14,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":47,"wins":14},"nex-agi/nex-n2-pro":{"draws":10,"losses":11,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":20,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":9},"o3":{"draws":15,"losses":70,"wins":27},"openai/gpt-oss-120b":{"draws":22,"losses":27,"wins":21},"poolside/laguna-s-2.1":{"draws":26,"losses":30,"wins":22},"qwen/qwen3.7-max":{"draws":17,"losses":23,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":50,"wins":8},"qwen/qwen3.8-27b":{"draws":14,"losses":32,"wins":8},"qwen/qwen3.8-flash":{"draws":13,"losses":23,"wins":16},"qwen/qwen3.8-max":{"draws":23,"losses":41,"wins":14},"qwen/qwen3.8-max-0902":{"draws":21,"losses":49,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":18,"wins":5},"stealth/ox-alpha":{"draws":55,"losses":148,"wins":39},"stealth/space-bunny-alpha":{"draws":18,"losses":31,"wins":13},"stepfun/step-3.7-flash":{"draws":11,"losses":18,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":18,"wins":11},"tencent/hy4-preview":{"draws":17,"losses":50,"wins":7},"thinkingmachines/inkling":{"draws":26,"losses":44,"wins":34},"thinkingmachines/inkling-small":{"draws":25,"losses":19,"wins":34},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":26,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":10,"wins":6},"x-ai/grok-4.5":{"draws":14,"losses":59,"wins":5},"x-ai/grok-4.6":{"draws":20,"losses":54,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":61,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.5":{"draws":43,"losses":40,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":20,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":28,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":37,"wins":8},"z-ai/glm-5.2":{"draws":47,"losses":72,"wins":37},"z-ai/glm-5.3":{"draws":16,"losses":52,"wins":6},"z-ai/glm-5.3-flash":{"draws":17,"losses":47,"wins":14},"z-ai/glm-5.3-flashx":{"draws":20,"losses":46,"wins":12}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":21,"wins":34},"claude-fable-5":{"draws":14,"losses":36,"wins":10},"claude-fable-5-1":{"draws":7,"losses":79,"wins":4},"claude-haiku-5-5":{"draws":19,"losses":40,"wins":15},"claude-opus-4-5":{"draws":40,"losses":59,"wins":37},"claude-opus-4-8":{"draws":19,"losses":36,"wins":17},"claude-opus-5":{"draws":11,"losses":84,"wins":11},"claude-opus-5-5":{"draws":5,"losses":71,"wins":0},"claude-sonnet-5":{"draws":17,"losses":33,"wins":22},"claude-sonnet-5-5":{"draws":16,"losses":39,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":13},"deepseek/deepseek-v4-flash":{"draws":27,"losses":36,"wins":51},"deepseek/deepseek-v4-pro":{"draws":15,"losses":21,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":32,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":35,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":61,"wins":22},"elorian/glimpse":{"draws":18,"losses":33,"wins":15},"fireworks/ember-1":{"draws":17,"losses":31,"wins":10},"gemini-3.1-pro-preview":{"draws":25,"losses":28,"wins":19},"gemini-4-argon":{"draws":13,"losses":97,"wins":10},"google/gemini-3.1-flash-lite":{"draws":12,"losses":7,"wins":39},"google/gemini-3.5-flash":{"draws":21,"losses":35,"wins":26},"google/gemini-3.5-flash-lite":{"draws":36,"losses":33,"wins":51},"google/gemini-3.6-flash":{"draws":34,"losses":75,"wins":39},"google/gemini-3.8-flash":{"draws":15,"losses":48,"wins":17},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":17},"gpt-4.1":{"draws":6,"losses":15,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":30,"wins":21},"gpt-5.4":{"draws":15,"losses":49,"wins":10},"gpt-5.4-mini":{"draws":24,"losses":9,"wins":25},"gpt-5.4-nano":{"draws":10,"losses":35,"wins":31},"gpt-5.5":{"draws":25,"losses":24,"wins":13},"gpt-5.6-luna":{"draws":19,"losses":26,"wins":27},"gpt-5.6-sol":{"draws":10,"losses":54,"wins":12},"gpt-5.6-terra":{"draws":17,"losses":29,"wins":22},"gpt-6-astra":{"draws":6,"losses":68,"wins":0},"gpt-6-luna":{"draws":15,"losses":32,"wins":25},"gpt-6-sol":{"draws":13,"losses":55,"wins":4},"gpt-6.1-sol":{"draws":8,"losses":55,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":8,"wins":29},"inception/mercury-3":{"draws":16,"losses":34,"wins":20},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":25,"wins":35},"meta/muse-glimmer-30b":{"draws":20,"losses":17,"wins":27},"meta/muse-spark-1.2":{"draws":16,"losses":33,"wins":23},"meta/muse-spark-1.3":{"draws":11,"losses":46,"wins":17},"meta/muse-spark-open":{"draws":20,"losses":61,"wins":33},"meta/muse-wonder":{"draws":6,"losses":46,"wins":12},"minimax/minimax-m3":{"draws":10,"losses":11,"wins":27},"minimax/minimax-m3.1-flash":{"draws":8,"losses":26,"wins":26},"mistralai/mistral-large-4-0":{"draws":11,"losses":19,"wins":16},"mistralai/mistral-medium-3-5":{"draws":11,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":7},"moonshotai/kimi-k3":{"draws":18,"losses":24,"wins":24},"nex-agi/nex-n2-pro":{"draws":17,"losses":11,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":5,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":16,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":18,"wins":19},"o3":{"draws":7,"losses":40,"wins":37},"openai/gpt-oss-120b":{"draws":19,"losses":10,"wins":27},"poolside/laguna-s-2.1":{"draws":17,"losses":19,"wins":30},"qwen/qwen3.7-max":{"draws":6,"losses":17,"wins":19},"qwen/qwen3.7-plus":{"draws":7,"losses":12,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":30,"wins":14},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":21},"qwen/qwen3.8-flash":{"draws":12,"losses":20,"wins":10},"qwen/qwen3.8-max":{"draws":20,"losses":40,"wins":24},"qwen/qwen3.8-max-0902":{"draws":16,"losses":44,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":27,"losses":44,"wins":39},"stealth/ox-alpha":{"draws":59,"losses":127,"wins":64},"stealth/space-bunny-alpha":{"draws":13,"losses":21,"wins":12},"stepfun/step-3.7-flash":{"draws":4,"losses":18,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":21,"wins":12},"tencent/hy4-preview":{"draws":14,"losses":29,"wins":23},"thinkingmachines/inkling":{"draws":20,"losses":38,"wins":45},"thinkingmachines/inkling-small":{"draws":28,"losses":18,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":38,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":30,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":11},"x-ai/grok-4.5":{"draws":19,"losses":42,"wins":17},"x-ai/grok-4.6":{"draws":21,"losses":32,"wins":17},"x-ai/grok-4.7":{"draws":5,"losses":45,"wins":12},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":27,"losses":38,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":17,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":30,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":27,"wins":9},"z-ai/glm-5.2":{"draws":44,"losses":51,"wins":51},"z-ai/glm-5.3":{"draws":9,"losses":41,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":45,"wins":28},"z-ai/glm-5.3-flashx":{"draws":14,"losses":49,"wins":17}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":24,"wins":33},"claude-fable-5":{"draws":18,"losses":49,"wins":23},"claude-fable-5-1":{"draws":4,"losses":92,"wins":6},"claude-haiku-5-5":{"draws":30,"losses":28,"wins":28},"claude-opus-4-5":{"draws":46,"losses":53,"wins":47},"claude-opus-4-8":{"draws":18,"losses":31,"wins":33},"claude-opus-5":{"draws":24,"losses":119,"wins":19},"claude-opus-5-5":{"draws":14,"losses":79,"wins":5},"claude-sonnet-5":{"draws":27,"losses":39,"wins":24},"claude-sonnet-5-5":{"draws":23,"losses":43,"wins":24},"cohere/north-mini-code":{"draws":9,"losses":5,"wins":20},"deepseek/deepseek-v4-flash":{"draws":45,"losses":20,"wins":69},"deepseek/deepseek-v4-pro":{"draws":26,"losses":26,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":28,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":31,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":29,"wins":12},"elorian/glimpse":{"draws":4,"losses":5,"wins":5},"fireworks/ember-1":{"draws":26,"losses":31,"wins":33},"gemini-3.1-pro-preview":{"draws":21,"losses":34,"wins":35},"gemini-4-argon":{"draws":2,"losses":24,"wins":4},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":39},"google/gemini-3.5-flash":{"draws":38,"losses":35,"wins":39},"google/gemini-3.5-flash-lite":{"draws":52,"losses":29,"wins":75},"google/gemini-3.6-flash":{"draws":41,"losses":72,"wins":59},"google/gemini-3.8-flash":{"draws":28,"losses":36,"wins":26},"google/gemma-4-31b-it":{"draws":19,"losses":9,"wins":24},"gpt-4.1":{"draws":12,"losses":8,"wins":10},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":30,"losses":16,"wins":34},"gpt-5.4":{"draws":30,"losses":40,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":12,"wins":20},"gpt-5.4-nano":{"draws":16,"losses":24,"wins":48},"gpt-5.5":{"draws":29,"losses":33,"wins":22},"gpt-5.6-luna":{"draws":32,"losses":15,"wins":43},"gpt-5.6-sol":{"draws":19,"losses":51,"wins":20},"gpt-5.6-terra":{"draws":41,"losses":19,"wins":26},"gpt-6-astra":{"draws":9,"losses":76,"wins":5},"gpt-6-luna":{"draws":27,"losses":32,"wins":31},"gpt-6-sol":{"draws":15,"losses":61,"wins":14},"gpt-6.1-sol":{"draws":9,"losses":70,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":9,"wins":27},"inception/mercury-3":{"draws":14,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":28,"losses":9,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":16,"wins":46},"meta/muse-glimmer-30b":{"draws":27,"losses":19,"wins":36},"meta/muse-spark-1.2":{"draws":16,"losses":45,"wins":27},"meta/muse-spark-1.3":{"draws":24,"losses":44,"wins":22},"meta/muse-spark-open":{"draws":5,"losses":21,"wins":14},"meta/muse-wonder":{"draws":19,"losses":48,"wins":23},"minimax/minimax-m3":{"draws":12,"losses":13,"wins":25},"minimax/minimax-m3.1-flash":{"draws":11,"losses":16,"wins":19},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":22,"losses":7,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":30,"losses":31,"wins":27},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":18,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":8,"wins":13},"o3":{"draws":28,"losses":39,"wins":53},"openai/gpt-oss-120b":{"draws":31,"losses":14,"wins":35},"poolside/laguna-s-2.1":{"draws":32,"losses":20,"wins":36},"qwen/qwen3.7-max":{"draws":21,"losses":5,"wins":26},"qwen/qwen3.7-plus":{"draws":13,"losses":2,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":42,"wins":26},"qwen/qwen3.8-27b":{"draws":19,"losses":21,"wins":22},"qwen/qwen3.8-flash":{"draws":22,"losses":17,"wins":21},"qwen/qwen3.8-max":{"draws":31,"losses":29,"wins":30},"qwen/qwen3.8-max-0902":{"draws":32,"losses":40,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":19,"wins":18},"stealth/ox-alpha":{"draws":98,"losses":120,"wins":82},"stealth/space-bunny-alpha":{"draws":26,"losses":14,"wins":32},"stepfun/step-3.7-flash":{"draws":20,"losses":9,"wins":33},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":20,"losses":16,"wins":14},"tencent/hy4-preview":{"draws":22,"losses":36,"wins":28},"thinkingmachines/inkling":{"draws":42,"losses":22,"wins":58},"thinkingmachines/inkling-small":{"draws":31,"losses":14,"wins":45},"unbiased/pareto-26.10":{"draws":3,"losses":18,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":24,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":13},"x-ai/grok-4.5":{"draws":20,"losses":41,"wins":29},"x-ai/grok-4.6":{"draws":30,"losses":43,"wins":17},"x-ai/grok-4.7":{"draws":14,"losses":50,"wins":16},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":58,"losses":19,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":11,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":20,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":28,"wins":19},"z-ai/glm-5.2":{"draws":71,"losses":37,"wins":72},"z-ai/glm-5.3":{"draws":15,"losses":51,"wins":20},"z-ai/glm-5.3-flash":{"draws":26,"losses":42,"wins":22},"z-ai/glm-5.3-flashx":{"draws":29,"losses":34,"wins":27}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":26,"wins":18},"claude-fable-5":{"draws":19,"losses":59,"wins":6},"claude-fable-5-1":{"draws":5,"losses":88,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":54,"wins":4},"claude-opus-4-5":{"draws":44,"losses":80,"wins":12},"claude-opus-4-8":{"draws":25,"losses":45,"wins":6},"claude-opus-5":{"draws":21,"losses":111,"wins":12},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":32,"losses":42,"wins":10},"claude-sonnet-5-5":{"draws":19,"losses":57,"wins":8},"cohere/north-mini-code":{"draws":9,"losses":12,"wins":11},"deepseek/deepseek-v4-flash":{"draws":53,"losses":42,"wins":29},"deepseek/deepseek-v4-pro":{"draws":20,"losses":47,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":41,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":45,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":37,"wins":3},"elorian/glimpse":{"draws":7,"losses":15,"wins":6},"fireworks/ember-1":{"draws":27,"losses":51,"wins":6},"gemini-3.1-pro-preview":{"draws":32,"losses":41,"wins":11},"gemini-4-argon":{"draws":3,"losses":37,"wins":0},"google/gemini-3.1-flash-lite":{"draws":14,"losses":16,"wins":24},"google/gemini-3.5-flash":{"draws":31,"losses":58,"wins":15},"google/gemini-3.5-flash-lite":{"draws":52,"losses":64,"wins":32},"google/gemini-3.6-flash":{"draws":57,"losses":89,"wins":14},"google/gemini-3.8-flash":{"draws":19,"losses":59,"wins":6},"google/gemma-4-31b-it":{"draws":22,"losses":21,"wins":7},"gpt-4.1":{"draws":13,"losses":10,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":22,"losses":34,"wins":16},"gpt-5.4":{"draws":23,"losses":45,"wins":12},"gpt-5.4-mini":{"draws":24,"losses":24,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":47,"wins":16},"gpt-5.5":{"draws":26,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":34,"losses":38,"wins":12},"gpt-5.6-sol":{"draws":13,"losses":66,"wins":5},"gpt-5.6-terra":{"draws":26,"losses":46,"wins":8},"gpt-6-astra":{"draws":6,"losses":78,"wins":0},"gpt-6-luna":{"draws":30,"losses":47,"wins":7},"gpt-6-sol":{"draws":7,"losses":73,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":81,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":29,"losses":17,"wins":16},"inception/mercury-3":{"draws":7,"losses":19,"wins":2},"inclusionai/ling-3.0-flash":{"draws":25,"losses":15,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":36,"losses":34,"wins":22},"meta/muse-glimmer-30b":{"draws":35,"losses":27,"wins":10},"meta/muse-spark-1.2":{"draws":21,"losses":48,"wins":11},"meta/muse-spark-1.3":{"draws":18,"losses":62,"wins":4},"meta/muse-spark-open":{"draws":9,"losses":31,"wins":8},"meta/muse-wonder":{"draws":16,"losses":62,"wins":6},"minimax/minimax-m3":{"draws":14,"losses":16,"wins":14},"minimax/minimax-m3.1-flash":{"draws":11,"losses":19,"wins":8},"mistralai/mistral-large-4-0":{"draws":22,"losses":23,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":46,"wins":9},"nex-agi/nex-n2-pro":{"draws":14,"losses":8,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":25,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":11,"wins":2},"o3":{"draws":25,"losses":71,"wins":14},"openai/gpt-oss-120b":{"draws":34,"losses":26,"wins":14},"poolside/laguna-s-2.1":{"draws":35,"losses":32,"wins":15},"qwen/qwen3.7-max":{"draws":24,"losses":20,"wins":4},"qwen/qwen3.7-plus":{"draws":17,"losses":13,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":56,"wins":3},"qwen/qwen3.8-27b":{"draws":20,"losses":34,"wins":4},"qwen/qwen3.8-flash":{"draws":22,"losses":29,"wins":5},"qwen/qwen3.8-max":{"draws":26,"losses":49,"wins":9},"qwen/qwen3.8-max-0902":{"draws":29,"losses":49,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":22,"wins":5},"stealth/ox-alpha":{"draws":72,"losses":171,"wins":39},"stealth/space-bunny-alpha":{"draws":24,"losses":30,"wins":12},"stepfun/step-3.7-flash":{"draws":19,"losses":24,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":28,"losses":46,"wins":6},"thinkingmachines/inkling":{"draws":39,"losses":48,"wins":23},"thinkingmachines/inkling-small":{"draws":39,"losses":30,"wins":15},"unbiased/pareto-26.10":{"draws":3,"losses":19,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":15,"wins":1},"x-ai/grok-4.5":{"draws":21,"losses":56,"wins":7},"x-ai/grok-4.6":{"draws":27,"losses":51,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":61,"wins":3},"x-ai/grok-build-0.1":{"draws":14,"losses":12,"wins":2},"xiaomi/mimo-v2.5":{"draws":58,"losses":45,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":23,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":33,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":42,"wins":7},"z-ai/glm-5.2":{"draws":74,"losses":75,"wins":19},"z-ai/glm-5.3":{"draws":15,"losses":63,"wins":4},"z-ai/glm-5.3-flash":{"draws":24,"losses":51,"wins":9},"z-ai/glm-5.3-flashx":{"draws":21,"losses":55,"wins":8}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":15},"claude-fable-5":{"draws":8,"losses":21,"wins":7},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":16,"losses":29,"wins":15},"claude-opus-4-8":{"draws":10,"losses":19,"wins":7},"claude-opus-5":{"draws":3,"losses":59,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":9,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":18,"wins":2},"elorian/glimpse":{"draws":2,"losses":3,"wins":3},"fireworks/ember-1":{"draws":11,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"gemini-4-argon":{"draws":4,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":14,"wins":33},"google/gemini-3.6-flash":{"draws":19,"losses":33,"wins":16},"google/gemini-3.8-flash":{"draws":6,"losses":13,"wins":17},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":11,"wins":15},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":16},"gpt-5.5":{"draws":13,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":23,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":13,"wins":11},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":14,"wins":10},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":14},"inception/mercury-3":{"draws":6,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":11},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":15},"meta/muse-spark-open":{"draws":2,"losses":15,"wins":5},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":13},"minimax/minimax-m3.1-flash":{"draws":3,"losses":7,"wins":8},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":15},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":4},"o3":{"draws":5,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":8,"wins":5},"stealth/ox-alpha":{"draws":24,"losses":49,"wins":29},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":9,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":28},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":22,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":11,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":16,"losses":26,"wins":30},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":30,"wins":60},"claude-fable-5":{"draws":26,"losses":84,"wins":28},"claude-fable-5-1":{"draws":7,"losses":137,"wins":12},"claude-haiku-5-5":{"draws":34,"losses":58,"wins":40},"claude-opus-4-5":{"draws":78,"losses":64,"wins":82},"claude-opus-4-8":{"draws":32,"losses":51,"wins":43},"claude-opus-5":{"draws":38,"losses":167,"wins":39},"claude-opus-5-5":{"draws":5,"losses":132,"wins":13},"claude-sonnet-5":{"draws":41,"losses":38,"wins":59},"claude-sonnet-5-5":{"draws":28,"losses":63,"wins":47},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":35},"deepseek/deepseek-v4-flash":{"draws":59,"losses":42,"wins":105},"deepseek/deepseek-v4-pro":{"draws":28,"losses":44,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":50,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":57,"wins":41},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":44,"wins":22},"elorian/glimpse":{"draws":10,"losses":16,"wins":12},"fireworks/ember-1":{"draws":45,"losses":56,"wins":37},"gemini-3.1-pro-preview":{"draws":36,"losses":41,"wins":61},"gemini-4-argon":{"draws":2,"losses":49,"wins":3},"google/gemini-3.1-flash-lite":{"draws":23,"losses":11,"wins":56},"google/gemini-3.5-flash":{"draws":53,"losses":60,"wins":59},"google/gemini-3.5-flash-lite":{"draws":77,"losses":44,"wins":119},"google/gemini-3.6-flash":{"draws":71,"losses":103,"wins":90},"google/gemini-3.8-flash":{"draws":34,"losses":71,"wins":33},"google/gemma-4-31b-it":{"draws":29,"losses":13,"wins":38},"gpt-4.1":{"draws":13,"losses":12,"wins":21},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":32,"losses":41,"wins":49},"gpt-5.4":{"draws":27,"losses":68,"wins":37},"gpt-5.4-mini":{"draws":32,"losses":22,"wins":38},"gpt-5.4-nano":{"draws":34,"losses":34,"wins":68},"gpt-5.5":{"draws":37,"losses":45,"wins":46},"gpt-5.6-luna":{"draws":46,"losses":31,"wins":61},"gpt-5.6-sol":{"draws":22,"losses":84,"wins":32},"gpt-5.6-terra":{"draws":38,"losses":43,"wins":51},"gpt-6-astra":{"draws":9,"losses":119,"wins":10},"gpt-6-luna":{"draws":45,"losses":42,"wins":51},"gpt-6-sol":{"draws":15,"losses":97,"wins":26},"gpt-6.1-sol":{"draws":10,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":44,"losses":8,"wins":44},"inception/mercury-3":{"draws":18,"losses":16,"wins":12},"inclusionai/ling-3.0-flash":{"draws":31,"losses":12,"wins":53},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":43,"losses":26,"wins":79},"meta/muse-glimmer-30b":{"draws":38,"losses":19,"wins":67},"meta/muse-spark-1.2":{"draws":26,"losses":56,"wins":52},"meta/muse-spark-1.3":{"draws":31,"losses":65,"wins":42},"meta/muse-spark-open":{"draws":19,"losses":29,"wins":20},"meta/muse-wonder":{"draws":26,"losses":85,"wins":27},"minimax/minimax-m3":{"draws":15,"losses":14,"wins":47},"minimax/minimax-m3.1-flash":{"draws":18,"losses":24,"wins":24},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":31},"mistralai/mistral-medium-3-5":{"draws":25,"losses":9,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":28,"losses":30,"wins":30},"nex-agi/nex-n2-pro":{"draws":16,"losses":10,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":28,"wins":51},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":5,"wins":11},"o3":{"draws":30,"losses":72,"wins":84},"openai/gpt-oss-120b":{"draws":35,"losses":19,"wins":68},"poolside/laguna-s-2.1":{"draws":47,"losses":22,"wins":65},"qwen/qwen3.7-max":{"draws":19,"losses":20,"wins":41},"qwen/qwen3.7-plus":{"draws":25,"losses":15,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":50,"wins":50},"qwen/qwen3.8-27b":{"draws":28,"losses":27,"wins":41},"qwen/qwen3.8-flash":{"draws":30,"losses":29,"wins":33},"qwen/qwen3.8-max":{"draws":38,"losses":52,"wins":48},"qwen/qwen3.8-max-0902":{"draws":36,"losses":68,"wins":34},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":19,"wins":27},"stealth/ox-alpha":{"draws":111,"losses":182,"wins":165},"stealth/space-bunny-alpha":{"draws":37,"losses":20,"wins":53},"stepfun/step-3.7-flash":{"draws":21,"losses":16,"wins":59},"stepfun/step-5-preview":{"draws":2,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":28,"losses":20,"wins":28},"tencent/hy4-preview":{"draws":33,"losses":55,"wins":44},"thinkingmachines/inkling":{"draws":54,"losses":39,"wins":93},"thinkingmachines/inkling-small":{"draws":48,"losses":21,"wins":69},"unbiased/pareto-26.10":{"draws":1,"losses":31,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":43,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":31,"losses":62,"wins":45},"x-ai/grok-4.6":{"draws":34,"losses":70,"wins":34},"x-ai/grok-4.7":{"draws":13,"losses":82,"wins":27},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":25},"xiaomi/mimo-v2.5":{"draws":75,"losses":31,"wins":106},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":23,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":32,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":49,"wins":25},"z-ai/glm-5.2":{"draws":95,"losses":70,"wins":111},"z-ai/glm-5.3":{"draws":29,"losses":66,"wins":37},"z-ai/glm-5.3-flash":{"draws":32,"losses":63,"wins":43},"z-ai/glm-5.3-flashx":{"draws":41,"losses":63,"wins":34}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":36,"wins":12},"claude-fable-5":{"draws":14,"losses":57,"wins":1},"claude-fable-5-1":{"draws":4,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":43,"wins":10},"claude-opus-4-5":{"draws":27,"losses":74,"wins":15},"claude-opus-4-8":{"draws":16,"losses":44,"wins":4},"claude-opus-5":{"draws":3,"losses":107,"wins":6},"claude-opus-5-5":{"draws":6,"losses":74,"wins":0},"claude-sonnet-5":{"draws":24,"losses":37,"wins":11},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":12,"wins":17},"deepseek/deepseek-v4-flash":{"draws":25,"losses":51,"wins":32},"deepseek/deepseek-v4-pro":{"draws":17,"losses":37,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":42,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":50,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":29,"wins":5},"elorian/glimpse":{"draws":6,"losses":7,"wins":7},"fireworks/ember-1":{"draws":19,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":20,"losses":41,"wins":11},"gemini-4-argon":{"draws":3,"losses":24,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":13,"wins":27},"google/gemini-3.5-flash":{"draws":24,"losses":49,"wins":17},"google/gemini-3.5-flash-lite":{"draws":32,"losses":58,"wins":38},"google/gemini-3.6-flash":{"draws":25,"losses":96,"wins":17},"google/gemini-3.8-flash":{"draws":13,"losses":52,"wins":7},"google/gemma-4-31b-it":{"draws":17,"losses":16,"wins":11},"gpt-4.1":{"draws":5,"losses":14,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":15,"losses":32,"wins":17},"gpt-5.4":{"draws":18,"losses":37,"wins":15},"gpt-5.4-mini":{"draws":19,"losses":17,"wins":12},"gpt-5.4-nano":{"draws":16,"losses":34,"wins":22},"gpt-5.5":{"draws":18,"losses":43,"wins":5},"gpt-5.6-luna":{"draws":20,"losses":41,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":59,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":41,"wins":8},"gpt-6-astra":{"draws":4,"losses":68,"wins":0},"gpt-6-luna":{"draws":15,"losses":46,"wins":11},"gpt-6-sol":{"draws":7,"losses":61,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":68,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":16,"wins":16},"inception/mercury-3":{"draws":2,"losses":15,"wins":3},"inclusionai/ling-3.0-flash":{"draws":19,"losses":17,"wins":12},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":42,"wins":26},"meta/muse-glimmer-30b":{"draws":25,"losses":23,"wins":14},"meta/muse-spark-1.2":{"draws":11,"losses":46,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":55,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":28,"wins":4},"meta/muse-wonder":{"draws":13,"losses":53,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":17,"wins":11},"minimax/minimax-m3.1-flash":{"draws":17,"losses":22,"wins":11},"mistralai/mistral-large-4-0":{"draws":13,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":22,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":9,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":42,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":28,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":6,"wins":4},"o3":{"draws":10,"losses":76,"wins":20},"openai/gpt-oss-120b":{"draws":19,"losses":23,"wins":24},"poolside/laguna-s-2.1":{"draws":29,"losses":31,"wins":12},"qwen/qwen3.7-max":{"draws":13,"losses":24,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":16,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":46,"wins":9},"qwen/qwen3.8-27b":{"draws":12,"losses":29,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":26,"wins":6},"qwen/qwen3.8-max":{"draws":21,"losses":45,"wins":6},"qwen/qwen3.8-max-0902":{"draws":21,"losses":42,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":21,"wins":5},"stealth/ox-alpha":{"draws":61,"losses":160,"wins":29},"stealth/space-bunny-alpha":{"draws":17,"losses":28,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":27,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":13},"tencent/hy4-preview":{"draws":17,"losses":47,"wins":6},"thinkingmachines/inkling":{"draws":26,"losses":40,"wins":28},"thinkingmachines/inkling-small":{"draws":24,"losses":31,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":13,"losses":50,"wins":9},"x-ai/grok-4.6":{"draws":18,"losses":51,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.5":{"draws":30,"losses":46,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":19,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":31,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":36,"wins":4},"z-ai/glm-5.2":{"draws":57,"losses":70,"wins":17},"z-ai/glm-5.3":{"draws":13,"losses":56,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":49,"wins":9},"z-ai/glm-5.3-flashx":{"draws":14,"losses":53,"wins":5}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":4,"wins":5},"claude-fable-5":{"draws":2,"losses":11,"wins":3},"claude-fable-5-1":{"draws":0,"losses":18,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":6,"wins":2},"claude-opus-4-5":{"draws":5,"losses":10,"wins":5},"claude-opus-4-8":{"draws":1,"losses":16,"wins":1},"claude-opus-5":{"draws":3,"losses":26,"wins":1},"claude-opus-5-5":{"draws":3,"losses":13,"wins":0},"claude-sonnet-5":{"draws":5,"losses":8,"wins":3},"claude-sonnet-5-5":{"draws":3,"losses":9,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":7,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":11,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":23,"wins":2},"elorian/glimpse":{"draws":3,"losses":10,"wins":3},"fireworks/ember-1":{"draws":0,"losses":9,"wins":1},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":4},"gemini-4-argon":{"draws":0,"losses":29,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":8},"google/gemini-3.5-flash-lite":{"draws":8,"losses":7,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":9,"wins":3},"google/gemini-3.8-flash":{"draws":2,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"gpt-4.1":{"draws":4,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":4,"wins":3},"gpt-5.4":{"draws":3,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":9},"gpt-5.5":{"draws":2,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":7,"losses":6,"wins":5},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":6,"losses":8,"wins":2},"gpt-6-sol":{"draws":0,"losses":14,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":15,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":6},"inception/mercury-3":{"draws":6,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":5,"losses":3,"wins":2},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":3,"wins":3},"meta/muse-glimmer-30b":{"draws":0,"losses":6,"wins":4},"meta/muse-spark-1.2":{"draws":4,"losses":9,"wins":3},"meta/muse-spark-1.3":{"draws":3,"losses":11,"wins":4},"meta/muse-spark-open":{"draws":4,"losses":18,"wins":4},"meta/muse-wonder":{"draws":4,"losses":5,"wins":1},"minimax/minimax-m3":{"draws":3,"losses":7,"wins":2},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":5},"mistralai/mistral-large-4-0":{"draws":6,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":4},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":6,"wins":3},"o3":{"draws":3,"losses":9,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":3},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":3},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.8-max-0902":{"draws":7,"losses":5,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":13,"wins":11},"stealth/ox-alpha":{"draws":15,"losses":30,"wins":7},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":3},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":6},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":4,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":6,"wins":5},"thinkingmachines/inkling-small":{"draws":6,"losses":5,"wins":3},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":4,"wins":1},"x-ai/grok-4.6":{"draws":2,"losses":9,"wins":1},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":9,"wins":6},"z-ai/glm-5.3":{"draws":0,"losses":11,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":3},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":4}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":34,"wins":35},"claude-fable-5":{"draws":27,"losses":89,"wins":10},"claude-fable-5-1":{"draws":7,"losses":129,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":66,"wins":26},"claude-opus-4-5":{"draws":79,"losses":99,"wins":30},"claude-opus-4-8":{"draws":27,"losses":77,"wins":18},"claude-opus-5":{"draws":28,"losses":180,"wins":6},"claude-opus-5-5":{"draws":4,"losses":136,"wins":2},"claude-sonnet-5":{"draws":45,"losses":52,"wins":29},"claude-sonnet-5-5":{"draws":22,"losses":82,"wins":22},"cohere/north-mini-code":{"draws":15,"losses":13,"wins":20},"deepseek/deepseek-v4-flash":{"draws":68,"losses":69,"wins":57},"deepseek/deepseek-v4-pro":{"draws":40,"losses":55,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":44,"losses":55,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":58,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":54,"wins":7},"elorian/glimpse":{"draws":10,"losses":24,"wins":6},"fireworks/ember-1":{"draws":49,"losses":59,"wins":18},"gemini-3.1-pro-preview":{"draws":47,"losses":50,"wins":29},"gemini-4-argon":{"draws":1,"losses":60,"wins":1},"google/gemini-3.1-flash-lite":{"draws":26,"losses":22,"wins":42},"google/gemini-3.5-flash":{"draws":49,"losses":78,"wins":33},"google/gemini-3.5-flash-lite":{"draws":83,"losses":69,"wins":68},"google/gemini-3.6-flash":{"draws":77,"losses":127,"wins":34},"google/gemini-3.8-flash":{"draws":35,"losses":82,"wins":9},"google/gemma-4-31b-it":{"draws":40,"losses":18,"wins":18},"gpt-4.1":{"draws":18,"losses":17,"wins":7},"gpt-4.1-nano":{"draws":8,"losses":2,"wins":4},"gpt-5":{"draws":37,"losses":52,"wins":21},"gpt-5.4":{"draws":42,"losses":70,"wins":8},"gpt-5.4-mini":{"draws":39,"losses":24,"wins":21},"gpt-5.4-nano":{"draws":35,"losses":60,"wins":45},"gpt-5.5":{"draws":52,"losses":54,"wins":8},"gpt-5.6-luna":{"draws":51,"losses":42,"wins":33},"gpt-5.6-sol":{"draws":16,"losses":100,"wins":10},"gpt-5.6-terra":{"draws":46,"losses":55,"wins":19},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":42,"losses":59,"wins":25},"gpt-6-sol":{"draws":12,"losses":106,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":112,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":44,"losses":22,"wins":26},"inception/mercury-3":{"draws":15,"losses":20,"wins":9},"inclusionai/ling-3.0-flash":{"draws":45,"losses":21,"wins":26},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":50,"losses":45,"wins":43},"meta/muse-glimmer-30b":{"draws":55,"losses":26,"wins":27},"meta/muse-spark-1.2":{"draws":33,"losses":68,"wins":19},"meta/muse-spark-1.3":{"draws":30,"losses":84,"wins":12},"meta/muse-spark-open":{"draws":12,"losses":34,"wins":6},"meta/muse-wonder":{"draws":36,"losses":82,"wins":8},"minimax/minimax-m3":{"draws":27,"losses":25,"wins":20},"minimax/minimax-m3.1-flash":{"draws":21,"losses":19,"wins":16},"mistralai/mistral-large-4-0":{"draws":28,"losses":32,"wins":18},"mistralai/mistral-medium-3-5":{"draws":37,"losses":12,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":19,"wins":5},"moonshotai/kimi-k3":{"draws":41,"losses":51,"wins":28},"nex-agi/nex-n2-pro":{"draws":22,"losses":12,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":19,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":20,"wins":7},"o3":{"draws":39,"losses":101,"wins":44},"openai/gpt-oss-120b":{"draws":46,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":58,"losses":35,"wins":31},"qwen/qwen3.7-max":{"draws":35,"losses":26,"wins":17},"qwen/qwen3.7-plus":{"draws":23,"losses":23,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":64,"wins":14},"qwen/qwen3.8-27b":{"draws":29,"losses":40,"wins":19},"qwen/qwen3.8-flash":{"draws":39,"losses":31,"wins":14},"qwen/qwen3.8-max":{"draws":48,"losses":56,"wins":22},"qwen/qwen3.8-max-0902":{"draws":49,"losses":65,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":27,"wins":8},"stealth/ox-alpha":{"draws":109,"losses":207,"wins":58},"stealth/space-bunny-alpha":{"draws":41,"losses":32,"wins":25},"stepfun/step-3.7-flash":{"draws":26,"losses":30,"wins":34},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":37,"losses":21,"wins":14},"tencent/hy4-preview":{"draws":42,"losses":64,"wins":14},"thinkingmachines/inkling":{"draws":52,"losses":51,"wins":59},"thinkingmachines/inkling-small":{"draws":59,"losses":32,"wins":35},"unbiased/pareto-26.10":{"draws":2,"losses":34,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":14,"wins":13},"x-ai/grok-4.5":{"draws":30,"losses":85,"wins":11},"x-ai/grok-4.6":{"draws":47,"losses":66,"wins":13},"x-ai/grok-4.7":{"draws":7,"losses":98,"wins":9},"x-ai/grok-build-0.1":{"draws":21,"losses":12,"wins":9},"xiaomi/mimo-v2.5":{"draws":87,"losses":57,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":32,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":56,"wins":10},"z-ai/glm-5.2":{"draws":109,"losses":89,"wins":54},"z-ai/glm-5.3":{"draws":25,"losses":82,"wins":13},"z-ai/glm-5.3-flash":{"draws":31,"losses":61,"wins":34},"z-ai/glm-5.3-flashx":{"draws":31,"losses":74,"wins":21}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":6},"claude-fable-5":{"draws":6,"losses":33,"wins":3},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":14,"wins":10},"claude-opus-4-5":{"draws":23,"losses":16,"wins":19},"claude-opus-4-8":{"draws":9,"losses":21,"wins":6},"claude-opus-5":{"draws":11,"losses":42,"wins":7},"claude-opus-5-5":{"draws":3,"losses":40,"wins":3},"claude-sonnet-5":{"draws":5,"losses":16,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":20,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":13,"losses":14,"wins":19},"deepseek/deepseek-v4-pro":{"draws":12,"losses":12,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":12,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":33,"wins":11},"elorian/glimpse":{"draws":10,"losses":16,"wins":10},"fireworks/ember-1":{"draws":16,"losses":15,"wins":5},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":13},"gemini-4-argon":{"draws":4,"losses":53,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":10,"losses":17,"wins":15},"google/gemini-3.5-flash-lite":{"draws":28,"losses":5,"wins":31},"google/gemini-3.6-flash":{"draws":22,"losses":29,"wins":13},"google/gemini-3.8-flash":{"draws":5,"losses":21,"wins":16},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":4,"losses":7,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":9,"wins":15},"gpt-5.4":{"draws":7,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":6,"losses":16,"wins":22},"gpt-5.5":{"draws":12,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":8,"losses":29,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":12},"gpt-6-astra":{"draws":2,"losses":48,"wins":0},"gpt-6-luna":{"draws":14,"losses":21,"wins":5},"gpt-6-sol":{"draws":3,"losses":16,"wins":1},"gpt-6.1-sol":{"draws":5,"losses":27,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":4,"wins":21},"inception/mercury-3":{"draws":13,"losses":19,"wins":10},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":9},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":7,"wins":17},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":16,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":23,"wins":12},"meta/muse-spark-open":{"draws":9,"losses":38,"wins":11},"meta/muse-wonder":{"draws":5,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":13,"losses":19,"wins":18},"mistralai/mistral-large-4-0":{"draws":11,"losses":13,"wins":8},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":11,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":4,"wins":4},"o3":{"draws":9,"losses":14,"wins":25},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":22},"poolside/laguna-s-2.1":{"draws":13,"losses":10,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":12},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":8},"qwen/qwen3.8-flash":{"draws":10,"losses":8,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":24,"wins":10},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":25,"wins":17},"stealth/ox-alpha":{"draws":38,"losses":54,"wins":26},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":19},"stepfun/step-5-preview":{"draws":0,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":8,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":18,"losses":13,"wins":17},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":10,"losses":20,"wins":6},"x-ai/grok-4.6":{"draws":5,"losses":21,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":10},"z-ai/glm-5.2":{"draws":21,"losses":21,"wins":20},"z-ai/glm-5.3":{"draws":4,"losses":31,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":20,"wins":14},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":8}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":56,"wins":88},"claude-fable-5":{"draws":18,"losses":151,"wins":29},"claude-fable-5-1":{"draws":5,"losses":204,"wins":9},"claude-haiku-5-5":{"draws":32,"losses":101,"wins":61},"claude-opus-4-5":{"draws":47,"losses":184,"wins":95},"claude-opus-4-8":{"draws":27,"losses":108,"wins":55},"claude-opus-5":{"draws":26,"losses":266,"wins":20},"claude-opus-5-5":{"draws":11,"losses":204,"wins":3},"claude-sonnet-5":{"draws":27,"losses":89,"wins":82},"claude-sonnet-5-5":{"draws":17,"losses":135,"wins":46},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":61},"deepseek/deepseek-v4-flash":{"draws":45,"losses":81,"wins":180},"deepseek/deepseek-v4-pro":{"draws":22,"losses":92,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":100,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":96,"wins":63},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":80,"wins":31},"elorian/glimpse":{"draws":6,"losses":26,"wins":20},"fireworks/ember-1":{"draws":40,"losses":110,"wins":48},"gemini-3.1-pro-preview":{"draws":31,"losses":76,"wins":91},"gemini-4-argon":{"draws":0,"losses":81,"wins":5},"google/gemini-3.1-flash-lite":{"draws":23,"losses":11,"wins":124},"google/gemini-3.5-flash":{"draws":36,"losses":137,"wins":85},"google/gemini-3.5-flash-lite":{"draws":58,"losses":97,"wins":201},"google/gemini-3.6-flash":{"draws":54,"losses":206,"wins":124},"google/gemini-3.8-flash":{"draws":23,"losses":131,"wins":44},"google/gemma-4-31b-it":{"draws":26,"losses":21,"wins":71},"gpt-4.1":{"draws":13,"losses":27,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":10},"gpt-5":{"draws":24,"losses":87,"wins":69},"gpt-5.4":{"draws":21,"losses":127,"wins":48},"gpt-5.4-mini":{"draws":26,"losses":35,"wins":71},"gpt-5.4-nano":{"draws":20,"losses":103,"wins":103},"gpt-5.5":{"draws":36,"losses":104,"wins":44},"gpt-5.6-luna":{"draws":40,"losses":70,"wins":88},"gpt-5.6-sol":{"draws":14,"losses":153,"wins":31},"gpt-5.6-terra":{"draws":37,"losses":82,"wins":67},"gpt-6-astra":{"draws":7,"losses":189,"wins":2},"gpt-6-luna":{"draws":34,"losses":100,"wins":64},"gpt-6-sol":{"draws":10,"losses":171,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":186,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":17,"wins":88},"inception/mercury-3":{"draws":8,"losses":31,"wins":15},"inclusionai/ling-3.0-flash":{"draws":29,"losses":21,"wins":90},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":35,"losses":60,"wins":137},"meta/muse-glimmer-30b":{"draws":34,"losses":35,"wins":103},"meta/muse-spark-1.2":{"draws":22,"losses":95,"wins":69},"meta/muse-spark-1.3":{"draws":20,"losses":125,"wins":53},"meta/muse-spark-open":{"draws":11,"losses":69,"wins":24},"meta/muse-wonder":{"draws":13,"losses":151,"wins":34},"minimax/minimax-m3":{"draws":15,"losses":27,"wins":70},"minimax/minimax-m3.1-flash":{"draws":7,"losses":37,"wins":40},"mistralai/mistral-large-4-0":{"draws":28,"losses":53,"wins":39},"mistralai/mistral-medium-3-5":{"draws":25,"losses":14,"wins":71},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":24,"wins":21},"moonshotai/kimi-k3":{"draws":30,"losses":84,"wins":72},"nex-agi/nex-n2-pro":{"draws":10,"losses":20,"wins":76},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":44,"wins":101},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":25,"wins":14},"o3":{"draws":26,"losses":121,"wins":121},"openai/gpt-oss-120b":{"draws":24,"losses":29,"wins":119},"poolside/laguna-s-2.1":{"draws":36,"losses":59,"wins":97},"qwen/qwen3.7-max":{"draws":26,"losses":42,"wins":56},"qwen/qwen3.7-plus":{"draws":13,"losses":29,"wins":68},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":111,"wins":58},"qwen/qwen3.8-27b":{"draws":13,"losses":73,"wins":58},"qwen/qwen3.8-flash":{"draws":24,"losses":61,"wins":47},"qwen/qwen3.8-max":{"draws":37,"losses":98,"wins":63},"qwen/qwen3.8-max-0902":{"draws":35,"losses":99,"wins":64},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":50,"wins":35},"stealth/ox-alpha":{"draws":86,"losses":316,"wins":202},"stealth/space-bunny-alpha":{"draws":26,"losses":56,"wins":78},"stepfun/step-3.7-flash":{"draws":24,"losses":43,"wins":93},"stepfun/step-5-preview":{"draws":8,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":22,"losses":40,"wins":42},"tencent/hy4-preview":{"draws":30,"losses":106,"wins":60},"thinkingmachines/inkling":{"draws":42,"losses":57,"wins":167},"thinkingmachines/inkling-small":{"draws":40,"losses":43,"wins":115},"unbiased/pareto-26.10":{"draws":0,"losses":36,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":63,"wins":3},"upstage/solar-mini4":{"draws":10,"losses":13,"wins":39},"x-ai/grok-4.5":{"draws":21,"losses":120,"wins":57},"x-ai/grok-4.6":{"draws":36,"losses":118,"wins":44},"x-ai/grok-4.7":{"draws":12,"losses":130,"wins":36},"x-ai/grok-build-0.1":{"draws":13,"losses":15,"wins":38},"xiaomi/mimo-v2.5":{"draws":57,"losses":64,"wins":195},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":44,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":74,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":95,"wins":26},"z-ai/glm-5.2":{"draws":73,"losses":150,"wins":173},"z-ai/glm-5.3":{"draws":18,"losses":135,"wins":35},"z-ai/glm-5.3-flash":{"draws":24,"losses":99,"wins":75},"z-ai/glm-5.3-flashx":{"draws":21,"losses":119,"wins":58}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":42,"wins":32},"claude-fable-5":{"draws":29,"losses":86,"wins":11},"claude-fable-5-1":{"draws":5,"losses":137,"wins":0},"claude-haiku-5-5":{"draws":30,"losses":78,"wins":12},"claude-opus-4-5":{"draws":66,"losses":106,"wins":32},"claude-opus-4-8":{"draws":36,"losses":68,"wins":10},"claude-opus-5":{"draws":32,"losses":177,"wins":11},"claude-opus-5-5":{"draws":9,"losses":129,"wins":0},"claude-sonnet-5":{"draws":38,"losses":71,"wins":17},"claude-sonnet-5-5":{"draws":26,"losses":82,"wins":18},"cohere/north-mini-code":{"draws":15,"losses":15,"wins":20},"deepseek/deepseek-v4-flash":{"draws":72,"losses":55,"wins":63},"deepseek/deepseek-v4-pro":{"draws":35,"losses":55,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":51,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":62,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":60,"wins":11},"elorian/glimpse":{"draws":10,"losses":19,"wins":11},"fireworks/ember-1":{"draws":48,"losses":64,"wins":14},"gemini-3.1-pro-preview":{"draws":42,"losses":54,"wins":30},"gemini-4-argon":{"draws":1,"losses":51,"wins":0},"google/gemini-3.1-flash-lite":{"draws":24,"losses":18,"wins":40},"google/gemini-3.5-flash":{"draws":45,"losses":77,"wins":34},"google/gemini-3.5-flash-lite":{"draws":68,"losses":76,"wins":74},"google/gemini-3.6-flash":{"draws":72,"losses":136,"wins":32},"google/gemini-3.8-flash":{"draws":26,"losses":92,"wins":8},"google/gemma-4-31b-it":{"draws":31,"losses":10,"wins":33},"gpt-4.1":{"draws":13,"losses":20,"wins":9},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":4},"gpt-5":{"draws":35,"losses":56,"wins":21},"gpt-5.4":{"draws":33,"losses":67,"wins":20},"gpt-5.4-mini":{"draws":32,"losses":31,"wins":21},"gpt-5.4-nano":{"draws":35,"losses":44,"wins":47},"gpt-5.5":{"draws":44,"losses":56,"wins":16},"gpt-5.6-luna":{"draws":57,"losses":42,"wins":27},"gpt-5.6-sol":{"draws":15,"losses":104,"wins":7},"gpt-5.6-terra":{"draws":42,"losses":66,"wins":12},"gpt-6-astra":{"draws":12,"losses":114,"wins":0},"gpt-6-luna":{"draws":41,"losses":58,"wins":27},"gpt-6-sol":{"draws":19,"losses":101,"wins":6},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":38,"losses":21,"wins":29},"inception/mercury-3":{"draws":16,"losses":17,"wins":9},"inclusionai/ling-3.0-flash":{"draws":38,"losses":8,"wins":40},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":43,"losses":57,"wins":38},"meta/muse-glimmer-30b":{"draws":47,"losses":27,"wins":38},"meta/muse-spark-1.2":{"draws":32,"losses":76,"wins":14},"meta/muse-spark-1.3":{"draws":32,"losses":82,"wins":12},"meta/muse-spark-open":{"draws":4,"losses":32,"wins":4},"meta/muse-wonder":{"draws":23,"losses":93,"wins":10},"minimax/minimax-m3":{"draws":22,"losses":21,"wins":27},"minimax/minimax-m3.1-flash":{"draws":19,"losses":27,"wins":10},"mistralai/mistral-large-4-0":{"draws":31,"losses":35,"wins":14},"mistralai/mistral-medium-3-5":{"draws":34,"losses":14,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":6},"moonshotai/kimi-k3":{"draws":35,"losses":68,"wins":19},"nex-agi/nex-n2-pro":{"draws":19,"losses":24,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":28,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":22,"wins":7},"o3":{"draws":24,"losses":119,"wins":29},"openai/gpt-oss-120b":{"draws":22,"losses":25,"wins":25},"poolside/laguna-s-2.1":{"draws":49,"losses":41,"wins":36},"qwen/qwen3.7-max":{"draws":29,"losses":31,"wins":14},"qwen/qwen3.7-plus":{"draws":21,"losses":21,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":72,"wins":12},"qwen/qwen3.8-27b":{"draws":22,"losses":46,"wins":18},"qwen/qwen3.8-flash":{"draws":27,"losses":34,"wins":23},"qwen/qwen3.8-max":{"draws":41,"losses":75,"wins":10},"qwen/qwen3.8-max-0902":{"draws":39,"losses":72,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":29,"wins":6},"stealth/ox-alpha":{"draws":110,"losses":256,"wins":58},"stealth/space-bunny-alpha":{"draws":33,"losses":44,"wins":23},"stepfun/step-3.7-flash":{"draws":29,"losses":36,"wins":23},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":27,"wins":19},"tencent/hy4-preview":{"draws":38,"losses":64,"wins":18},"thinkingmachines/inkling":{"draws":47,"losses":65,"wins":56},"thinkingmachines/inkling-small":{"draws":48,"losses":31,"wins":47},"unbiased/pareto-26.10":{"draws":0,"losses":22,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":11},"x-ai/grok-4.5":{"draws":34,"losses":79,"wins":13},"x-ai/grok-4.6":{"draws":37,"losses":79,"wins":10},"x-ai/grok-4.7":{"draws":9,"losses":99,"wins":4},"x-ai/grok-build-0.1":{"draws":17,"losses":16,"wins":9},"xiaomi/mimo-v2.5":{"draws":66,"losses":54,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":27,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":53,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":62,"wins":6},"z-ai/glm-5.2":{"draws":95,"losses":108,"wins":49},"z-ai/glm-5.3":{"draws":31,"losses":87,"wins":4},"z-ai/glm-5.3-flash":{"draws":27,"losses":79,"wins":20},"z-ai/glm-5.3-flashx":{"draws":37,"losses":76,"wins":13}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":51,"losses":38,"wins":39},"claude-fable-5":{"draws":27,"losses":90,"wins":21},"claude-fable-5-1":{"draws":5,"losses":145,"wins":2},"claude-haiku-5-5":{"draws":34,"losses":61,"wins":35},"claude-opus-4-5":{"draws":79,"losses":105,"wins":38},"claude-opus-4-8":{"draws":37,"losses":69,"wins":16},"claude-opus-5":{"draws":25,"losses":209,"wins":14},"claude-opus-5-5":{"draws":10,"losses":144,"wins":0},"claude-sonnet-5":{"draws":43,"losses":69,"wins":26},"claude-sonnet-5-5":{"draws":25,"losses":87,"wins":26},"cohere/north-mini-code":{"draws":13,"losses":23,"wins":18},"deepseek/deepseek-v4-flash":{"draws":77,"losses":61,"wins":72},"deepseek/deepseek-v4-pro":{"draws":36,"losses":49,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":53,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":59,"losses":57,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":60,"wins":8},"elorian/glimpse":{"draws":5,"losses":21,"wins":8},"fireworks/ember-1":{"draws":52,"losses":64,"wins":22},"gemini-3.1-pro-preview":{"draws":47,"losses":59,"wins":32},"gemini-4-argon":{"draws":4,"losses":57,"wins":3},"google/gemini-3.1-flash-lite":{"draws":26,"losses":16,"wins":44},"google/gemini-3.5-flash":{"draws":43,"losses":93,"wins":34},"google/gemini-3.5-flash-lite":{"draws":75,"losses":66,"wins":97},"google/gemini-3.6-flash":{"draws":79,"losses":135,"wins":48},"google/gemini-3.8-flash":{"draws":28,"losses":93,"wins":17},"google/gemma-4-31b-it":{"draws":33,"losses":20,"wins":25},"gpt-4.1":{"draws":16,"losses":17,"wins":13},"gpt-4.1-nano":{"draws":13,"losses":3,"wins":2},"gpt-5":{"draws":43,"losses":47,"wins":36},"gpt-5.4":{"draws":36,"losses":81,"wins":15},"gpt-5.4-mini":{"draws":39,"losses":31,"wins":22},"gpt-5.4-nano":{"draws":40,"losses":50,"wins":54},"gpt-5.5":{"draws":52,"losses":55,"wins":21},"gpt-5.6-luna":{"draws":51,"losses":46,"wins":41},"gpt-5.6-sol":{"draws":19,"losses":111,"wins":8},"gpt-5.6-terra":{"draws":52,"losses":62,"wins":16},"gpt-6-astra":{"draws":7,"losses":131,"wins":0},"gpt-6-luna":{"draws":45,"losses":59,"wins":34},"gpt-6-sol":{"draws":22,"losses":105,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":128,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":22,"wins":28},"inception/mercury-3":{"draws":22,"losses":21,"wins":7},"inclusionai/ling-3.0-flash":{"draws":45,"losses":13,"wins":36},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":51,"losses":46,"wins":53},"meta/muse-glimmer-30b":{"draws":54,"losses":29,"wins":41},"meta/muse-spark-1.2":{"draws":29,"losses":86,"wins":19},"meta/muse-spark-1.3":{"draws":31,"losses":81,"wins":26},"meta/muse-spark-open":{"draws":21,"losses":42,"wins":5},"meta/muse-wonder":{"draws":22,"losses":105,"wins":11},"minimax/minimax-m3":{"draws":26,"losses":22,"wins":30},"minimax/minimax-m3.1-flash":{"draws":17,"losses":30,"wins":19},"mistralai/mistral-large-4-0":{"draws":32,"losses":36,"wins":20},"mistralai/mistral-medium-3-5":{"draws":35,"losses":15,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":47,"losses":65,"wins":22},"nex-agi/nex-n2-pro":{"draws":29,"losses":12,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":58,"losses":31,"wins":35},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":23,"wins":10},"o3":{"draws":36,"losses":97,"wins":59},"openai/gpt-oss-120b":{"draws":49,"losses":36,"wins":41},"poolside/laguna-s-2.1":{"draws":48,"losses":28,"wins":28},"qwen/qwen3.7-max":{"draws":33,"losses":29,"wins":20},"qwen/qwen3.7-plus":{"draws":24,"losses":13,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":78,"wins":15},"qwen/qwen3.8-27b":{"draws":28,"losses":44,"wins":22},"qwen/qwen3.8-flash":{"draws":40,"losses":33,"wins":19},"qwen/qwen3.8-max":{"draws":48,"losses":57,"wins":33},"qwen/qwen3.8-max-0902":{"draws":45,"losses":70,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":26,"wins":9},"stealth/ox-alpha":{"draws":130,"losses":263,"wins":85},"stealth/space-bunny-alpha":{"draws":33,"losses":40,"wins":33},"stepfun/step-3.7-flash":{"draws":31,"losses":30,"wins":37},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":26,"wins":22},"tencent/hy4-preview":{"draws":42,"losses":66,"wins":24},"thinkingmachines/inkling":{"draws":58,"losses":55,"wins":75},"thinkingmachines/inkling-small":{"draws":59,"losses":20,"wins":59},"unbiased/pareto-26.10":{"draws":1,"losses":37,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":14,"wins":8},"x-ai/grok-4.5":{"draws":35,"losses":84,"wins":19},"x-ai/grok-4.6":{"draws":39,"losses":84,"wins":15},"x-ai/grok-4.7":{"draws":11,"losses":99,"wins":14},"x-ai/grok-build-0.1":{"draws":21,"losses":14,"wins":11},"xiaomi/mimo-v2.5":{"draws":66,"losses":57,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":25,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":51,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":64,"wins":18},"z-ai/glm-5.2":{"draws":119,"losses":92,"wins":65},"z-ai/glm-5.3":{"draws":25,"losses":92,"wins":15},"z-ai/glm-5.3-flash":{"draws":33,"losses":76,"wins":29},"z-ai/glm-5.3-flashx":{"draws":40,"losses":75,"wins":23}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":23,"wins":27},"claude-fable-5":{"draws":15,"losses":56,"wins":13},"claude-fable-5-1":{"draws":3,"losses":88,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":35,"wins":20},"claude-opus-4-5":{"draws":44,"losses":62,"wins":32},"claude-opus-4-8":{"draws":24,"losses":35,"wins":21},"claude-opus-5":{"draws":17,"losses":111,"wins":12},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":27,"losses":40,"wins":17},"claude-sonnet-5-5":{"draws":18,"losses":44,"wins":22},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":54,"losses":28,"wins":48},"deepseek/deepseek-v4-pro":{"draws":25,"losses":36,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":35,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":28,"wins":7},"elorian/glimpse":{"draws":4,"losses":11,"wins":11},"fireworks/ember-1":{"draws":26,"losses":39,"wins":19},"gemini-3.1-pro-preview":{"draws":26,"losses":29,"wins":29},"gemini-4-argon":{"draws":2,"losses":41,"wins":5},"google/gemini-3.1-flash-lite":{"draws":19,"losses":7,"wins":34},"google/gemini-3.5-flash":{"draws":32,"losses":41,"wins":33},"google/gemini-3.5-flash-lite":{"draws":41,"losses":42,"wins":63},"google/gemini-3.6-flash":{"draws":47,"losses":75,"wins":38},"google/gemini-3.8-flash":{"draws":27,"losses":37,"wins":20},"google/gemma-4-31b-it":{"draws":17,"losses":13,"wins":20},"gpt-4.1":{"draws":13,"losses":5,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":31,"losses":28,"wins":15},"gpt-5.4":{"draws":18,"losses":43,"wins":19},"gpt-5.4-mini":{"draws":19,"losses":15,"wins":22},"gpt-5.4-nano":{"draws":27,"losses":29,"wins":36},"gpt-5.5":{"draws":27,"losses":35,"wins":14},"gpt-5.6-luna":{"draws":31,"losses":21,"wins":32},"gpt-5.6-sol":{"draws":11,"losses":59,"wins":14},"gpt-5.6-terra":{"draws":24,"losses":40,"wins":16},"gpt-6-astra":{"draws":6,"losses":77,"wins":1},"gpt-6-luna":{"draws":22,"losses":35,"wins":27},"gpt-6-sol":{"draws":16,"losses":58,"wins":10},"gpt-6.1-sol":{"draws":7,"losses":75,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":23},"inception/mercury-3":{"draws":8,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":29,"losses":7,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":18,"wins":44},"meta/muse-glimmer-30b":{"draws":29,"losses":16,"wins":27},"meta/muse-spark-1.2":{"draws":11,"losses":50,"wins":19},"meta/muse-spark-1.3":{"draws":18,"losses":47,"wins":19},"meta/muse-spark-open":{"draws":7,"losses":25,"wins":8},"meta/muse-wonder":{"draws":11,"losses":61,"wins":12},"minimax/minimax-m3":{"draws":17,"losses":8,"wins":23},"minimax/minimax-m3.1-flash":{"draws":6,"losses":19,"wins":17},"mistralai/mistral-large-4-0":{"draws":21,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":24,"losses":4,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":9,"wins":9},"moonshotai/kimi-k3":{"draws":19,"losses":41,"wins":20},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":17,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":9},"o3":{"draws":26,"losses":56,"wins":42},"openai/gpt-oss-120b":{"draws":29,"losses":14,"wins":31},"poolside/laguna-s-2.1":{"draws":33,"losses":20,"wins":29},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":13,"losses":12,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":38,"wins":17},"qwen/qwen3.8-27b":{"draws":16,"losses":26,"wins":18},"qwen/qwen3.8-flash":{"draws":20,"losses":20,"wins":16},"qwen/qwen3.8-max":{"draws":31,"losses":30,"wins":23},"qwen/qwen3.8-max-0902":{"draws":26,"losses":41,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":20,"wins":12},"stealth/ox-alpha":{"draws":64,"losses":136,"wins":58},"stealth/space-bunny-alpha":{"draws":21,"losses":22,"wins":23},"stepfun/step-3.7-flash":{"draws":16,"losses":12,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":17},"tencent/hy4-preview":{"draws":18,"losses":44,"wins":18},"thinkingmachines/inkling":{"draws":34,"losses":17,"wins":59},"thinkingmachines/inkling-small":{"draws":32,"losses":16,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":19,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":14},"x-ai/grok-4.5":{"draws":21,"losses":44,"wins":19},"x-ai/grok-4.6":{"draws":21,"losses":47,"wins":16},"x-ai/grok-4.7":{"draws":10,"losses":51,"wins":15},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":9},"xiaomi/mimo-v2.5":{"draws":53,"losses":27,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":11,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":28,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":55,"losses":60,"wins":53},"z-ai/glm-5.3":{"draws":19,"losses":48,"wins":13},"z-ai/glm-5.3-flash":{"draws":25,"losses":41,"wins":18},"z-ai/glm-5.3-flashx":{"draws":22,"losses":42,"wins":20}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":22,"wins":20},"claude-fable-5":{"draws":14,"losses":50,"wins":8},"claude-fable-5-1":{"draws":5,"losses":72,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":50,"wins":8},"claude-opus-4-5":{"draws":40,"losses":52,"wins":28},"claude-opus-4-8":{"draws":16,"losses":43,"wins":13},"claude-opus-5":{"draws":16,"losses":92,"wins":8},"claude-opus-5-5":{"draws":5,"losses":71,"wins":0},"claude-sonnet-5":{"draws":20,"losses":35,"wins":17},"claude-sonnet-5-5":{"draws":16,"losses":43,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":14},"deepseek/deepseek-v4-flash":{"draws":33,"losses":43,"wins":36},"deepseek/deepseek-v4-pro":{"draws":16,"losses":35,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":27,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":40,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":28,"wins":9},"elorian/glimpse":{"draws":6,"losses":13,"wins":5},"fireworks/ember-1":{"draws":23,"losses":38,"wins":11},"gemini-3.1-pro-preview":{"draws":23,"losses":35,"wins":14},"gemini-4-argon":{"draws":1,"losses":39,"wins":0},"google/gemini-3.1-flash-lite":{"draws":13,"losses":13,"wins":30},"google/gemini-3.5-flash":{"draws":22,"losses":51,"wins":19},"google/gemini-3.5-flash-lite":{"draws":35,"losses":51,"wins":40},"google/gemini-3.6-flash":{"draws":39,"losses":77,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":48,"wins":7},"google/gemma-4-31b-it":{"draws":16,"losses":13,"wins":15},"gpt-4.1":{"draws":8,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":16,"losses":36,"wins":10},"gpt-5.4":{"draws":12,"losses":49,"wins":7},"gpt-5.4-mini":{"draws":16,"losses":14,"wins":18},"gpt-5.4-nano":{"draws":19,"losses":33,"wins":30},"gpt-5.5":{"draws":26,"losses":32,"wins":6},"gpt-5.6-luna":{"draws":26,"losses":28,"wins":18},"gpt-5.6-sol":{"draws":13,"losses":52,"wins":7},"gpt-5.6-terra":{"draws":27,"losses":30,"wins":11},"gpt-6-astra":{"draws":3,"losses":69,"wins":0},"gpt-6-luna":{"draws":25,"losses":35,"wins":12},"gpt-6-sol":{"draws":10,"losses":55,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":66,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":10,"wins":22},"inception/mercury-3":{"draws":12,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":20,"losses":14,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":32,"wins":29},"meta/muse-glimmer-30b":{"draws":25,"losses":20,"wins":15},"meta/muse-spark-1.2":{"draws":16,"losses":40,"wins":12},"meta/muse-spark-1.3":{"draws":15,"losses":44,"wins":13},"meta/muse-spark-open":{"draws":9,"losses":26,"wins":5},"meta/muse-wonder":{"draws":15,"losses":55,"wins":2},"minimax/minimax-m3":{"draws":12,"losses":14,"wins":16},"minimax/minimax-m3.1-flash":{"draws":7,"losses":23,"wins":12},"mistralai/mistral-large-4-0":{"draws":13,"losses":29,"wins":2},"mistralai/mistral-medium-3-5":{"draws":17,"losses":10,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":28,"wins":15},"nex-agi/nex-n2-pro":{"draws":9,"losses":9,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":22,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":2},"o3":{"draws":13,"losses":68,"wins":29},"openai/gpt-oss-120b":{"draws":21,"losses":20,"wins":21},"poolside/laguna-s-2.1":{"draws":24,"losses":29,"wins":13},"qwen/qwen3.7-max":{"draws":13,"losses":21,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":35,"wins":9},"qwen/qwen3.8-27b":{"draws":11,"losses":28,"wins":15},"qwen/qwen3.8-flash":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max":{"draws":27,"losses":29,"wins":16},"qwen/qwen3.8-max-0902":{"draws":26,"losses":37,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":6},"stealth/ox-alpha":{"draws":45,"losses":130,"wins":27},"stealth/space-bunny-alpha":{"draws":16,"losses":31,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":21,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":16,"losses":41,"wins":11},"thinkingmachines/inkling":{"draws":27,"losses":29,"wins":38},"thinkingmachines/inkling-small":{"draws":28,"losses":24,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":17,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":2},"upstage/solar-mini4":{"draws":3,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":18,"losses":46,"wins":8},"x-ai/grok-4.6":{"draws":21,"losses":45,"wins":6},"x-ai/grok-4.7":{"draws":7,"losses":52,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":42,"losses":37,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":22,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":29,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":45,"losses":68,"wins":31},"z-ai/glm-5.3":{"draws":15,"losses":46,"wins":6},"z-ai/glm-5.3-flash":{"draws":17,"losses":43,"wins":12},"z-ai/glm-5.3-flashx":{"draws":17,"losses":45,"wins":10}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":25,"wins":66},"claude-fable-5":{"draws":36,"losses":74,"wins":34},"claude-fable-5-1":{"draws":11,"losses":145,"wins":6},"claude-haiku-5-5":{"draws":36,"losses":55,"wins":47},"claude-opus-4-5":{"draws":87,"losses":59,"wins":88},"claude-opus-4-8":{"draws":38,"losses":44,"wins":50},"claude-opus-5":{"draws":32,"losses":174,"wins":40},"claude-opus-5-5":{"draws":11,"losses":127,"wins":18},"claude-sonnet-5":{"draws":45,"losses":37,"wins":62},"claude-sonnet-5-5":{"draws":31,"losses":62,"wins":51},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":45},"deepseek/deepseek-v4-flash":{"draws":69,"losses":32,"wins":115},"deepseek/deepseek-v4-pro":{"draws":36,"losses":36,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":43,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":57,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":46,"wins":25},"elorian/glimpse":{"draws":5,"losses":18,"wins":13},"fireworks/ember-1":{"draws":50,"losses":47,"wins":47},"gemini-3.1-pro-preview":{"draws":36,"losses":45,"wins":63},"gemini-4-argon":{"draws":4,"losses":52,"wins":8},"google/gemini-3.1-flash-lite":{"draws":25,"losses":3,"wins":68},"google/gemini-3.5-flash":{"draws":48,"losses":56,"wins":76},"google/gemini-3.5-flash-lite":{"draws":80,"losses":42,"wins":130},"google/gemini-3.6-flash":{"draws":73,"losses":108,"wins":95},"google/gemini-3.8-flash":{"draws":35,"losses":68,"wins":41},"google/gemma-4-31b-it":{"draws":29,"losses":10,"wins":45},"gpt-4.1":{"draws":18,"losses":6,"wins":24},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":37,"losses":33,"wins":56},"gpt-5.4":{"draws":29,"losses":56,"wins":53},"gpt-5.4-mini":{"draws":34,"losses":13,"wins":49},"gpt-5.4-nano":{"draws":37,"losses":28,"wins":79},"gpt-5.5":{"draws":40,"losses":47,"wins":45},"gpt-5.6-luna":{"draws":51,"losses":27,"wins":66},"gpt-5.6-sol":{"draws":23,"losses":84,"wins":37},"gpt-5.6-terra":{"draws":49,"losses":29,"wins":60},"gpt-6-astra":{"draws":5,"losses":133,"wins":6},"gpt-6-luna":{"draws":37,"losses":48,"wins":59},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":11,"losses":113,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":6,"wins":56},"inception/mercury-3":{"draws":19,"losses":13,"wins":14},"inclusionai/ling-3.0-flash":{"draws":41,"losses":4,"wins":57},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":42,"losses":23,"wins":91},"meta/muse-glimmer-30b":{"draws":47,"losses":15,"wins":64},"meta/muse-spark-1.2":{"draws":36,"losses":48,"wins":54},"meta/muse-spark-1.3":{"draws":34,"losses":59,"wins":51},"meta/muse-spark-open":{"draws":13,"losses":31,"wins":20},"meta/muse-wonder":{"draws":27,"losses":73,"wins":44},"minimax/minimax-m3":{"draws":20,"losses":8,"wins":50},"minimax/minimax-m3.1-flash":{"draws":22,"losses":14,"wins":30},"mistralai/mistral-large-4-0":{"draws":22,"losses":26,"wins":42},"mistralai/mistral-medium-3-5":{"draws":25,"losses":3,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":9,"wins":16},"moonshotai/kimi-k3":{"draws":38,"losses":50,"wins":50},"nex-agi/nex-n2-pro":{"draws":17,"losses":9,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":14,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":12,"wins":18},"o3":{"draws":29,"losses":58,"wins":111},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":72},"poolside/laguna-s-2.1":{"draws":45,"losses":15,"wins":78},"qwen/qwen3.7-max":{"draws":29,"losses":17,"wins":38},"qwen/qwen3.7-plus":{"draws":28,"losses":9,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":35,"wins":35},"qwen/qwen3.8-27b":{"draws":40,"losses":26,"wins":36},"qwen/qwen3.8-flash":{"draws":27,"losses":30,"wins":39},"qwen/qwen3.8-max":{"draws":45,"losses":49,"wins":50},"qwen/qwen3.8-max-0902":{"draws":47,"losses":53,"wins":44},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":16,"wins":37},"stealth/ox-alpha":{"draws":122,"losses":176,"wins":176},"stealth/space-bunny-alpha":{"draws":40,"losses":27,"wins":47},"stepfun/step-3.7-flash":{"draws":16,"losses":15,"wins":71},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":28,"losses":16,"wins":34},"tencent/hy4-preview":{"draws":40,"losses":52,"wins":46},"thinkingmachines/inkling":{"draws":59,"losses":25,"wins":108},"thinkingmachines/inkling-small":{"draws":47,"losses":17,"wins":80},"unbiased/pareto-26.10":{"draws":4,"losses":24,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":34,"losses":62,"wins":48},"x-ai/grok-4.6":{"draws":34,"losses":61,"wins":49},"x-ai/grok-4.7":{"draws":10,"losses":86,"wins":30},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":88,"losses":25,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":19,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":41,"wins":31},"z-ai/glm-5.2":{"draws":105,"losses":70,"wins":113},"z-ai/glm-5.3":{"draws":27,"losses":83,"wins":28},"z-ai/glm-5.3-flash":{"draws":31,"losses":65,"wins":48},"z-ai/glm-5.3-flashx":{"draws":38,"losses":61,"wins":45}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":23,"wins":48},"claude-fable-5":{"draws":20,"losses":66,"wins":16},"claude-fable-5-1":{"draws":6,"losses":107,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":47,"wins":29},"claude-opus-4-5":{"draws":51,"losses":48,"wins":67},"claude-opus-4-8":{"draws":20,"losses":43,"wins":31},"claude-opus-5":{"draws":28,"losses":125,"wins":13},"claude-opus-5-5":{"draws":5,"losses":98,"wins":3},"claude-sonnet-5":{"draws":26,"losses":38,"wins":38},"claude-sonnet-5-5":{"draws":17,"losses":60,"wins":25},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":25},"deepseek/deepseek-v4-flash":{"draws":38,"losses":35,"wins":81},"deepseek/deepseek-v4-pro":{"draws":26,"losses":31,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":30,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":49,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":15},"elorian/glimpse":{"draws":7,"losses":13,"wins":14},"fireworks/ember-1":{"draws":29,"losses":35,"wins":38},"gemini-3.1-pro-preview":{"draws":23,"losses":32,"wins":47},"gemini-4-argon":{"draws":7,"losses":37,"wins":4},"google/gemini-3.1-flash-lite":{"draws":14,"losses":11,"wins":45},"google/gemini-3.5-flash":{"draws":22,"losses":57,"wins":49},"google/gemini-3.5-flash-lite":{"draws":36,"losses":43,"wins":101},"google/gemini-3.6-flash":{"draws":44,"losses":90,"wins":64},"google/gemini-3.8-flash":{"draws":16,"losses":64,"wins":22},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":29},"gpt-4.1":{"draws":9,"losses":11,"wins":14},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":6},"gpt-5":{"draws":17,"losses":30,"wins":41},"gpt-5.4":{"draws":22,"losses":56,"wins":20},"gpt-5.4-mini":{"draws":17,"losses":19,"wins":32},"gpt-5.4-nano":{"draws":22,"losses":34,"wins":48},"gpt-5.5":{"draws":29,"losses":37,"wins":26},"gpt-5.6-luna":{"draws":32,"losses":25,"wins":45},"gpt-5.6-sol":{"draws":16,"losses":68,"wins":18},"gpt-5.6-terra":{"draws":36,"losses":33,"wins":29},"gpt-6-astra":{"draws":4,"losses":97,"wins":1},"gpt-6-luna":{"draws":26,"losses":41,"wins":35},"gpt-6-sol":{"draws":17,"losses":71,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":91,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":7,"wins":43},"inception/mercury-3":{"draws":15,"losses":14,"wins":15},"inclusionai/ling-3.0-flash":{"draws":15,"losses":13,"wins":46},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":22,"losses":18,"wins":68},"meta/muse-glimmer-30b":{"draws":25,"losses":14,"wins":47},"meta/muse-spark-1.2":{"draws":21,"losses":36,"wins":39},"meta/muse-spark-1.3":{"draws":19,"losses":52,"wins":31},"meta/muse-spark-open":{"draws":9,"losses":33,"wins":16},"meta/muse-wonder":{"draws":19,"losses":69,"wins":14},"minimax/minimax-m3":{"draws":14,"losses":8,"wins":32},"minimax/minimax-m3.1-flash":{"draws":11,"losses":21,"wins":10},"mistralai/mistral-large-4-0":{"draws":19,"losses":22,"wins":21},"mistralai/mistral-medium-3-5":{"draws":20,"losses":4,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k3":{"draws":28,"losses":41,"wins":27},"nex-agi/nex-n2-pro":{"draws":12,"losses":7,"wins":29},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":19,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":8,"wins":12},"o3":{"draws":13,"losses":58,"wins":73},"openai/gpt-oss-120b":{"draws":22,"losses":18,"wins":46},"poolside/laguna-s-2.1":{"draws":28,"losses":22,"wins":44},"qwen/qwen3.7-max":{"draws":16,"losses":18,"wins":26},"qwen/qwen3.7-plus":{"draws":11,"losses":15,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":36,"wins":26},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":18,"losses":28,"wins":22},"qwen/qwen3.8-max":{"draws":33,"losses":34,"wins":35},"qwen/qwen3.8-max-0902":{"draws":26,"losses":49,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":14,"wins":10},"stealth/ox-alpha":{"draws":74,"losses":151,"wins":107},"stealth/space-bunny-alpha":{"draws":21,"losses":20,"wins":39},"stepfun/step-3.7-flash":{"draws":12,"losses":26,"wins":38},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":15,"losses":13,"wins":26},"tencent/hy4-preview":{"draws":26,"losses":45,"wins":27},"thinkingmachines/inkling":{"draws":37,"losses":30,"wins":71},"thinkingmachines/inkling-small":{"draws":30,"losses":16,"wins":56},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":34,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":24,"losses":53,"wins":25},"x-ai/grok-4.6":{"draws":27,"losses":52,"wins":23},"x-ai/grok-4.7":{"draws":11,"losses":58,"wins":19},"x-ai/grok-build-0.1":{"draws":13,"losses":1,"wins":20},"xiaomi/mimo-v2.5":{"draws":44,"losses":29,"wins":87},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":26,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":36,"wins":20},"z-ai/glm-5.2":{"draws":66,"losses":70,"wins":68},"z-ai/glm-5.3":{"draws":26,"losses":58,"wins":12},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":32},"z-ai/glm-5.3-flashx":{"draws":24,"losses":53,"wins":25}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":19,"wins":39},"claude-fable-5":{"draws":23,"losses":55,"wins":18},"claude-fable-5-1":{"draws":6,"losses":97,"wins":5},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":19},"claude-opus-4-5":{"draws":57,"losses":53,"wins":46},"claude-opus-4-8":{"draws":31,"losses":41,"wins":16},"claude-opus-5":{"draws":23,"losses":127,"wins":14},"claude-opus-5-5":{"draws":10,"losses":91,"wins":3},"claude-sonnet-5":{"draws":32,"losses":33,"wins":31},"claude-sonnet-5-5":{"draws":17,"losses":49,"wins":30},"cohere/north-mini-code":{"draws":7,"losses":11,"wins":18},"deepseek/deepseek-v4-flash":{"draws":46,"losses":30,"wins":68},"deepseek/deepseek-v4-pro":{"draws":22,"losses":30,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":31,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":41,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":38,"wins":15},"elorian/glimpse":{"draws":5,"losses":11,"wins":12},"fireworks/ember-1":{"draws":34,"losses":33,"wins":29},"gemini-3.1-pro-preview":{"draws":36,"losses":30,"wins":30},"gemini-4-argon":{"draws":5,"losses":24,"wins":9},"google/gemini-3.1-flash-lite":{"draws":21,"losses":10,"wins":33},"google/gemini-3.5-flash":{"draws":37,"losses":48,"wins":35},"google/gemini-3.5-flash-lite":{"draws":55,"losses":30,"wins":83},"google/gemini-3.6-flash":{"draws":60,"losses":79,"wins":45},"google/gemini-3.8-flash":{"draws":23,"losses":47,"wins":26},"google/gemma-4-31b-it":{"draws":27,"losses":6,"wins":23},"gpt-4.1":{"draws":11,"losses":5,"wins":16},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":7},"gpt-5":{"draws":21,"losses":31,"wins":32},"gpt-5.4":{"draws":21,"losses":43,"wins":28},"gpt-5.4-mini":{"draws":25,"losses":14,"wins":25},"gpt-5.4-nano":{"draws":25,"losses":26,"wins":45},"gpt-5.5":{"draws":34,"losses":36,"wins":18},"gpt-5.6-luna":{"draws":31,"losses":28,"wins":37},"gpt-5.6-sol":{"draws":17,"losses":61,"wins":18},"gpt-5.6-terra":{"draws":30,"losses":33,"wins":29},"gpt-6-astra":{"draws":13,"losses":80,"wins":3},"gpt-6-luna":{"draws":28,"losses":35,"wins":33},"gpt-6-sol":{"draws":9,"losses":69,"wins":18},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":31,"losses":6,"wins":31},"inception/mercury-3":{"draws":12,"losses":13,"wins":7},"inclusionai/ling-3.0-flash":{"draws":27,"losses":5,"wins":36},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":23,"wins":47},"meta/muse-glimmer-30b":{"draws":37,"losses":21,"wins":26},"meta/muse-spark-1.2":{"draws":22,"losses":42,"wins":28},"meta/muse-spark-1.3":{"draws":23,"losses":47,"wins":26},"meta/muse-spark-open":{"draws":13,"losses":19,"wins":20},"meta/muse-wonder":{"draws":24,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":16,"wins":23},"minimax/minimax-m3.1-flash":{"draws":12,"losses":10,"wins":20},"mistralai/mistral-large-4-0":{"draws":22,"losses":21,"wins":17},"mistralai/mistral-medium-3-5":{"draws":22,"losses":5,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":30,"losses":33,"wins":29},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":14,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":6,"wins":8},"o3":{"draws":24,"losses":47,"wins":61},"openai/gpt-oss-120b":{"draws":27,"losses":23,"wins":34},"poolside/laguna-s-2.1":{"draws":40,"losses":19,"wins":33},"qwen/qwen3.7-max":{"draws":20,"losses":16,"wins":20},"qwen/qwen3.7-plus":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":39,"wins":30},"qwen/qwen3.8-27b":{"draws":18,"losses":22,"wins":28},"qwen/qwen3.8-flash":{"draws":18,"losses":7,"wins":7},"qwen/qwen3.8-max":{"draws":33,"losses":37,"wins":26},"qwen/qwen3.8-max-0902":{"draws":33,"losses":34,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":18,"wins":16},"stealth/ox-alpha":{"draws":93,"losses":124,"wins":99},"stealth/space-bunny-alpha":{"draws":28,"losses":18,"wins":30},"stepfun/step-3.7-flash":{"draws":14,"losses":14,"wins":40},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":22},"tencent/hy4-preview":{"draws":26,"losses":40,"wins":26},"thinkingmachines/inkling":{"draws":43,"losses":25,"wins":60},"thinkingmachines/inkling-small":{"draws":42,"losses":18,"wins":36},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":26,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":25,"losses":44,"wins":27},"x-ai/grok-4.6":{"draws":36,"losses":44,"wins":16},"x-ai/grok-4.7":{"draws":8,"losses":63,"wins":13},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":60,"losses":31,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":12,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":22,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":35,"wins":16},"z-ai/glm-5.2":{"draws":71,"losses":54,"wins":67},"z-ai/glm-5.3":{"draws":25,"losses":53,"wins":14},"z-ai/glm-5.3-flash":{"draws":21,"losses":42,"wins":33},"z-ai/glm-5.3-flashx":{"draws":32,"losses":42,"wins":22}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":33,"wins":52},"claude-fable-5":{"draws":27,"losses":80,"wins":37},"claude-fable-5-1":{"draws":8,"losses":151,"wins":3},"claude-haiku-5-5":{"draws":34,"losses":67,"wins":37},"claude-opus-4-5":{"draws":76,"losses":66,"wins":92},"claude-opus-4-8":{"draws":26,"losses":61,"wins":45},"claude-opus-5":{"draws":36,"losses":180,"wins":30},"claude-opus-5-5":{"draws":13,"losses":131,"wins":12},"claude-sonnet-5":{"draws":46,"losses":44,"wins":54},"claude-sonnet-5-5":{"draws":23,"losses":79,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":41},"deepseek/deepseek-v4-flash":{"draws":68,"losses":36,"wins":112},"deepseek/deepseek-v4-pro":{"draws":37,"losses":36,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":39,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":54,"wins":48},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":49,"wins":18},"elorian/glimpse":{"draws":9,"losses":11,"wins":18},"fireworks/ember-1":{"draws":44,"losses":58,"wins":42},"gemini-3.1-pro-preview":{"draws":43,"losses":45,"wins":56},"gemini-4-argon":{"draws":3,"losses":47,"wins":6},"google/gemini-3.1-flash-lite":{"draws":29,"losses":1,"wins":66},"google/gemini-3.5-flash":{"draws":57,"losses":62,"wins":61},"google/gemini-3.5-flash-lite":{"draws":82,"losses":47,"wins":123},"google/gemini-3.6-flash":{"draws":72,"losses":115,"wins":89},"google/gemini-3.8-flash":{"draws":36,"losses":62,"wins":46},"google/gemma-4-31b-it":{"draws":33,"losses":8,"wins":43},"gpt-4.1":{"draws":19,"losses":13,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":1,"wins":7},"gpt-5":{"draws":39,"losses":29,"wins":58},"gpt-5.4":{"draws":38,"losses":51,"wins":49},"gpt-5.4-mini":{"draws":41,"losses":18,"wins":37},"gpt-5.4-nano":{"draws":33,"losses":37,"wins":74},"gpt-5.5":{"draws":44,"losses":48,"wins":40},"gpt-5.6-luna":{"draws":48,"losses":31,"wins":65},"gpt-5.6-sol":{"draws":26,"losses":88,"wins":30},"gpt-5.6-terra":{"draws":58,"losses":36,"wins":44},"gpt-6-astra":{"draws":13,"losses":129,"wins":2},"gpt-6-luna":{"draws":37,"losses":50,"wins":57},"gpt-6-sol":{"draws":17,"losses":99,"wins":28},"gpt-6.1-sol":{"draws":11,"losses":124,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":43,"losses":8,"wins":51},"inception/mercury-3":{"draws":18,"losses":11,"wins":19},"inclusionai/ling-3.0-flash":{"draws":41,"losses":14,"wins":47},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":48,"losses":28,"wins":80},"meta/muse-glimmer-30b":{"draws":41,"losses":24,"wins":61},"meta/muse-spark-1.2":{"draws":35,"losses":51,"wins":52},"meta/muse-spark-1.3":{"draws":33,"losses":71,"wins":40},"meta/muse-spark-open":{"draws":13,"losses":30,"wins":27},"meta/muse-wonder":{"draws":31,"losses":81,"wins":32},"minimax/minimax-m3":{"draws":23,"losses":14,"wins":41},"minimax/minimax-m3.1-flash":{"draws":20,"losses":24,"wins":40},"mistralai/mistral-large-4-0":{"draws":31,"losses":30,"wins":29},"mistralai/mistral-medium-3-5":{"draws":26,"losses":9,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":38,"losses":48,"wins":52},"nex-agi/nex-n2-pro":{"draws":21,"losses":6,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":22,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":10,"wins":24},"o3":{"draws":37,"losses":63,"wins":98},"openai/gpt-oss-120b":{"draws":41,"losses":10,"wins":75},"poolside/laguna-s-2.1":{"draws":48,"losses":33,"wins":57},"qwen/qwen3.7-max":{"draws":31,"losses":23,"wins":30},"qwen/qwen3.7-plus":{"draws":27,"losses":16,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":50,"wins":49},"qwen/qwen3.8-27b":{"draws":33,"losses":35,"wins":34},"qwen/qwen3.8-flash":{"draws":33,"losses":26,"wins":37},"qwen/qwen3.8-max":{"draws":28,"losses":34,"wins":34},"qwen/qwen3.8-max-0902":{"draws":37,"losses":63,"wins":44},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":12,"wins":20},"stealth/ox-alpha":{"draws":126,"losses":191,"wins":157},"stealth/space-bunny-alpha":{"draws":37,"losses":31,"wins":46},"stepfun/step-3.7-flash":{"draws":24,"losses":17,"wins":61},"stepfun/step-5-preview":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":30,"losses":13,"wins":35},"tencent/hy4-preview":{"draws":37,"losses":58,"wins":43},"thinkingmachines/inkling":{"draws":61,"losses":33,"wins":98},"thinkingmachines/inkling-small":{"draws":44,"losses":39,"wins":61},"unbiased/pareto-26.10":{"draws":1,"losses":35,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":44,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":9,"wins":22},"x-ai/grok-4.5":{"draws":32,"losses":65,"wins":47},"x-ai/grok-4.6":{"draws":40,"losses":64,"wins":40},"x-ai/grok-4.7":{"draws":12,"losses":88,"wins":26},"x-ai/grok-build-0.1":{"draws":19,"losses":9,"wins":20},"xiaomi/mimo-v2.5":{"draws":76,"losses":41,"wins":105},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":23,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":38,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":52,"wins":19},"z-ai/glm-5.2":{"draws":97,"losses":77,"wins":114},"z-ai/glm-5.3":{"draws":28,"losses":80,"wins":30},"z-ai/glm-5.3-flash":{"draws":33,"losses":57,"wins":54},"z-ai/glm-5.3-flashx":{"draws":40,"losses":56,"wins":48}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":21,"wins":74},"claude-fable-5":{"draws":29,"losses":81,"wins":34},"claude-fable-5-1":{"draws":6,"losses":141,"wins":15},"claude-haiku-5-5":{"draws":40,"losses":50,"wins":48},"claude-opus-4-5":{"draws":66,"losses":77,"wins":91},"claude-opus-4-8":{"draws":33,"losses":51,"wins":48},"claude-opus-5":{"draws":35,"losses":169,"wins":42},"claude-opus-5-5":{"draws":16,"losses":128,"wins":12},"claude-sonnet-5":{"draws":42,"losses":36,"wins":66},"claude-sonnet-5-5":{"draws":26,"losses":67,"wins":51},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":41},"deepseek/deepseek-v4-flash":{"draws":64,"losses":29,"wins":123},"deepseek/deepseek-v4-pro":{"draws":34,"losses":35,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":39,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":49,"losses":52,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":38,"wins":23},"elorian/glimpse":{"draws":15,"losses":12,"wins":11},"fireworks/ember-1":{"draws":44,"losses":42,"wins":58},"gemini-3.1-pro-preview":{"draws":40,"losses":39,"wins":65},"gemini-4-argon":{"draws":4,"losses":43,"wins":5},"google/gemini-3.1-flash-lite":{"draws":28,"losses":2,"wins":66},"google/gemini-3.5-flash":{"draws":48,"losses":46,"wins":86},"google/gemini-3.5-flash-lite":{"draws":72,"losses":37,"wins":143},"google/gemini-3.6-flash":{"draws":76,"losses":96,"wins":104},"google/gemini-3.8-flash":{"draws":37,"losses":60,"wins":47},"google/gemma-4-31b-it":{"draws":29,"losses":9,"wins":46},"gpt-4.1":{"draws":18,"losses":7,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":36,"losses":31,"wins":59},"gpt-5.4":{"draws":31,"losses":62,"wins":45},"gpt-5.4-mini":{"draws":38,"losses":14,"wins":44},"gpt-5.4-nano":{"draws":37,"losses":35,"wins":72},"gpt-5.5":{"draws":47,"losses":42,"wins":43},"gpt-5.6-luna":{"draws":51,"losses":32,"wins":61},"gpt-5.6-sol":{"draws":23,"losses":87,"wins":34},"gpt-5.6-terra":{"draws":48,"losses":37,"wins":53},"gpt-6-astra":{"draws":9,"losses":129,"wins":6},"gpt-6-luna":{"draws":41,"losses":47,"wins":56},"gpt-6-sol":{"draws":16,"losses":100,"wins":28},"gpt-6.1-sol":{"draws":12,"losses":121,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":44,"losses":10,"wins":48},"inception/mercury-3":{"draws":23,"losses":17,"wins":20},"inclusionai/ling-3.0-flash":{"draws":39,"losses":9,"wins":54},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":24,"wins":102},"meta/muse-glimmer-30b":{"draws":46,"losses":12,"wins":68},"meta/muse-spark-1.2":{"draws":31,"losses":52,"wins":55},"meta/muse-spark-1.3":{"draws":39,"losses":52,"wins":53},"meta/muse-spark-open":{"draws":14,"losses":27,"wins":29},"meta/muse-wonder":{"draws":33,"losses":78,"wins":33},"minimax/minimax-m3":{"draws":21,"losses":8,"wins":49},"minimax/minimax-m3.1-flash":{"draws":16,"losses":10,"wins":44},"mistralai/mistral-large-4-0":{"draws":32,"losses":18,"wins":40},"mistralai/mistral-medium-3-5":{"draws":29,"losses":6,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":36,"losses":34,"wins":68},"nex-agi/nex-n2-pro":{"draws":21,"losses":9,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":12,"wins":65},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":7,"wins":17},"o3":{"draws":35,"losses":64,"wins":99},"openai/gpt-oss-120b":{"draws":39,"losses":15,"wins":72},"poolside/laguna-s-2.1":{"draws":45,"losses":23,"wins":70},"qwen/qwen3.7-max":{"draws":26,"losses":17,"wins":41},"qwen/qwen3.7-plus":{"draws":26,"losses":9,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":44,"wins":53},"qwen/qwen3.8-27b":{"draws":26,"losses":27,"wins":49},"qwen/qwen3.8-flash":{"draws":33,"losses":29,"wins":34},"qwen/qwen3.8-max":{"draws":37,"losses":44,"wins":63},"qwen/qwen3.8-max-0902":{"draws":24,"losses":36,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":16,"wins":23},"stealth/ox-alpha":{"draws":113,"losses":176,"wins":185},"stealth/space-bunny-alpha":{"draws":36,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":25,"losses":19,"wins":58},"stepfun/step-5-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":27,"losses":14,"wins":37},"tencent/hy4-preview":{"draws":34,"losses":53,"wins":51},"thinkingmachines/inkling":{"draws":54,"losses":30,"wins":108},"thinkingmachines/inkling-small":{"draws":49,"losses":15,"wins":80},"unbiased/pareto-26.10":{"draws":2,"losses":30,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":29},"x-ai/grok-4.5":{"draws":31,"losses":61,"wins":52},"x-ai/grok-4.6":{"draws":44,"losses":66,"wins":34},"x-ai/grok-4.7":{"draws":18,"losses":80,"wins":28},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":25},"xiaomi/mimo-v2.5":{"draws":83,"losses":28,"wins":111},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":20,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":39,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":52,"wins":30},"z-ai/glm-5.2":{"draws":97,"losses":57,"wins":134},"z-ai/glm-5.3":{"draws":35,"losses":73,"wins":30},"z-ai/glm-5.3-flash":{"draws":38,"losses":53,"wins":53},"z-ai/glm-5.3-flashx":{"draws":36,"losses":57,"wins":51}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":29},"claude-fable-5":{"draws":16,"losses":24,"wins":18},"claude-fable-5-1":{"draws":4,"losses":58,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":35,"wins":14},"claude-opus-4-5":{"draws":32,"losses":29,"wins":35},"claude-opus-4-8":{"draws":11,"losses":27,"wins":20},"claude-opus-5":{"draws":14,"losses":87,"wins":13},"claude-opus-5-5":{"draws":4,"losses":64,"wins":2},"claude-sonnet-5":{"draws":19,"losses":22,"wins":21},"claude-sonnet-5-5":{"draws":13,"losses":42,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":44},"deepseek/deepseek-v4-pro":{"draws":12,"losses":21,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":31,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":70,"wins":27},"elorian/glimpse":{"draws":18,"losses":33,"wins":19},"fireworks/ember-1":{"draws":17,"losses":28,"wins":37},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":18},"gemini-4-argon":{"draws":7,"losses":112,"wins":13},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":31},"google/gemini-3.5-flash":{"draws":18,"losses":30,"wins":34},"google/gemini-3.5-flash-lite":{"draws":35,"losses":31,"wins":56},"google/gemini-3.6-flash":{"draws":28,"losses":57,"wins":45},"google/gemini-3.8-flash":{"draws":20,"losses":30,"wins":14},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":27},"gpt-4.1":{"draws":7,"losses":9,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":14,"wins":24},"gpt-5.4":{"draws":19,"losses":21,"wins":22},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":22},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":35},"gpt-5.5":{"draws":13,"losses":28,"wins":15},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":22},"gpt-5.6-sol":{"draws":5,"losses":30,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":15,"wins":14},"gpt-6-astra":{"draws":3,"losses":60,"wins":1},"gpt-6-luna":{"draws":13,"losses":20,"wins":25},"gpt-6-sol":{"draws":8,"losses":49,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":74,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":28,"losses":1,"wins":33},"inception/mercury-3":{"draws":24,"losses":29,"wins":31},"inclusionai/ling-3.0-flash":{"draws":14,"losses":1,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":17,"wins":37},"meta/muse-glimmer-30b":{"draws":17,"losses":8,"wins":31},"meta/muse-spark-1.2":{"draws":20,"losses":21,"wins":19},"meta/muse-spark-1.3":{"draws":8,"losses":32,"wins":14},"meta/muse-spark-open":{"draws":27,"losses":59,"wins":34},"meta/muse-wonder":{"draws":14,"losses":43,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":18},"minimax/minimax-m3.1-flash":{"draws":27,"losses":39,"wins":44},"mistralai/mistral-large-4-0":{"draws":11,"losses":18,"wins":19},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":16,"losses":27,"wins":19},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":11,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":17,"wins":25},"o3":{"draws":15,"losses":35,"wins":50},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":29},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":26},"qwen/qwen3.7-max":{"draws":12,"losses":12,"wins":20},"qwen/qwen3.7-plus":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":37,"wins":16},"qwen/qwen3.8-27b":{"draws":10,"losses":10,"wins":14},"qwen/qwen3.8-flash":{"draws":8,"losses":16,"wins":18},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":12},"qwen/qwen3.8-max-0902":{"draws":15,"losses":23,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":28,"wins":28},"stealth/ox-alpha":{"draws":47,"losses":102,"wins":71},"stealth/space-bunny-alpha":{"draws":17,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":8,"losses":19,"wins":25},"tencent/hy3-preview":{"draws":3,"losses":10,"wins":13},"tencent/hy4-preview":{"draws":24,"losses":28,"wins":14},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":44},"thinkingmachines/inkling-small":{"draws":12,"losses":11,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":42,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":26,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":14,"losses":23,"wins":13},"x-ai/grok-4.6":{"draws":21,"losses":33,"wins":16},"x-ai/grok-4.7":{"draws":4,"losses":47,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":38,"losses":12,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":18,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":23,"wins":12},"z-ai/glm-5.2":{"draws":50,"losses":38,"wins":42},"z-ai/glm-5.3":{"draws":7,"losses":41,"wins":12},"z-ai/glm-5.3-flash":{"draws":11,"losses":32,"wins":15},"z-ai/glm-5.3-flashx":{"draws":16,"losses":22,"wins":18}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":102,"losses":87,"wins":251},"claude-fable-5":{"draws":82,"losses":277,"wins":115},"claude-fable-5-1":{"draws":32,"losses":492,"wins":26},"claude-haiku-5-5":{"draws":96,"losses":173,"wins":165},"claude-opus-4-5":{"draws":201,"losses":213,"wins":336},"claude-opus-4-8":{"draws":85,"losses":153,"wins":156},"claude-opus-5":{"draws":129,"losses":582,"wins":121},"claude-opus-5-5":{"draws":46,"losses":432,"wins":28},"claude-sonnet-5":{"draws":108,"losses":133,"wins":233},"claude-sonnet-5-5":{"draws":85,"losses":225,"wins":164},"cohere/north-mini-code":{"draws":24,"losses":23,"wins":131},"deepseek/deepseek-v4-flash":{"draws":170,"losses":126,"wins":400},"deepseek/deepseek-v4-pro":{"draws":106,"losses":132,"wins":204},"deepseek/deepseek-v4-pro-0813":{"draws":110,"losses":148,"wins":182},"deepseek/deepseek-v4.1-flash":{"draws":110,"losses":182,"wins":181},"deepseek/deepseek-v4.1-flash-1017":{"draws":41,"losses":146,"wins":93},"elorian/glimpse":{"draws":35,"losses":41,"wins":66},"fireworks/ember-1":{"draws":123,"losses":171,"wins":180},"gemini-3.1-pro-preview":{"draws":105,"losses":145,"wins":224},"gemini-4-argon":{"draws":27,"losses":148,"wins":23},"google/gemini-3.1-flash-lite":{"draws":52,"losses":28,"wins":192},"google/gemini-3.5-flash":{"draws":114,"losses":202,"wins":260},"google/gemini-3.5-flash-lite":{"draws":174,"losses":167,"wins":485},"google/gemini-3.6-flash":{"draws":196,"losses":362,"wins":358},"google/gemini-3.8-flash":{"draws":100,"losses":225,"wins":149},"google/gemma-4-31b-it":{"draws":60,"losses":40,"wins":160},"gpt-4.1":{"draws":43,"losses":36,"wins":79},"gpt-4.1-nano":{"draws":33,"losses":5,"wins":34},"gpt-5":{"draws":98,"losses":127,"wins":199},"gpt-5.4":{"draws":124,"losses":179,"wins":155},"gpt-5.4-mini":{"draws":94,"losses":60,"wins":162},"gpt-5.4-nano":{"draws":83,"losses":118,"wins":223},"gpt-5.5":{"draws":123,"losses":155,"wins":164},"gpt-5.6-luna":{"draws":146,"losses":100,"wins":228},"gpt-5.6-sol":{"draws":72,"losses":286,"wins":116},"gpt-5.6-terra":{"draws":135,"losses":126,"wins":195},"gpt-6-astra":{"draws":36,"losses":418,"wins":20},"gpt-6-luna":{"draws":112,"losses":154,"wins":208},"gpt-6-sol":{"draws":61,"losses":340,"wins":73},"gpt-6.1-sol":{"draws":43,"losses":401,"wins":30},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":102,"losses":32,"wins":176},"inception/mercury-3":{"draws":42,"losses":40,"wins":68},"inclusionai/ling-3.0-flash":{"draws":94,"losses":26,"wins":208},"inclusionai/ling-3.1-flash":{"draws":6,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":114,"losses":79,"wins":317},"meta/muse-glimmer-30b":{"draws":104,"losses":56,"wins":266},"meta/muse-spark-1.2":{"draws":105,"losses":148,"wins":205},"meta/muse-spark-1.3":{"draws":87,"losses":220,"wins":167},"meta/muse-spark-open":{"draws":36,"losses":91,"wins":65},"meta/muse-wonder":{"draws":93,"losses":253,"wins":128},"minimax/minimax-m3":{"draws":55,"losses":39,"wins":148},"minimax/minimax-m3.1-flash":{"draws":59,"losses":64,"wins":127},"mistralai/mistral-large-4-0":{"draws":98,"losses":82,"wins":120},"mistralai/mistral-medium-3-5":{"draws":72,"losses":39,"wins":171},"moonshotai/kimi-k2.7-code":{"draws":24,"losses":29,"wins":49},"moonshotai/kimi-k3":{"draws":111,"losses":165,"wins":182},"nex-agi/nex-n2-pro":{"draws":61,"losses":29,"wins":160},"nex-agi/nex-n2.5-pro":{"draws":15,"losses":7,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":109,"losses":58,"wins":207},"nvidia/nemotron-3.5-super-vl":{"draws":38,"losses":26,"wins":54},"o3":{"draws":86,"losses":202,"wins":316},"openai/gpt-oss-120b":{"draws":110,"losses":58,"wins":256},"poolside/laguna-s-2.1":{"draws":130,"losses":85,"wins":263},"qwen/qwen3.7-max":{"draws":64,"losses":58,"wins":136},"qwen/qwen3.7-plus":{"draws":45,"losses":27,"wins":130},"qwen/qwen3.8-2.4t-a95b":{"draws":122,"losses":176,"wins":176},"qwen/qwen3.8-27b":{"draws":74,"losses":107,"wins":151},"qwen/qwen3.8-flash":{"draws":93,"losses":99,"wins":124},"qwen/qwen3.8-max":{"draws":126,"losses":157,"wins":191},"qwen/qwen3.8-max-0902":{"draws":113,"losses":185,"wins":176},"reflection/beam-1.0-501b-a23b":{"draws":47,"losses":71,"wins":102},"stealth/ox-alpha":{"draws":296,"losses":672,"wins":672},"stealth/space-bunny-alpha":{"draws":99,"losses":83,"wins":188},"stepfun/step-3.7-flash":{"draws":51,"losses":57,"wins":224},"stepfun/step-5-preview":{"draws":8,"losses":15,"wins":9},"tencent/hy3-preview":{"draws":72,"losses":46,"wins":124},"tencent/hy4-preview":{"draws":102,"losses":198,"wins":158},"thinkingmachines/inkling":{"draws":163,"losses":120,"wins":375},"thinkingmachines/inkling-small":{"draws":134,"losses":68,"wins":272},"unbiased/pareto-26.10":{"draws":7,"losses":84,"wins":3},"unbiased/pareto-26.10-preview":{"draws":10,"losses":141,"wins":7},"upstage/solar-mini4":{"draws":13,"losses":15,"wins":74},"x-ai/grok-4.5":{"draws":100,"losses":206,"wins":168},"x-ai/grok-4.6":{"draws":137,"losses":192,"wins":145},"x-ai/grok-4.7":{"draws":46,"losses":280,"wins":74},"x-ai/grok-build-0.1":{"draws":40,"losses":18,"wins":100},"xiaomi/mimo-v2.5":{"draws":172,"losses":94,"wins":380},"xiaomi/mimo-v2.5-pro":{"draws":48,"losses":58,"wins":136},"xiaomi/mimo-v2.6-flash":{"draws":57,"losses":110,"wins":131},"xiaomi/mimo-v2.6-pro":{"draws":57,"losses":154,"wins":105},"z-ai/glm-5.2":{"draws":255,"losses":220,"wins":473},"z-ai/glm-5.3":{"draws":82,"losses":258,"wins":118},"z-ai/glm-5.3-flash":{"draws":80,"losses":212,"wins":182},"z-ai/glm-5.3-flashx":{"draws":86,"losses":221,"wins":167}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":31,"wins":38},"claude-fable-5":{"draws":31,"losses":68,"wins":15},"claude-fable-5-1":{"draws":6,"losses":121,"wins":3},"claude-haiku-5-5":{"draws":33,"losses":54,"wins":23},"claude-opus-4-5":{"draws":58,"losses":79,"wins":49},"claude-opus-4-8":{"draws":30,"losses":52,"wins":24},"claude-opus-5":{"draws":31,"losses":151,"wins":14},"claude-opus-5-5":{"draws":5,"losses":116,"wins":1},"claude-sonnet-5":{"draws":30,"losses":47,"wins":37},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":24},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-flash":{"draws":58,"losses":39,"wins":71},"deepseek/deepseek-v4-pro":{"draws":31,"losses":47,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":46,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":53,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":45,"wins":6},"elorian/glimpse":{"draws":4,"losses":11,"wins":7},"fireworks/ember-1":{"draws":36,"losses":55,"wins":23},"gemini-3.1-pro-preview":{"draws":35,"losses":44,"wins":35},"gemini-4-argon":{"draws":4,"losses":44,"wins":4},"google/gemini-3.1-flash-lite":{"draws":21,"losses":12,"wins":47},"google/gemini-3.5-flash":{"draws":44,"losses":67,"wins":33},"google/gemini-3.5-flash-lite":{"draws":58,"losses":61,"wins":83},"google/gemini-3.6-flash":{"draws":57,"losses":118,"wins":45},"google/gemini-3.8-flash":{"draws":27,"losses":70,"wins":17},"google/gemma-4-31b-it":{"draws":26,"losses":16,"wins":26},"gpt-4.1":{"draws":15,"losses":10,"wins":13},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":5},"gpt-5":{"draws":25,"losses":38,"wins":37},"gpt-5.4":{"draws":33,"losses":61,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":15,"wins":33},"gpt-5.4-nano":{"draws":26,"losses":39,"wins":47},"gpt-5.5":{"draws":41,"losses":46,"wins":19},"gpt-5.6-luna":{"draws":43,"losses":31,"wins":40},"gpt-5.6-sol":{"draws":20,"losses":80,"wins":14},"gpt-5.6-terra":{"draws":37,"losses":39,"wins":32},"gpt-6-astra":{"draws":6,"losses":108,"wins":0},"gpt-6-luna":{"draws":41,"losses":50,"wins":23},"gpt-6-sol":{"draws":16,"losses":87,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":100,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":37,"losses":10,"wins":35},"inception/mercury-3":{"draws":5,"losses":18,"wins":9},"inclusionai/ling-3.0-flash":{"draws":34,"losses":11,"wins":31},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":29,"wins":57},"meta/muse-glimmer-30b":{"draws":39,"losses":27,"wins":36},"meta/muse-spark-1.2":{"draws":31,"losses":53,"wins":26},"meta/muse-spark-1.3":{"draws":24,"losses":69,"wins":21},"meta/muse-spark-open":{"draws":14,"losses":30,"wins":16},"meta/muse-wonder":{"draws":28,"losses":68,"wins":18},"minimax/minimax-m3":{"draws":18,"losses":13,"wins":31},"minimax/minimax-m3.1-flash":{"draws":13,"losses":12,"wins":21},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":14},"mistralai/mistral-medium-3-5":{"draws":24,"losses":12,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":14,"wins":7},"moonshotai/kimi-k3":{"draws":37,"losses":53,"wins":20},"nex-agi/nex-n2-pro":{"draws":17,"losses":13,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":25,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":10,"wins":9},"o3":{"draws":26,"losses":78,"wins":56},"openai/gpt-oss-120b":{"draws":33,"losses":23,"wins":44},"poolside/laguna-s-2.1":{"draws":33,"losses":33,"wins":40},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":22},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":47,"wins":27},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":20},"qwen/qwen3.8-flash":{"draws":28,"losses":30,"wins":18},"qwen/qwen3.8-max":{"draws":37,"losses":46,"wins":31},"qwen/qwen3.8-max-0902":{"draws":36,"losses":59,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":99,"losses":188,"wins":83},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":18},"stepfun/step-3.7-flash":{"draws":19,"losses":23,"wins":38},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":21},"tencent/hy4-preview":{"draws":33,"losses":51,"wins":26},"thinkingmachines/inkling":{"draws":50,"losses":44,"wins":60},"thinkingmachines/inkling-small":{"draws":38,"losses":29,"wins":47},"unbiased/pareto-26.10":{"draws":3,"losses":27,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":37,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":9,"wins":16},"x-ai/grok-4.5":{"draws":31,"losses":63,"wins":20},"x-ai/grok-4.6":{"draws":36,"losses":59,"wins":19},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":17},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":16},"xiaomi/mimo-v2.5":{"draws":71,"losses":38,"wins":69},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":15,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":38,"wins":19},"z-ai/glm-5.2":{"draws":89,"losses":74,"wins":65},"z-ai/glm-5.3":{"draws":25,"losses":76,"wins":9},"z-ai/glm-5.3-flash":{"draws":30,"losses":67,"wins":17},"z-ai/glm-5.3-flashx":{"draws":33,"losses":59,"wins":22}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":38,"wins":33},"claude-fable-5":{"draws":13,"losses":82,"wins":7},"claude-fable-5-1":{"draws":3,"losses":111,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":67,"wins":16},"claude-opus-4-5":{"draws":32,"losses":94,"wins":40},"claude-opus-4-8":{"draws":16,"losses":61,"wins":17},"claude-opus-5":{"draws":14,"losses":141,"wins":7},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":21,"losses":54,"wins":27},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":26},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":25},"deepseek/deepseek-v4-flash":{"draws":35,"losses":66,"wins":57},"deepseek/deepseek-v4-pro":{"draws":17,"losses":55,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":55,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":62,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":37,"wins":7},"elorian/glimpse":{"draws":4,"losses":27,"wins":7},"fireworks/ember-1":{"draws":23,"losses":61,"wins":18},"gemini-3.1-pro-preview":{"draws":21,"losses":49,"wins":32},"gemini-4-argon":{"draws":0,"losses":38,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":10,"wins":49},"google/gemini-3.5-flash":{"draws":21,"losses":82,"wins":27},"google/gemini-3.5-flash-lite":{"draws":49,"losses":71,"wins":60},"google/gemini-3.6-flash":{"draws":35,"losses":131,"wins":32},"google/gemini-3.8-flash":{"draws":16,"losses":77,"wins":9},"google/gemma-4-31b-it":{"draws":18,"losses":13,"wins":27},"gpt-4.1":{"draws":7,"losses":21,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":21,"losses":53,"wins":18},"gpt-5.4":{"draws":18,"losses":66,"wins":16},"gpt-5.4-mini":{"draws":22,"losses":24,"wins":22},"gpt-5.4-nano":{"draws":16,"losses":60,"wins":34},"gpt-5.5":{"draws":26,"losses":54,"wins":14},"gpt-5.6-luna":{"draws":27,"losses":44,"wins":31},"gpt-5.6-sol":{"draws":11,"losses":85,"wins":6},"gpt-5.6-terra":{"draws":24,"losses":53,"wins":21},"gpt-6-astra":{"draws":6,"losses":96,"wins":0},"gpt-6-luna":{"draws":21,"losses":57,"wins":24},"gpt-6-sol":{"draws":13,"losses":85,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":99,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":10,"wins":38},"inception/mercury-3":{"draws":7,"losses":20,"wins":5},"inclusionai/ling-3.0-flash":{"draws":26,"losses":20,"wins":30},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":45,"wins":49},"meta/muse-glimmer-30b":{"draws":20,"losses":41,"wins":27},"meta/muse-spark-1.2":{"draws":15,"losses":57,"wins":24},"meta/muse-spark-1.3":{"draws":10,"losses":79,"wins":13},"meta/muse-spark-open":{"draws":8,"losses":39,"wins":7},"meta/muse-wonder":{"draws":12,"losses":80,"wins":10},"minimax/minimax-m3":{"draws":11,"losses":27,"wins":18},"minimax/minimax-m3.1-flash":{"draws":4,"losses":26,"wins":18},"mistralai/mistral-large-4-0":{"draws":20,"losses":33,"wins":9},"mistralai/mistral-medium-3-5":{"draws":19,"losses":13,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":15,"wins":5},"moonshotai/kimi-k3":{"draws":21,"losses":59,"wins":16},"nex-agi/nex-n2-pro":{"draws":8,"losses":17,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":34,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":19,"wins":4},"o3":{"draws":24,"losses":93,"wins":43},"openai/gpt-oss-120b":{"draws":29,"losses":23,"wins":36},"poolside/laguna-s-2.1":{"draws":31,"losses":37,"wins":30},"qwen/qwen3.7-max":{"draws":16,"losses":34,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":23,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":71,"wins":15},"qwen/qwen3.8-27b":{"draws":12,"losses":38,"wins":26},"qwen/qwen3.8-flash":{"draws":14,"losses":40,"wins":14},"qwen/qwen3.8-max":{"draws":24,"losses":61,"wins":17},"qwen/qwen3.8-max-0902":{"draws":25,"losses":58,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":25,"wins":19},"stealth/ox-alpha":{"draws":51,"losses":224,"wins":57},"stealth/space-bunny-alpha":{"draws":19,"losses":38,"wins":23},"stepfun/step-3.7-flash":{"draws":10,"losses":19,"wins":19},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":22,"wins":12},"tencent/hy4-preview":{"draws":20,"losses":63,"wins":17},"thinkingmachines/inkling":{"draws":38,"losses":38,"wins":62},"thinkingmachines/inkling-small":{"draws":28,"losses":37,"wins":37},"unbiased/pareto-26.10":{"draws":2,"losses":22,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":9,"wins":19},"x-ai/grok-4.5":{"draws":12,"losses":71,"wins":19},"x-ai/grok-4.6":{"draws":21,"losses":67,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":75,"wins":10},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":15},"xiaomi/mimo-v2.5":{"draws":44,"losses":54,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":34,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":44,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":52,"wins":8},"z-ai/glm-5.2":{"draws":50,"losses":105,"wins":49},"z-ai/glm-5.3":{"draws":15,"losses":78,"wins":3},"z-ai/glm-5.3-flash":{"draws":15,"losses":67,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":75,"wins":14}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":4},"claude-fable-5":{"draws":2,"losses":5,"wins":5},"claude-fable-5-1":{"draws":0,"losses":10,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-5":{"draws":3,"losses":7,"wins":10},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":0,"losses":17,"wins":7},"claude-opus-5-5":{"draws":0,"losses":16,"wins":4},"claude-sonnet-5":{"draws":3,"losses":3,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":4,"wins":4},"elorian/glimpse":{"draws":0,"losses":4,"wins":2},"fireworks/ember-1":{"draws":3,"losses":5,"wins":4},"gemini-3.1-pro-preview":{"draws":4,"losses":4,"wins":4},"gemini-4-argon":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":5,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":0,"wins":7},"gpt-5.4":{"draws":5,"losses":1,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":9},"gpt-5.5":{"draws":6,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":6},"gpt-6-astra":{"draws":0,"losses":8,"wins":4},"gpt-6-luna":{"draws":3,"losses":3,"wins":6},"gpt-6-sol":{"draws":1,"losses":8,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":10,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":5},"inception/mercury-3":{"draws":0,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":8},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":5},"meta/muse-spark-open":{"draws":0,"losses":1,"wins":1},"meta/muse-wonder":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":5},"o3":{"draws":8,"losses":2,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":8,"losses":9,"wins":15},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":6},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":11,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":13},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":0,"wins":7},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":8}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":26,"wins":23},"claude-fable-5":{"draws":22,"losses":45,"wins":11},"claude-fable-5-1":{"draws":8,"losses":74,"wins":4},"claude-haiku-5-5":{"draws":25,"losses":31,"wins":20},"claude-opus-4-5":{"draws":46,"losses":52,"wins":30},"claude-opus-4-8":{"draws":20,"losses":38,"wins":16},"claude-opus-5":{"draws":25,"losses":106,"wins":11},"claude-opus-5-5":{"draws":8,"losses":78,"wins":0},"claude-sonnet-5":{"draws":25,"losses":31,"wins":22},"claude-sonnet-5-5":{"draws":19,"losses":49,"wins":10},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":13},"deepseek/deepseek-v4-flash":{"draws":35,"losses":38,"wins":43},"deepseek/deepseek-v4-pro":{"draws":24,"losses":30,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":24,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":36,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":31,"wins":7},"elorian/glimpse":{"draws":9,"losses":8,"wins":1},"fireworks/ember-1":{"draws":30,"losses":36,"wins":12},"gemini-3.1-pro-preview":{"draws":22,"losses":34,"wins":22},"gemini-4-argon":{"draws":3,"losses":40,"wins":3},"google/gemini-3.1-flash-lite":{"draws":17,"losses":11,"wins":24},"google/gemini-3.5-flash":{"draws":28,"losses":41,"wins":29},"google/gemini-3.5-flash-lite":{"draws":48,"losses":30,"wins":58},"google/gemini-3.6-flash":{"draws":47,"losses":70,"wins":31},"google/gemini-3.8-flash":{"draws":31,"losses":39,"wins":8},"google/gemma-4-31b-it":{"draws":21,"losses":9,"wins":16},"gpt-4.1":{"draws":10,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":20,"losses":21,"wins":27},"gpt-5.4":{"draws":28,"losses":33,"wins":13},"gpt-5.4-mini":{"draws":21,"losses":14,"wins":17},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":37},"gpt-5.5":{"draws":33,"losses":30,"wins":9},"gpt-5.6-luna":{"draws":29,"losses":21,"wins":28},"gpt-5.6-sol":{"draws":14,"losses":55,"wins":9},"gpt-5.6-terra":{"draws":31,"losses":28,"wins":15},"gpt-6-astra":{"draws":11,"losses":67,"wins":0},"gpt-6-luna":{"draws":26,"losses":32,"wins":20},"gpt-6-sol":{"draws":15,"losses":58,"wins":5},"gpt-6.1-sol":{"draws":7,"losses":68,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":12,"wins":16},"inception/mercury-3":{"draws":13,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":22,"losses":7,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":25,"wins":32},"meta/muse-glimmer-30b":{"draws":26,"losses":13,"wins":31},"meta/muse-spark-1.2":{"draws":21,"losses":42,"wins":13},"meta/muse-spark-1.3":{"draws":15,"losses":49,"wins":14},"meta/muse-spark-open":{"draws":14,"losses":17,"wins":5},"meta/muse-wonder":{"draws":15,"losses":51,"wins":12},"minimax/minimax-m3":{"draws":15,"losses":11,"wins":18},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":21},"mistralai/mistral-large-4-0":{"draws":20,"losses":14,"wins":16},"mistralai/mistral-medium-3-5":{"draws":18,"losses":12,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":6},"moonshotai/kimi-k3":{"draws":28,"losses":28,"wins":20},"nex-agi/nex-n2-pro":{"draws":12,"losses":13,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":14,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":12,"wins":4},"o3":{"draws":22,"losses":42,"wins":40},"openai/gpt-oss-120b":{"draws":22,"losses":19,"wins":27},"poolside/laguna-s-2.1":{"draws":28,"losses":22,"wins":26},"qwen/qwen3.7-max":{"draws":19,"losses":17,"wins":10},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":34,"wins":16},"qwen/qwen3.8-27b":{"draws":15,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":18,"losses":22,"wins":12},"qwen/qwen3.8-max":{"draws":30,"losses":35,"wins":13},"qwen/qwen3.8-max-0902":{"draws":27,"losses":37,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":13,"wins":10},"stealth/ox-alpha":{"draws":72,"losses":124,"wins":46},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":17},"stepfun/step-3.7-flash":{"draws":18,"losses":12,"wins":22},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":31,"wins":19},"thinkingmachines/inkling":{"draws":31,"losses":26,"wins":47},"thinkingmachines/inkling-small":{"draws":32,"losses":16,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":17,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":2},"upstage/solar-mini4":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":24,"losses":47,"wins":7},"x-ai/grok-4.6":{"draws":22,"losses":46,"wins":10},"x-ai/grok-4.7":{"draws":12,"losses":55,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.5":{"draws":48,"losses":33,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":14,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":26,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":33,"wins":10},"z-ai/glm-5.2":{"draws":53,"losses":56,"wins":47},"z-ai/glm-5.3":{"draws":14,"losses":50,"wins":10},"z-ai/glm-5.3-flash":{"draws":21,"losses":43,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":48,"wins":14}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":15,"wins":72},"claude-fable-5":{"draws":25,"losses":81,"wins":32},"claude-fable-5-1":{"draws":9,"losses":135,"wins":12},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":54},"claude-opus-4-5":{"draws":62,"losses":60,"wins":102},"claude-opus-4-8":{"draws":31,"losses":46,"wins":49},"claude-opus-5":{"draws":24,"losses":175,"wins":35},"claude-opus-5-5":{"draws":12,"losses":125,"wins":13},"claude-sonnet-5":{"draws":40,"losses":34,"wins":64},"claude-sonnet-5-5":{"draws":24,"losses":67,"wins":47},"cohere/north-mini-code":{"draws":14,"losses":3,"wins":37},"deepseek/deepseek-v4-flash":{"draws":55,"losses":35,"wins":116},"deepseek/deepseek-v4-pro":{"draws":32,"losses":36,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":43,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":41,"wins":56},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":47,"wins":26},"elorian/glimpse":{"draws":10,"losses":15,"wins":17},"fireworks/ember-1":{"draws":42,"losses":42,"wins":54},"gemini-3.1-pro-preview":{"draws":33,"losses":40,"wins":65},"gemini-4-argon":{"draws":8,"losses":47,"wins":9},"google/gemini-3.1-flash-lite":{"draws":23,"losses":3,"wins":68},"google/gemini-3.5-flash":{"draws":39,"losses":46,"wins":89},"google/gemini-3.5-flash-lite":{"draws":62,"losses":48,"wins":134},"google/gemini-3.6-flash":{"draws":59,"losses":102,"wins":105},"google/gemini-3.8-flash":{"draws":31,"losses":53,"wins":54},"google/gemma-4-31b-it":{"draws":26,"losses":11,"wins":43},"gpt-4.1":{"draws":13,"losses":9,"wins":24},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":11},"gpt-5":{"draws":35,"losses":37,"wins":50},"gpt-5.4":{"draws":30,"losses":56,"wins":48},"gpt-5.4-mini":{"draws":34,"losses":11,"wins":47},"gpt-5.4-nano":{"draws":23,"losses":28,"wins":87},"gpt-5.5":{"draws":44,"losses":40,"wins":44},"gpt-5.6-luna":{"draws":43,"losses":26,"wins":69},"gpt-5.6-sol":{"draws":20,"losses":70,"wins":48},"gpt-5.6-terra":{"draws":37,"losses":36,"wins":59},"gpt-6-astra":{"draws":9,"losses":124,"wins":5},"gpt-6-luna":{"draws":39,"losses":35,"wins":64},"gpt-6-sol":{"draws":19,"losses":93,"wins":26},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":39,"losses":8,"wins":49},"inception/mercury-3":{"draws":12,"losses":13,"wins":21},"inclusionai/ling-3.0-flash":{"draws":37,"losses":5,"wins":56},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":39,"losses":22,"wins":91},"meta/muse-glimmer-30b":{"draws":43,"losses":10,"wins":69},"meta/muse-spark-1.2":{"draws":19,"losses":53,"wins":60},"meta/muse-spark-1.3":{"draws":28,"losses":60,"wins":50},"meta/muse-spark-open":{"draws":9,"losses":42,"wins":19},"meta/muse-wonder":{"draws":28,"losses":71,"wins":39},"minimax/minimax-m3":{"draws":17,"losses":7,"wins":50},"minimax/minimax-m3.1-flash":{"draws":14,"losses":23,"wins":29},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":36},"mistralai/mistral-medium-3-5":{"draws":28,"losses":6,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":33,"losses":44,"wins":55},"nex-agi/nex-n2-pro":{"draws":17,"losses":6,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":14,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":9},"o3":{"draws":30,"losses":60,"wins":106},"openai/gpt-oss-120b":{"draws":38,"losses":18,"wins":64},"poolside/laguna-s-2.1":{"draws":42,"losses":24,"wins":66},"qwen/qwen3.7-max":{"draws":18,"losses":18,"wins":44},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":46,"wins":52},"qwen/qwen3.8-27b":{"draws":26,"losses":27,"wins":45},"qwen/qwen3.8-flash":{"draws":26,"losses":26,"wins":40},"qwen/qwen3.8-max":{"draws":37,"losses":43,"wins":58},"qwen/qwen3.8-max-0902":{"draws":34,"losses":51,"wins":53},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":14,"wins":28},"stealth/ox-alpha":{"draws":102,"losses":158,"wins":198},"stealth/space-bunny-alpha":{"draws":33,"losses":26,"wins":51},"stepfun/step-3.7-flash":{"draws":20,"losses":17,"wins":63},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":24,"losses":19,"wins":31},"tencent/hy4-preview":{"draws":20,"losses":34,"wins":34},"thinkingmachines/inkling":{"draws":50,"losses":29,"wins":107},"thinkingmachines/inkling-small":{"draws":44,"losses":14,"wins":80},"unbiased/pareto-26.10":{"draws":2,"losses":28,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":3},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":30,"losses":55,"wins":53},"x-ai/grok-4.6":{"draws":43,"losses":62,"wins":33},"x-ai/grok-4.7":{"draws":12,"losses":73,"wins":35},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":24},"xiaomi/mimo-v2.5":{"draws":69,"losses":20,"wins":123},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":14,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":35,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":43,"wins":33},"z-ai/glm-5.2":{"draws":75,"losses":56,"wins":145},"z-ai/glm-5.3":{"draws":23,"losses":85,"wins":24},"z-ai/glm-5.3-flash":{"draws":24,"losses":63,"wins":51},"z-ai/glm-5.3-flashx":{"draws":32,"losses":49,"wins":57}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":61,"losses":71,"wins":46},"claude-fable-5":{"draws":40,"losses":140,"wins":12},"claude-fable-5-1":{"draws":9,"losses":209,"wins":0},"claude-haiku-5-5":{"draws":49,"losses":110,"wins":23},"claude-opus-4-5":{"draws":102,"losses":160,"wins":48},"claude-opus-4-8":{"draws":43,"losses":108,"wins":21},"claude-opus-5":{"draws":48,"losses":261,"wins":29},"claude-opus-5-5":{"draws":18,"losses":186,"wins":0},"claude-sonnet-5":{"draws":62,"losses":102,"wins":28},"claude-sonnet-5-5":{"draws":41,"losses":110,"wins":41},"cohere/north-mini-code":{"draws":18,"losses":21,"wins":33},"deepseek/deepseek-v4-flash":{"draws":94,"losses":92,"wins":98},"deepseek/deepseek-v4-pro":{"draws":56,"losses":93,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":75,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":63,"losses":99,"wins":30},"deepseek/deepseek-v4.1-flash-1017":{"draws":28,"losses":75,"wins":9},"elorian/glimpse":{"draws":23,"losses":24,"wins":15},"fireworks/ember-1":{"draws":60,"losses":107,"wins":25},"gemini-3.1-pro-preview":{"draws":57,"losses":87,"wins":48},"gemini-4-argon":{"draws":7,"losses":68,"wins":5},"google/gemini-3.1-flash-lite":{"draws":34,"losses":34,"wins":58},"google/gemini-3.5-flash":{"draws":57,"losses":135,"wins":48},"google/gemini-3.5-flash-lite":{"draws":93,"losses":132,"wins":113},"google/gemini-3.6-flash":{"draws":103,"losses":213,"wins":56},"google/gemini-3.8-flash":{"draws":50,"losses":123,"wins":19},"google/gemma-4-31b-it":{"draws":40,"losses":32,"wins":36},"gpt-4.1":{"draws":17,"losses":27,"wins":20},"gpt-4.1-nano":{"draws":14,"losses":1,"wins":7},"gpt-5":{"draws":40,"losses":93,"wins":39},"gpt-5.4":{"draws":49,"losses":108,"wins":29},"gpt-5.4-mini":{"draws":48,"losses":43,"wins":37},"gpt-5.4-nano":{"draws":42,"losses":77,"wins":69},"gpt-5.5":{"draws":55,"losses":98,"wins":27},"gpt-5.6-luna":{"draws":63,"losses":85,"wins":44},"gpt-5.6-sol":{"draws":28,"losses":147,"wins":17},"gpt-5.6-terra":{"draws":55,"losses":91,"wins":36},"gpt-6-astra":{"draws":11,"losses":178,"wins":3},"gpt-6-luna":{"draws":56,"losses":96,"wins":40},"gpt-6-sol":{"draws":25,"losses":154,"wins":13},"gpt-6.1-sol":{"draws":13,"losses":173,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":52,"losses":32,"wins":44},"inception/mercury-3":{"draws":13,"losses":22,"wins":13},"inclusionai/ling-3.0-flash":{"draws":51,"losses":27,"wins":52},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":54,"losses":75,"wins":77},"meta/muse-glimmer-30b":{"draws":60,"losses":58,"wins":56},"meta/muse-spark-1.2":{"draws":50,"losses":101,"wins":35},"meta/muse-spark-1.3":{"draws":33,"losses":141,"wins":18},"meta/muse-spark-open":{"draws":27,"losses":60,"wins":11},"meta/muse-wonder":{"draws":44,"losses":126,"wins":22},"minimax/minimax-m3":{"draws":26,"losses":34,"wins":44},"minimax/minimax-m3.1-flash":{"draws":20,"losses":45,"wins":38},"mistralai/mistral-large-4-0":{"draws":42,"losses":58,"wins":22},"mistralai/mistral-medium-3-5":{"draws":39,"losses":23,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":28,"wins":10},"moonshotai/kimi-k3":{"draws":54,"losses":93,"wins":39},"nex-agi/nex-n2-pro":{"draws":26,"losses":28,"wins":40},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":59,"wins":51},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":17,"wins":13},"o3":{"draws":42,"losses":167,"wins":57},"openai/gpt-oss-120b":{"draws":47,"losses":56,"wins":65},"poolside/laguna-s-2.1":{"draws":58,"losses":75,"wins":55},"qwen/qwen3.7-max":{"draws":34,"losses":59,"wins":17},"qwen/qwen3.7-plus":{"draws":27,"losses":38,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":59,"losses":108,"wins":25},"qwen/qwen3.8-27b":{"draws":37,"losses":71,"wins":30},"qwen/qwen3.8-flash":{"draws":43,"losses":60,"wins":25},"qwen/qwen3.8-max":{"draws":61,"losses":98,"wins":33},"qwen/qwen3.8-max-0902":{"draws":54,"losses":108,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":44,"wins":16},"stealth/ox-alpha":{"draws":163,"losses":375,"wins":120},"stealth/space-bunny-alpha":{"draws":50,"losses":60,"wins":44},"stepfun/step-3.7-flash":{"draws":38,"losses":62,"wins":38},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":31,"losses":47,"wins":26},"tencent/hy4-preview":{"draws":50,"losses":107,"wins":29},"thinkingmachines/inkling":{"draws":68,"losses":68,"wins":68},"thinkingmachines/inkling-small":{"draws":70,"losses":47,"wins":75},"unbiased/pareto-26.10":{"draws":1,"losses":41,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":63,"wins":1},"upstage/solar-mini4":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.5":{"draws":53,"losses":115,"wins":24},"x-ai/grok-4.6":{"draws":64,"losses":107,"wins":21},"x-ai/grok-4.7":{"draws":21,"losses":134,"wins":13},"x-ai/grok-build-0.1":{"draws":22,"losses":26,"wins":16},"xiaomi/mimo-v2.5":{"draws":95,"losses":113,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":58,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":30,"losses":69,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":89,"wins":14},"z-ai/glm-5.2":{"draws":119,"losses":172,"wins":93},"z-ai/glm-5.3":{"draws":35,"losses":127,"wins":20},"z-ai/glm-5.3-flash":{"draws":40,"losses":121,"wins":31},"z-ai/glm-5.3-flashx":{"draws":44,"losses":123,"wins":25}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":52,"wins":30},"claude-fable-5":{"draws":29,"losses":101,"wins":14},"claude-fable-5-1":{"draws":7,"losses":155,"wins":0},"claude-haiku-5-5":{"draws":33,"losses":92,"wins":13},"claude-opus-4-5":{"draws":79,"losses":122,"wins":33},"claude-opus-4-8":{"draws":40,"losses":80,"wins":12},"claude-opus-5":{"draws":38,"losses":196,"wins":12},"claude-opus-5-5":{"draws":10,"losses":146,"wins":0},"claude-sonnet-5":{"draws":47,"losses":73,"wins":24},"claude-sonnet-5-5":{"draws":32,"losses":91,"wins":21},"cohere/north-mini-code":{"draws":15,"losses":17,"wins":22},"deepseek/deepseek-v4-flash":{"draws":89,"losses":79,"wins":48},"deepseek/deepseek-v4-pro":{"draws":47,"losses":68,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":65,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":74,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":65,"wins":4},"elorian/glimpse":{"draws":10,"losses":25,"wins":7},"fireworks/ember-1":{"draws":50,"losses":77,"wins":17},"gemini-3.1-pro-preview":{"draws":45,"losses":71,"wins":28},"gemini-4-argon":{"draws":6,"losses":64,"wins":4},"google/gemini-3.1-flash-lite":{"draws":34,"losses":29,"wins":33},"google/gemini-3.5-flash":{"draws":52,"losses":97,"wins":31},"google/gemini-3.5-flash-lite":{"draws":83,"losses":95,"wins":74},"google/gemini-3.6-flash":{"draws":84,"losses":147,"wins":45},"google/gemini-3.8-flash":{"draws":39,"losses":88,"wins":17},"google/gemma-4-31b-it":{"draws":35,"losses":24,"wins":25},"gpt-4.1":{"draws":17,"losses":18,"wins":13},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":5},"gpt-5":{"draws":48,"losses":58,"wins":20},"gpt-5.4":{"draws":43,"losses":80,"wins":15},"gpt-5.4-mini":{"draws":44,"losses":30,"wins":22},"gpt-5.4-nano":{"draws":49,"losses":56,"wins":39},"gpt-5.5":{"draws":50,"losses":64,"wins":18},"gpt-5.6-luna":{"draws":58,"losses":49,"wins":37},"gpt-5.6-sol":{"draws":22,"losses":109,"wins":13},"gpt-5.6-terra":{"draws":46,"losses":70,"wins":22},"gpt-6-astra":{"draws":9,"losses":135,"wins":0},"gpt-6-luna":{"draws":40,"losses":72,"wins":32},"gpt-6-sol":{"draws":18,"losses":118,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":138,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":49,"losses":22,"wins":31},"inception/mercury-3":{"draws":16,"losses":21,"wins":3},"inclusionai/ling-3.0-flash":{"draws":50,"losses":19,"wins":33},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":53,"losses":56,"wins":47},"meta/muse-glimmer-30b":{"draws":60,"losses":42,"wins":24},"meta/muse-spark-1.2":{"draws":36,"losses":75,"wins":27},"meta/muse-spark-1.3":{"draws":37,"losses":94,"wins":13},"meta/muse-spark-open":{"draws":14,"losses":48,"wins":10},"meta/muse-wonder":{"draws":33,"losses":96,"wins":15},"minimax/minimax-m3":{"draws":25,"losses":34,"wins":19},"minimax/minimax-m3.1-flash":{"draws":28,"losses":30,"wins":18},"mistralai/mistral-large-4-0":{"draws":31,"losses":45,"wins":14},"mistralai/mistral-medium-3-5":{"draws":39,"losses":15,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":48,"losses":69,"wins":21},"nex-agi/nex-n2-pro":{"draws":24,"losses":17,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":59,"losses":35,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":24,"wins":4},"o3":{"draws":40,"losses":115,"wins":43},"openai/gpt-oss-120b":{"draws":48,"losses":47,"wins":31},"poolside/laguna-s-2.1":{"draws":59,"losses":59,"wins":20},"qwen/qwen3.7-max":{"draws":32,"losses":36,"wins":16},"qwen/qwen3.7-plus":{"draws":28,"losses":20,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":80,"wins":17},"qwen/qwen3.8-27b":{"draws":30,"losses":56,"wins":16},"qwen/qwen3.8-flash":{"draws":42,"losses":36,"wins":18},"qwen/qwen3.8-max":{"draws":44,"losses":61,"wins":39},"qwen/qwen3.8-max-0902":{"draws":49,"losses":80,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":27,"wins":11},"stealth/ox-alpha":{"draws":134,"losses":272,"wins":68},"stealth/space-bunny-alpha":{"draws":38,"losses":47,"wins":29},"stepfun/step-3.7-flash":{"draws":28,"losses":37,"wins":37},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":30,"wins":16},"tencent/hy4-preview":{"draws":44,"losses":80,"wins":14},"thinkingmachines/inkling":{"draws":70,"losses":75,"wins":47},"thinkingmachines/inkling-small":{"draws":38,"losses":29,"wins":29},"unbiased/pareto-26.10":{"draws":3,"losses":31,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":47,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.5":{"draws":37,"losses":90,"wins":17},"x-ai/grok-4.6":{"draws":44,"losses":84,"wins":16},"x-ai/grok-4.7":{"draws":15,"losses":109,"wins":2},"x-ai/grok-build-0.1":{"draws":20,"losses":14,"wins":14},"xiaomi/mimo-v2.5":{"draws":91,"losses":71,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":33,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":54,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":71,"wins":12},"z-ai/glm-5.2":{"draws":109,"losses":123,"wins":56},"z-ai/glm-5.3":{"draws":25,"losses":103,"wins":10},"z-ai/glm-5.3-flash":{"draws":34,"losses":91,"wins":19},"z-ai/glm-5.3-flashx":{"draws":36,"losses":85,"wins":23}},"unbiased/pareto-26.10":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":30},"claude-fable-5":{"draws":1,"losses":3,"wins":26},"claude-fable-5-1":{"draws":6,"losses":11,"wins":11},"claude-haiku-5-5":{"draws":2,"losses":4,"wins":26},"claude-opus-4-5":{"draws":6,"losses":0,"wins":50},"claude-opus-4-8":{"draws":3,"losses":3,"wins":24},"claude-opus-5":{"draws":7,"losses":16,"wins":31},"claude-opus-5-5":{"draws":2,"losses":17,"wins":11},"claude-sonnet-5":{"draws":3,"losses":0,"wins":27},"claude-sonnet-5-5":{"draws":3,"losses":5,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":50},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":1,"wins":39},"elorian/glimpse":{"draws":1,"losses":0,"wins":25},"fireworks/ember-1":{"draws":2,"losses":0,"wins":28},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":20},"gemini-4-argon":{"draws":4,"losses":13,"wins":31},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":0,"wins":25},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":46},"google/gemini-3.6-flash":{"draws":7,"losses":3,"wins":44},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":26},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":15},"gpt-4.1":{"draws":1,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":25},"gpt-5.4":{"draws":4,"losses":2,"wins":28},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":12},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":22},"gpt-5.5":{"draws":2,"losses":2,"wins":20},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":24},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":31},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":26},"gpt-6-astra":{"draws":5,"losses":11,"wins":8},"gpt-6-luna":{"draws":2,"losses":0,"wins":22},"gpt-6-sol":{"draws":3,"losses":3,"wins":34},"gpt-6.1-sol":{"draws":6,"losses":10,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":19},"inception/mercury-3":{"draws":2,"losses":1,"wins":27},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":39},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":24},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":30},"meta/muse-spark-1.3":{"draws":3,"losses":0,"wins":21},"meta/muse-spark-open":{"draws":2,"losses":2,"wins":40},"meta/muse-wonder":{"draws":6,"losses":6,"wins":28},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":14},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":38},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":18},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":1,"losses":0,"wins":31},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":13},"o3":{"draws":0,"losses":0,"wins":36},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":22},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":37},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":19},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":24},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":14},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":13},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":35},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":42},"stealth/ox-alpha":{"draws":7,"losses":3,"wins":84},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":27},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":17},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":28},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":41},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":31},"unbiased/pareto-26.10-preview":{"draws":0,"losses":7,"wins":7},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":3,"losses":0,"wins":27},"x-ai/grok-4.6":{"draws":6,"losses":1,"wins":25},"x-ai/grok-4.7":{"draws":4,"losses":6,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":0,"wins":15},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":56},"z-ai/glm-5.3":{"draws":4,"losses":2,"wins":18},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":21},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":22}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":22,"wins":29},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":76},"claude-opus-4-8":{"draws":2,"losses":1,"wins":41},"claude-opus-5":{"draws":3,"losses":29,"wins":50},"claude-opus-5-5":{"draws":1,"losses":26,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":6,"wins":24},"elorian/glimpse":{"draws":0,"losses":1,"wins":17},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"gemini-4-argon":{"draws":0,"losses":5,"wins":15},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":0,"losses":5,"wins":55},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":78},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":42},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":4,"wins":39},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":43},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":6,"losses":22,"wins":20},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":9,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":0,"losses":1,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":42},"meta/muse-spark-open":{"draws":0,"losses":2,"wins":20},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":30},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":11},"o3":{"draws":0,"losses":3,"wins":63},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":45},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":34},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":26},"stealth/ox-alpha":{"draws":10,"losses":7,"wins":141},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":24},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10":{"draws":0,"losses":7,"wins":7},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":41},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":88},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":14,"wins":15},"claude-fable-5":{"draws":4,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":27,"wins":4},"claude-opus-4-5":{"draws":9,"losses":39,"wins":12},"claude-opus-4-8":{"draws":6,"losses":27,"wins":3},"claude-opus-5":{"draws":7,"losses":40,"wins":1},"claude-opus-5-5":{"draws":2,"losses":34,"wins":0},"claude-sonnet-5":{"draws":6,"losses":22,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":26,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":10,"losses":28,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":26,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":26,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":21,"wins":1},"elorian/glimpse":{"draws":4,"losses":6,"wins":2},"fireworks/ember-1":{"draws":5,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":5,"losses":18,"wins":13},"gemini-4-argon":{"draws":3,"losses":15,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":19},"google/gemini-3.5-flash":{"draws":7,"losses":29,"wins":12},"google/gemini-3.5-flash-lite":{"draws":20,"losses":23,"wins":25},"google/gemini-3.6-flash":{"draws":14,"losses":49,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":11},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":4,"losses":23,"wins":3},"gpt-5.4":{"draws":3,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":15},"gpt-5.5":{"draws":5,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":17,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":32,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":25,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":1,"losses":25,"wins":10},"gpt-6-sol":{"draws":1,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":11},"inception/mercury-3":{"draws":0,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":17,"wins":16},"meta/muse-glimmer-30b":{"draws":7,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":26,"wins":8},"meta/muse-spark-open":{"draws":2,"losses":19,"wins":5},"meta/muse-wonder":{"draws":3,"losses":32,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":10},"minimax/minimax-m3.1-flash":{"draws":2,"losses":11,"wins":5},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":24,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":13,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":8,"wins":2},"o3":{"draws":10,"losses":39,"wins":13},"openai/gpt-oss-120b":{"draws":6,"losses":11,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":14,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":26,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":22,"wins":9},"qwen/qwen3.8-max-0902":{"draws":2,"losses":29,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":13,"losses":74,"wins":15},"stealth/space-bunny-alpha":{"draws":5,"losses":16,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":26,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":15,"wins":22},"thinkingmachines/inkling-small":{"draws":6,"losses":10,"wins":20},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":6,"losses":24,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":48,"wins":16},"z-ai/glm-5.3":{"draws":2,"losses":32,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":22,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":27,"wins":4}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":18,"wins":84},"claude-fable-5":{"draws":22,"losses":74,"wins":48},"claude-fable-5-1":{"draws":10,"losses":141,"wins":11},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":60},"claude-opus-4-5":{"draws":65,"losses":63,"wins":106},"claude-opus-4-8":{"draws":35,"losses":46,"wins":51},"claude-opus-5":{"draws":37,"losses":167,"wins":42},"claude-opus-5-5":{"draws":17,"losses":123,"wins":16},"claude-sonnet-5":{"draws":39,"losses":34,"wins":71},"claude-sonnet-5-5":{"draws":31,"losses":63,"wins":50},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":43},"deepseek/deepseek-v4-flash":{"draws":39,"losses":34,"wins":143},"deepseek/deepseek-v4-pro":{"draws":34,"losses":39,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":43,"wins":60},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":48,"wins":65},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":36,"wins":35},"elorian/glimpse":{"draws":4,"losses":15,"wins":13},"fireworks/ember-1":{"draws":33,"losses":40,"wins":71},"gemini-3.1-pro-preview":{"draws":31,"losses":40,"wins":73},"gemini-4-argon":{"draws":6,"losses":48,"wins":12},"google/gemini-3.1-flash-lite":{"draws":19,"losses":2,"wins":75},"google/gemini-3.5-flash":{"draws":31,"losses":63,"wins":86},"google/gemini-3.5-flash-lite":{"draws":64,"losses":46,"wins":142},"google/gemini-3.6-flash":{"draws":59,"losses":101,"wins":116},"google/gemini-3.8-flash":{"draws":25,"losses":51,"wins":68},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":55},"gpt-4.1":{"draws":11,"losses":9,"wins":28},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":25,"losses":34,"wins":67},"gpt-5.4":{"draws":33,"losses":59,"wins":46},"gpt-5.4-mini":{"draws":30,"losses":14,"wins":52},"gpt-5.4-nano":{"draws":30,"losses":30,"wins":84},"gpt-5.5":{"draws":35,"losses":46,"wins":51},"gpt-5.6-luna":{"draws":37,"losses":35,"wins":72},"gpt-5.6-sol":{"draws":19,"losses":82,"wins":43},"gpt-5.6-terra":{"draws":39,"losses":30,"wins":69},"gpt-6-astra":{"draws":9,"losses":121,"wins":14},"gpt-6-luna":{"draws":34,"losses":45,"wins":65},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":10,"losses":118,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":4,"wins":64},"inception/mercury-3":{"draws":22,"losses":9,"wins":25},"inclusionai/ling-3.0-flash":{"draws":24,"losses":6,"wins":72},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":30,"losses":24,"wins":102},"meta/muse-glimmer-30b":{"draws":31,"losses":14,"wins":81},"meta/muse-spark-1.2":{"draws":33,"losses":36,"wins":69},"meta/muse-spark-1.3":{"draws":23,"losses":61,"wins":60},"meta/muse-spark-open":{"draws":11,"losses":31,"wins":34},"meta/muse-wonder":{"draws":29,"losses":79,"wins":36},"minimax/minimax-m3":{"draws":14,"losses":5,"wins":59},"minimax/minimax-m3.1-flash":{"draws":19,"losses":17,"wins":42},"mistralai/mistral-large-4-0":{"draws":20,"losses":29,"wins":41},"mistralai/mistral-medium-3-5":{"draws":21,"losses":7,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":4,"wins":22},"moonshotai/kimi-k3":{"draws":31,"losses":45,"wins":62},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":50},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":11,"wins":85},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":6,"wins":20},"o3":{"draws":21,"losses":57,"wins":120},"openai/gpt-oss-120b":{"draws":34,"losses":13,"wins":79},"poolside/laguna-s-2.1":{"draws":35,"losses":19,"wins":84},"qwen/qwen3.7-max":{"draws":21,"losses":19,"wins":44},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":48,"wins":62},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":25,"losses":27,"wins":44},"qwen/qwen3.8-max":{"draws":32,"losses":47,"wins":65},"qwen/qwen3.8-max-0902":{"draws":31,"losses":52,"wins":61},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":100,"losses":168,"wins":206},"stealth/space-bunny-alpha":{"draws":31,"losses":20,"wins":63},"stepfun/step-3.7-flash":{"draws":12,"losses":19,"wins":71},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":24,"losses":7,"wins":47},"tencent/hy4-preview":{"draws":30,"losses":53,"wins":55},"thinkingmachines/inkling":{"draws":53,"losses":24,"wins":115},"thinkingmachines/inkling-small":{"draws":37,"losses":17,"wins":90},"unbiased/pareto-26.10":{"draws":3,"losses":27,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":6},"upstage/solar-mini4":{"draws":5,"losses":6,"wins":25},"x-ai/grok-4.5":{"draws":32,"losses":32,"wins":32},"x-ai/grok-4.6":{"draws":42,"losses":54,"wins":48},"x-ai/grok-4.7":{"draws":16,"losses":82,"wins":28},"x-ai/grok-build-0.1":{"draws":13,"losses":5,"wins":30},"xiaomi/mimo-v2.5":{"draws":59,"losses":18,"wins":145},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":31,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":71,"losses":59,"wins":158},"z-ai/glm-5.3":{"draws":27,"losses":79,"wins":32},"z-ai/glm-5.3-flash":{"draws":20,"losses":65,"wins":59},"z-ai/glm-5.3-flashx":{"draws":25,"losses":61,"wins":58}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":15,"wins":82},"claude-fable-5":{"draws":34,"losses":61,"wins":49},"claude-fable-5-1":{"draws":9,"losses":132,"wins":21},"claude-haiku-5-5":{"draws":36,"losses":42,"wins":60},"claude-opus-4-5":{"draws":59,"losses":52,"wins":123},"claude-opus-4-8":{"draws":32,"losses":42,"wins":58},"claude-opus-5":{"draws":36,"losses":159,"wins":50},"claude-opus-5-5":{"draws":17,"losses":124,"wins":15},"claude-sonnet-5":{"draws":39,"losses":32,"wins":73},"claude-sonnet-5-5":{"draws":24,"losses":61,"wins":59},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":41},"deepseek/deepseek-v4-flash":{"draws":54,"losses":22,"wins":140},"deepseek/deepseek-v4-pro":{"draws":33,"losses":26,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":29,"wins":62},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":19,"losses":30,"wins":25},"elorian/glimpse":{"draws":9,"losses":12,"wins":17},"fireworks/ember-1":{"draws":40,"losses":43,"wins":61},"gemini-3.1-pro-preview":{"draws":40,"losses":28,"wins":76},"gemini-4-argon":{"draws":14,"losses":54,"wins":12},"google/gemini-3.1-flash-lite":{"draws":18,"losses":6,"wins":72},"google/gemini-3.5-flash":{"draws":48,"losses":35,"wins":97},"google/gemini-3.5-flash-lite":{"draws":59,"losses":31,"wins":162},"google/gemini-3.6-flash":{"draws":71,"losses":82,"wins":123},"google/gemini-3.8-flash":{"draws":40,"losses":51,"wins":53},"google/gemma-4-31b-it":{"draws":24,"losses":6,"wins":54},"gpt-4.1":{"draws":19,"losses":6,"wins":23},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":36,"losses":19,"wins":71},"gpt-5.4":{"draws":40,"losses":47,"wins":51},"gpt-5.4-mini":{"draws":32,"losses":14,"wins":50},"gpt-5.4-nano":{"draws":23,"losses":24,"wins":97},"gpt-5.5":{"draws":41,"losses":36,"wins":55},"gpt-5.6-luna":{"draws":37,"losses":23,"wins":84},"gpt-5.6-sol":{"draws":28,"losses":60,"wins":56},"gpt-5.6-terra":{"draws":46,"losses":21,"wins":71},"gpt-6-astra":{"draws":11,"losses":119,"wins":14},"gpt-6-luna":{"draws":39,"losses":24,"wins":81},"gpt-6-sol":{"draws":21,"losses":92,"wins":31},"gpt-6.1-sol":{"draws":16,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":64},"inception/mercury-3":{"draws":17,"losses":8,"wins":23},"inclusionai/ling-3.0-flash":{"draws":35,"losses":5,"wins":62},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":40,"losses":21,"wins":95},"meta/muse-glimmer-30b":{"draws":40,"losses":8,"wins":78},"meta/muse-spark-1.2":{"draws":30,"losses":32,"wins":76},"meta/muse-spark-1.3":{"draws":32,"losses":53,"wins":59},"meta/muse-spark-open":{"draws":13,"losses":25,"wins":30},"meta/muse-wonder":{"draws":41,"losses":62,"wins":41},"minimax/minimax-m3":{"draws":20,"losses":4,"wins":54},"minimax/minimax-m3.1-flash":{"draws":21,"losses":17,"wins":32},"mistralai/mistral-large-4-0":{"draws":30,"losses":17,"wins":43},"mistralai/mistral-medium-3-5":{"draws":27,"losses":6,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":8,"wins":18},"moonshotai/kimi-k3":{"draws":34,"losses":34,"wins":70},"nex-agi/nex-n2-pro":{"draws":18,"losses":3,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":13,"wins":66},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":21},"o3":{"draws":36,"losses":44,"wins":118},"openai/gpt-oss-120b":{"draws":37,"losses":10,"wins":79},"poolside/laguna-s-2.1":{"draws":39,"losses":15,"wins":84},"qwen/qwen3.7-max":{"draws":21,"losses":16,"wins":47},"qwen/qwen3.7-plus":{"draws":21,"losses":6,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":49,"wins":61},"qwen/qwen3.8-27b":{"draws":27,"losses":23,"wins":52},"qwen/qwen3.8-flash":{"draws":36,"losses":16,"wins":44},"qwen/qwen3.8-max":{"draws":40,"losses":40,"wins":64},"qwen/qwen3.8-max-0902":{"draws":44,"losses":34,"wins":66},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":16,"wins":33},"stealth/ox-alpha":{"draws":137,"losses":145,"wins":192},"stealth/space-bunny-alpha":{"draws":36,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":67},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":22,"losses":10,"wins":46},"tencent/hy4-preview":{"draws":43,"losses":33,"wins":62},"thinkingmachines/inkling":{"draws":64,"losses":21,"wins":107},"thinkingmachines/inkling-small":{"draws":44,"losses":16,"wins":84},"unbiased/pareto-26.10":{"draws":6,"losses":25,"wins":1},"unbiased/pareto-26.10-preview":{"draws":4,"losses":40,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":42,"losses":48,"wins":54},"x-ai/grok-4.6":{"draws":38,"losses":29,"wins":29},"x-ai/grok-4.7":{"draws":16,"losses":79,"wins":31},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":27},"xiaomi/mimo-v2.5":{"draws":74,"losses":19,"wins":129},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":10,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":32,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":41,"wins":34},"z-ai/glm-5.2":{"draws":78,"losses":49,"wins":161},"z-ai/glm-5.3":{"draws":29,"losses":66,"wins":43},"z-ai/glm-5.3-flash":{"draws":35,"losses":50,"wins":59},"z-ai/glm-5.3-flashx":{"draws":33,"losses":52,"wins":59}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":17,"wins":91},"claude-fable-5":{"draws":7,"losses":44,"wins":75},"claude-fable-5-1":{"draws":6,"losses":96,"wins":38},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":90},"claude-opus-4-5":{"draws":16,"losses":34,"wins":156},"claude-opus-4-8":{"draws":16,"losses":30,"wins":72},"claude-opus-5":{"draws":22,"losses":100,"wins":98},"claude-opus-5-5":{"draws":11,"losses":96,"wins":31},"claude-sonnet-5":{"draws":12,"losses":24,"wins":90},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":64},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":45},"deepseek/deepseek-v4-flash":{"draws":20,"losses":15,"wins":157},"deepseek/deepseek-v4-pro":{"draws":10,"losses":21,"wins":85},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":22,"wins":83},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":32,"wins":83},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":39},"elorian/glimpse":{"draws":5,"losses":6,"wins":13},"fireworks/ember-1":{"draws":11,"losses":27,"wins":88},"gemini-3.1-pro-preview":{"draws":13,"losses":23,"wins":90},"gemini-4-argon":{"draws":10,"losses":34,"wins":12},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":78},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":119},"google/gemini-3.5-flash-lite":{"draws":21,"losses":28,"wins":169},"google/gemini-3.6-flash":{"draws":14,"losses":54,"wins":172},"google/gemini-3.8-flash":{"draws":13,"losses":27,"wins":86},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":62},"gpt-4.1":{"draws":4,"losses":4,"wins":34},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":10},"gpt-5":{"draws":10,"losses":18,"wins":84},"gpt-5.4":{"draws":13,"losses":28,"wins":79},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":66},"gpt-5.4-nano":{"draws":16,"losses":11,"wins":105},"gpt-5.5":{"draws":11,"losses":36,"wins":69},"gpt-5.6-luna":{"draws":13,"losses":17,"wins":96},"gpt-5.6-sol":{"draws":16,"losses":42,"wins":68},"gpt-5.6-terra":{"draws":13,"losses":21,"wins":86},"gpt-6-astra":{"draws":12,"losses":92,"wins":22},"gpt-6-luna":{"draws":10,"losses":20,"wins":96},"gpt-6-sol":{"draws":13,"losses":53,"wins":60},"gpt-6.1-sol":{"draws":6,"losses":79,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":72},"inception/mercury-3":{"draws":6,"losses":4,"wins":34},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":74},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":120},"meta/muse-glimmer-30b":{"draws":6,"losses":13,"wins":93},"meta/muse-spark-1.2":{"draws":9,"losses":28,"wins":85},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":83},"meta/muse-spark-open":{"draws":5,"losses":12,"wins":39},"meta/muse-wonder":{"draws":16,"losses":38,"wins":72},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":61},"minimax/minimax-m3.1-flash":{"draws":5,"losses":12,"wins":45},"mistralai/mistral-large-4-0":{"draws":14,"losses":16,"wins":50},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":24},"moonshotai/kimi-k3":{"draws":13,"losses":27,"wins":82},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":54},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":98},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":4,"wins":22},"o3":{"draws":12,"losses":36,"wins":130},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":99},"poolside/laguna-s-2.1":{"draws":11,"losses":14,"wins":99},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":51},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":30,"wins":86},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":58},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":63},"qwen/qwen3.8-max":{"draws":12,"losses":26,"wins":88},"qwen/qwen3.8-max-0902":{"draws":18,"losses":28,"wins":80},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":5,"wins":47},"stealth/ox-alpha":{"draws":46,"losses":74,"wins":280},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":73},"stepfun/step-3.7-flash":{"draws":5,"losses":10,"wins":75},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":12,"losses":3,"wins":55},"tencent/hy4-preview":{"draws":12,"losses":35,"wins":73},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":134},"thinkingmachines/inkling-small":{"draws":15,"losses":2,"wins":109},"unbiased/pareto-26.10":{"draws":4,"losses":12,"wins":6},"unbiased/pareto-26.10-preview":{"draws":3,"losses":31,"wins":8},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":23},"x-ai/grok-4.5":{"draws":16,"losses":28,"wins":82},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":79},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":35},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":35},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":18,"wins":55},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":58},"z-ai/glm-5.2":{"draws":29,"losses":37,"wins":186},"z-ai/glm-5.3":{"draws":16,"losses":33,"wins":71},"z-ai/glm-5.3-flash":{"draws":15,"losses":34,"wins":77},"z-ai/glm-5.3-flashx":{"draws":15,"losses":28,"wins":83}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":18,"wins":10},"claude-fable-5":{"draws":11,"losses":31,"wins":6},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":27,"losses":40,"wins":11},"claude-opus-4-8":{"draws":10,"losses":28,"wins":6},"claude-opus-5":{"draws":13,"losses":65,"wins":4},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":19,"losses":26,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":27,"wins":18},"deepseek/deepseek-v4-pro":{"draws":18,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":19,"wins":5},"elorian/glimpse":{"draws":4,"losses":10,"wins":6},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"gemini-4-argon":{"draws":0,"losses":27,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":20,"losses":31,"wins":9},"google/gemini-3.5-flash-lite":{"draws":34,"losses":26,"wins":24},"google/gemini-3.6-flash":{"draws":30,"losses":57,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":9},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":18,"wins":9},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":23,"wins":14},"gpt-5.5":{"draws":23,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":24,"wins":5},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":8,"wins":8},"inception/mercury-3":{"draws":4,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":16,"wins":17},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":14},"meta/muse-spark-1.2":{"draws":10,"losses":28,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":6,"losses":17,"wins":3},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":8,"wins":10},"minimax/minimax-m3.1-flash":{"draws":10,"losses":14,"wins":4},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":9,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":10,"wins":2},"o3":{"draws":13,"losses":38,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":21,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":17,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":11,"wins":1},"stealth/ox-alpha":{"draws":40,"losses":100,"wins":18},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":5},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":26},"thinkingmachines/inkling-small":{"draws":20,"losses":14,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":20,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":42,"losses":36,"wins":18},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":72,"losses":80,"wins":52},"claude-fable-5":{"draws":45,"losses":172,"wins":5},"claude-fable-5-1":{"draws":12,"losses":227,"wins":5},"claude-haiku-5-5":{"draws":56,"losses":133,"wins":31},"claude-opus-4-5":{"draws":132,"losses":183,"wins":53},"claude-opus-4-8":{"draws":63,"losses":131,"wins":24},"claude-opus-5":{"draws":57,"losses":295,"wins":26},"claude-opus-5-5":{"draws":11,"losses":227,"wins":4},"claude-sonnet-5":{"draws":81,"losses":103,"wins":38},"claude-sonnet-5-5":{"draws":49,"losses":146,"wins":27},"cohere/north-mini-code":{"draws":21,"losses":28,"wins":31},"deepseek/deepseek-v4-flash":{"draws":117,"losses":109,"wins":108},"deepseek/deepseek-v4-pro":{"draws":73,"losses":98,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":69,"losses":96,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":75,"losses":118,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":90,"wins":9},"elorian/glimpse":{"draws":21,"losses":22,"wins":7},"fireworks/ember-1":{"draws":83,"losses":112,"wins":27},"gemini-3.1-pro-preview":{"draws":73,"losses":100,"wins":49},"gemini-4-argon":{"draws":5,"losses":84,"wins":1},"google/gemini-3.1-flash-lite":{"draws":58,"losses":36,"wins":68},"google/gemini-3.5-flash":{"draws":84,"losses":150,"wins":50},"google/gemini-3.5-flash-lite":{"draws":119,"losses":142,"wins":131},"google/gemini-3.6-flash":{"draws":129,"losses":246,"wins":49},"google/gemini-3.8-flash":{"draws":61,"losses":141,"wins":20},"google/gemma-4-31b-it":{"draws":61,"losses":32,"wins":41},"gpt-4.1":{"draws":29,"losses":28,"wins":17},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":9},"gpt-5":{"draws":58,"losses":93,"wins":39},"gpt-5.4":{"draws":57,"losses":134,"wins":21},"gpt-5.4-mini":{"draws":57,"losses":51,"wins":40},"gpt-5.4-nano":{"draws":55,"losses":107,"wins":74},"gpt-5.5":{"draws":85,"losses":97,"wins":20},"gpt-5.6-luna":{"draws":91,"losses":84,"wins":47},"gpt-5.6-sol":{"draws":36,"losses":174,"wins":12},"gpt-5.6-terra":{"draws":79,"losses":118,"wins":15},"gpt-6-astra":{"draws":13,"losses":207,"wins":2},"gpt-6-luna":{"draws":79,"losses":114,"wins":29},"gpt-6-sol":{"draws":35,"losses":170,"wins":17},"gpt-6.1-sol":{"draws":19,"losses":195,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":78,"losses":21,"wins":67},"inception/mercury-3":{"draws":27,"losses":33,"wins":6},"inclusionai/ling-3.0-flash":{"draws":71,"losses":34,"wins":55},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":77,"losses":82,"wins":79},"meta/muse-glimmer-30b":{"draws":80,"losses":62,"wins":50},"meta/muse-spark-1.2":{"draws":62,"losses":123,"wins":27},"meta/muse-spark-1.3":{"draws":55,"losses":148,"wins":19},"meta/muse-spark-open":{"draws":32,"losses":91,"wins":9},"meta/muse-wonder":{"draws":45,"losses":160,"wins":17},"minimax/minimax-m3":{"draws":43,"losses":41,"wins":40},"minimax/minimax-m3.1-flash":{"draws":27,"losses":53,"wins":38},"mistralai/mistral-large-4-0":{"draws":58,"losses":61,"wins":19},"mistralai/mistral-medium-3-5":{"draws":58,"losses":25,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":21,"losses":30,"wins":11},"moonshotai/kimi-k3":{"draws":75,"losses":106,"wins":31},"nex-agi/nex-n2-pro":{"draws":30,"losses":26,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":87,"losses":64,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":21,"losses":33,"wins":10},"o3":{"draws":57,"losses":195,"wins":64},"openai/gpt-oss-120b":{"draws":66,"losses":68,"wins":54},"poolside/laguna-s-2.1":{"draws":66,"losses":79,"wins":57},"qwen/qwen3.7-max":{"draws":53,"losses":54,"wins":27},"qwen/qwen3.7-plus":{"draws":42,"losses":43,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":88,"losses":109,"wins":25},"qwen/qwen3.8-27b":{"draws":44,"losses":87,"wins":29},"qwen/qwen3.8-flash":{"draws":60,"losses":57,"wins":31},"qwen/qwen3.8-max":{"draws":76,"losses":105,"wins":41},"qwen/qwen3.8-max-0902":{"draws":83,"losses":111,"wins":28},"reflection/beam-1.0-501b-a23b":{"draws":38,"losses":44,"wins":12},"stealth/ox-alpha":{"draws":172,"losses":380,"wins":94},"stealth/space-bunny-alpha":{"draws":71,"losses":69,"wins":38},"stepfun/step-3.7-flash":{"draws":44,"losses":58,"wins":54},"stepfun/step-5-preview":{"draws":8,"losses":12,"wins":0},"tencent/hy3-preview":{"draws":48,"losses":47,"wins":33},"tencent/hy4-preview":{"draws":69,"losses":123,"wins":20},"thinkingmachines/inkling":{"draws":95,"losses":82,"wins":113},"thinkingmachines/inkling-small":{"draws":91,"losses":60,"wins":71},"unbiased/pareto-26.10":{"draws":4,"losses":42,"wins":0},"unbiased/pareto-26.10-preview":{"draws":4,"losses":70,"wins":0},"upstage/solar-mini4":{"draws":16,"losses":30,"wins":16},"x-ai/grok-4.5":{"draws":59,"losses":145,"wins":18},"x-ai/grok-4.6":{"draws":74,"losses":129,"wins":19},"x-ai/grok-4.7":{"draws":22,"losses":160,"wins":16},"x-ai/grok-build-0.1":{"draws":31,"losses":23,"wins":20},"xiaomi/mimo-v2.5":{"draws":120,"losses":92,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":42,"losses":58,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":38,"losses":83,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":36,"losses":98,"wins":14},"z-ai/glm-5.2":{"draws":166,"losses":188,"wins":90},"z-ai/glm-5.3":{"draws":47,"losses":159,"wins":4},"z-ai/glm-5.3-flash":{"draws":52,"losses":134,"wins":36},"z-ai/glm-5.3-flashx":{"draws":72,"losses":134,"wins":16}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":23,"wins":24},"claude-fable-5":{"draws":9,"losses":65,"wins":4},"claude-fable-5-1":{"draws":2,"losses":84,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":41,"wins":18},"claude-opus-4-5":{"draws":31,"losses":59,"wins":38},"claude-opus-4-8":{"draws":16,"losses":43,"wins":15},"claude-opus-5":{"draws":13,"losses":110,"wins":5},"claude-opus-5-5":{"draws":3,"losses":82,"wins":1},"claude-sonnet-5":{"draws":13,"losses":44,"wins":21},"claude-sonnet-5-5":{"draws":15,"losses":50,"wins":13},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":15},"deepseek/deepseek-v4-flash":{"draws":36,"losses":39,"wins":45},"deepseek/deepseek-v4-pro":{"draws":13,"losses":37,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":37,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":36,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":36,"wins":13},"elorian/glimpse":{"draws":2,"losses":13,"wins":11},"fireworks/ember-1":{"draws":25,"losses":35,"wins":18},"gemini-3.1-pro-preview":{"draws":20,"losses":33,"wins":25},"gemini-4-argon":{"draws":1,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":45},"google/gemini-3.5-flash":{"draws":22,"losses":48,"wins":30},"google/gemini-3.5-flash-lite":{"draws":39,"losses":50,"wins":49},"google/gemini-3.6-flash":{"draws":33,"losses":88,"wins":29},"google/gemini-3.8-flash":{"draws":17,"losses":49,"wins":12},"google/gemma-4-31b-it":{"draws":19,"losses":5,"wins":22},"gpt-4.1":{"draws":7,"losses":12,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":20,"losses":29,"wins":21},"gpt-5.4":{"draws":13,"losses":50,"wins":13},"gpt-5.4-mini":{"draws":15,"losses":20,"wins":17},"gpt-5.4-nano":{"draws":18,"losses":31,"wins":37},"gpt-5.5":{"draws":24,"losses":36,"wins":12},"gpt-5.6-luna":{"draws":28,"losses":22,"wins":28},"gpt-5.6-sol":{"draws":10,"losses":54,"wins":14},"gpt-5.6-terra":{"draws":19,"losses":43,"wins":12},"gpt-6-astra":{"draws":3,"losses":74,"wins":1},"gpt-6-luna":{"draws":20,"losses":40,"wins":18},"gpt-6-sol":{"draws":5,"losses":64,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":70,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":12,"wins":25},"inception/mercury-3":{"draws":13,"losses":11,"wins":10},"inclusionai/ling-3.0-flash":{"draws":22,"losses":7,"wins":27},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":21,"wins":41},"meta/muse-glimmer-30b":{"draws":25,"losses":15,"wins":28},"meta/muse-spark-1.2":{"draws":10,"losses":43,"wins":21},"meta/muse-spark-1.3":{"draws":10,"losses":54,"wins":14},"meta/muse-spark-open":{"draws":4,"losses":18,"wins":2},"meta/muse-wonder":{"draws":7,"losses":56,"wins":15},"minimax/minimax-m3":{"draws":11,"losses":13,"wins":20},"minimax/minimax-m3.1-flash":{"draws":7,"losses":20,"wins":17},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":15,"losses":6,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":11,"wins":5},"moonshotai/kimi-k3":{"draws":18,"losses":33,"wins":23},"nex-agi/nex-n2-pro":{"draws":12,"losses":9,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":15,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":12,"wins":7},"o3":{"draws":18,"losses":60,"wins":44},"openai/gpt-oss-120b":{"draws":20,"losses":21,"wins":27},"poolside/laguna-s-2.1":{"draws":25,"losses":26,"wins":25},"qwen/qwen3.7-max":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":8,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":42,"wins":19},"qwen/qwen3.8-27b":{"draws":10,"losses":26,"wins":20},"qwen/qwen3.8-flash":{"draws":15,"losses":25,"wins":12},"qwen/qwen3.8-max":{"draws":11,"losses":44,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":40,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":19,"wins":7},"stealth/ox-alpha":{"draws":48,"losses":136,"wins":58},"stealth/space-bunny-alpha":{"draws":24,"losses":23,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":16,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":14,"wins":14},"tencent/hy4-preview":{"draws":18,"losses":44,"wins":14},"thinkingmachines/inkling":{"draws":22,"losses":24,"wins":58},"thinkingmachines/inkling-small":{"draws":28,"losses":17,"wins":33},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":13,"losses":44,"wins":21},"x-ai/grok-4.6":{"draws":18,"losses":50,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":60,"wins":7},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":42,"losses":24,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":27,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":29,"wins":16},"z-ai/glm-5.2":{"draws":52,"losses":55,"wins":49},"z-ai/glm-5.3":{"draws":14,"losses":55,"wins":5},"z-ai/glm-5.3-flash":{"draws":12,"losses":53,"wins":13},"z-ai/glm-5.3-flashx":{"draws":24,"losses":40,"wins":14}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":49},"claude-fable-5":{"draws":17,"losses":51,"wins":22},"claude-fable-5-1":{"draws":5,"losses":84,"wins":11},"claude-haiku-5-5":{"draws":21,"losses":38,"wins":27},"claude-opus-4-5":{"draws":33,"losses":45,"wins":68},"claude-opus-4-8":{"draws":16,"losses":28,"wins":38},"claude-opus-5":{"draws":16,"losses":119,"wins":17},"claude-opus-5-5":{"draws":9,"losses":87,"wins":2},"claude-sonnet-5":{"draws":16,"losses":24,"wins":50},"claude-sonnet-5-5":{"draws":10,"losses":46,"wins":34},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":22},"deepseek/deepseek-v4-flash":{"draws":31,"losses":24,"wins":83},"deepseek/deepseek-v4-pro":{"draws":19,"losses":28,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":37,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":33,"wins":32},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":26,"wins":7},"elorian/glimpse":{"draws":3,"losses":3,"wins":8},"fireworks/ember-1":{"draws":18,"losses":36,"wins":36},"gemini-3.1-pro-preview":{"draws":17,"losses":31,"wins":42},"gemini-4-argon":{"draws":1,"losses":39,"wins":2},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":44},"google/gemini-3.5-flash":{"draws":20,"losses":40,"wins":52},"google/gemini-3.5-flash-lite":{"draws":27,"losses":24,"wins":105},"google/gemini-3.6-flash":{"draws":25,"losses":76,"wins":71},"google/gemini-3.8-flash":{"draws":22,"losses":40,"wins":28},"google/gemma-4-31b-it":{"draws":11,"losses":9,"wins":32},"gpt-4.1":{"draws":10,"losses":3,"wins":17},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":16,"losses":27,"wins":37},"gpt-5.4":{"draws":23,"losses":36,"wins":27},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":32},"gpt-5.4-nano":{"draws":25,"losses":19,"wins":50},"gpt-5.5":{"draws":26,"losses":33,"wins":23},"gpt-5.6-luna":{"draws":22,"losses":25,"wins":43},"gpt-5.6-sol":{"draws":9,"losses":62,"wins":19},"gpt-5.6-terra":{"draws":20,"losses":34,"wins":32},"gpt-6-astra":{"draws":3,"losses":81,"wins":6},"gpt-6-luna":{"draws":22,"losses":33,"wins":35},"gpt-6-sol":{"draws":10,"losses":62,"wins":18},"gpt-6.1-sol":{"draws":4,"losses":79,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":41},"inception/mercury-3":{"draws":6,"losses":14,"wins":12},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":41},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":18,"wins":56},"meta/muse-glimmer-30b":{"draws":19,"losses":16,"wins":43},"meta/muse-spark-1.2":{"draws":11,"losses":47,"wins":28},"meta/muse-spark-1.3":{"draws":13,"losses":52,"wins":25},"meta/muse-spark-open":{"draws":5,"losses":34,"wins":15},"meta/muse-wonder":{"draws":5,"losses":63,"wins":22},"minimax/minimax-m3":{"draws":12,"losses":10,"wins":28},"minimax/minimax-m3.1-flash":{"draws":10,"losses":18,"wins":30},"mistralai/mistral-large-4-0":{"draws":17,"losses":19,"wins":20},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":11},"moonshotai/kimi-k3":{"draws":23,"losses":31,"wins":32},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":15,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":7},"o3":{"draws":18,"losses":36,"wins":74},"openai/gpt-oss-120b":{"draws":20,"losses":7,"wins":53},"poolside/laguna-s-2.1":{"draws":25,"losses":14,"wins":51},"qwen/qwen3.7-max":{"draws":15,"losses":11,"wins":28},"qwen/qwen3.7-plus":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":33,"wins":35},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":26},"qwen/qwen3.8-flash":{"draws":16,"losses":22,"wins":22},"qwen/qwen3.8-max":{"draws":21,"losses":31,"wins":38},"qwen/qwen3.8-max-0902":{"draws":19,"losses":32,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":25,"wins":18},"stealth/ox-alpha":{"draws":57,"losses":131,"wins":110},"stealth/space-bunny-alpha":{"draws":18,"losses":16,"wins":36},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":44},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":26},"tencent/hy4-preview":{"draws":14,"losses":37,"wins":35},"thinkingmachines/inkling":{"draws":30,"losses":21,"wins":69},"thinkingmachines/inkling-small":{"draws":27,"losses":9,"wins":54},"unbiased/pareto-26.10":{"draws":2,"losses":11,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":29,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":13,"losses":46,"wins":31},"x-ai/grok-4.6":{"draws":19,"losses":39,"wins":32},"x-ai/grok-4.7":{"draws":7,"losses":55,"wins":18},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":38,"losses":15,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":9,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":30,"wins":17},"z-ai/glm-5.2":{"draws":39,"losses":50,"wins":91},"z-ai/glm-5.3":{"draws":14,"losses":54,"wins":18},"z-ai/glm-5.3-flash":{"draws":15,"losses":44,"wins":31},"z-ai/glm-5.3-flashx":{"draws":21,"losses":35,"wins":34}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":57},"claude-fable-5":{"draws":7,"losses":48,"wins":41},"claude-fable-5-1":{"draws":14,"losses":84,"wins":10},"claude-haiku-5-5":{"draws":17,"losses":32,"wins":43},"claude-opus-4-5":{"draws":39,"losses":32,"wins":85},"claude-opus-4-8":{"draws":11,"losses":35,"wins":42},"claude-opus-5":{"draws":26,"losses":99,"wins":39},"claude-opus-5-5":{"draws":10,"losses":80,"wins":14},"claude-sonnet-5":{"draws":15,"losses":24,"wins":57},"claude-sonnet-5-5":{"draws":13,"losses":46,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":31},"deepseek/deepseek-v4-flash":{"draws":25,"losses":24,"wins":95},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":27,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":30,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":22,"wins":23},"elorian/glimpse":{"draws":4,"losses":11,"wins":5},"fireworks/ember-1":{"draws":21,"losses":30,"wins":45},"gemini-3.1-pro-preview":{"draws":16,"losses":24,"wins":56},"gemini-4-argon":{"draws":2,"losses":40,"wins":10},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":50},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":62},"google/gemini-3.5-flash-lite":{"draws":21,"losses":29,"wins":118},"google/gemini-3.6-flash":{"draws":38,"losses":60,"wins":86},"google/gemini-3.8-flash":{"draws":20,"losses":28,"wins":48},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":41},"gpt-4.1":{"draws":6,"losses":7,"wins":19},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":8},"gpt-5":{"draws":11,"losses":22,"wins":51},"gpt-5.4":{"draws":17,"losses":37,"wins":38},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":40},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":66},"gpt-5.5":{"draws":20,"losses":31,"wins":37},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":62},"gpt-5.6-sol":{"draws":17,"losses":44,"wins":35},"gpt-5.6-terra":{"draws":24,"losses":24,"wins":44},"gpt-6-astra":{"draws":9,"losses":80,"wins":7},"gpt-6-luna":{"draws":19,"losses":27,"wins":50},"gpt-6-sol":{"draws":18,"losses":54,"wins":24},"gpt-6.1-sol":{"draws":14,"losses":62,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":1,"wins":48},"inception/mercury-3":{"draws":6,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":49},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":19,"losses":11,"wins":74},"meta/muse-glimmer-30b":{"draws":15,"losses":13,"wins":56},"meta/muse-spark-1.2":{"draws":11,"losses":27,"wins":54},"meta/muse-spark-1.3":{"draws":15,"losses":32,"wins":49},"meta/muse-spark-open":{"draws":9,"losses":17,"wins":20},"meta/muse-wonder":{"draws":17,"losses":43,"wins":36},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":37},"minimax/minimax-m3.1-flash":{"draws":12,"losses":9,"wins":27},"mistralai/mistral-large-4-0":{"draws":13,"losses":19,"wins":28},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":16},"moonshotai/kimi-k3":{"draws":18,"losses":25,"wins":49},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":10,"wins":9},"o3":{"draws":11,"losses":26,"wins":95},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":62},"poolside/laguna-s-2.1":{"draws":10,"losses":18,"wins":64},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":34},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":31,"wins":41},"qwen/qwen3.8-27b":{"draws":12,"losses":20,"wins":36},"qwen/qwen3.8-flash":{"draws":13,"losses":16,"wins":35},"qwen/qwen3.8-max":{"draws":25,"losses":19,"wins":52},"qwen/qwen3.8-max-0902":{"draws":14,"losses":30,"wins":52},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":12,"wins":23},"stealth/ox-alpha":{"draws":57,"losses":105,"wins":154},"stealth/space-bunny-alpha":{"draws":19,"losses":19,"wins":38},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":52},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":9,"losses":10,"wins":33},"tencent/hy4-preview":{"draws":16,"losses":33,"wins":43},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":89},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":71},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":6},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":16},"x-ai/grok-4.5":{"draws":17,"losses":35,"wins":44},"x-ai/grok-4.6":{"draws":21,"losses":34,"wins":41},"x-ai/grok-4.7":{"draws":6,"losses":58,"wins":20},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":22},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":17,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":15},"z-ai/glm-5.2":{"draws":49,"losses":37,"wins":106},"z-ai/glm-5.3":{"draws":15,"losses":43,"wins":34},"z-ai/glm-5.3-flash":{"draws":16,"losses":30,"wins":50},"z-ai/glm-5.3-flashx":{"draws":17,"losses":35,"wins":44}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":96,"losses":72,"wins":96},"claude-fable-5":{"draws":61,"losses":184,"wins":43},"claude-fable-5-1":{"draws":20,"losses":296,"wins":8},"claude-haiku-5-5":{"draws":64,"losses":148,"wins":64},"claude-opus-4-5":{"draws":149,"losses":185,"wins":134},"claude-opus-4-8":{"draws":74,"losses":133,"wins":57},"claude-opus-5":{"draws":74,"losses":385,"wins":33},"claude-opus-5-5":{"draws":18,"losses":282,"wins":12},"claude-sonnet-5":{"draws":79,"losses":121,"wins":88},"claude-sonnet-5-5":{"draws":55,"losses":167,"wins":66},"cohere/north-mini-code":{"draws":30,"losses":18,"wins":60},"deepseek/deepseek-v4-flash":{"draws":151,"losses":102,"wins":179},"deepseek/deepseek-v4-pro":{"draws":90,"losses":99,"wins":75},"deepseek/deepseek-v4-pro-0813":{"draws":89,"losses":94,"wins":81},"deepseek/deepseek-v4.1-flash":{"draws":103,"losses":122,"wins":63},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":114,"wins":28},"elorian/glimpse":{"draws":19,"losses":33,"wins":26},"fireworks/ember-1":{"draws":94,"losses":128,"wins":66},"gemini-3.1-pro-preview":{"draws":85,"losses":109,"wins":94},"gemini-4-argon":{"draws":10,"losses":115,"wins":9},"google/gemini-3.1-flash-lite":{"draws":42,"losses":24,"wins":126},"google/gemini-3.5-flash":{"draws":102,"losses":149,"wins":109},"google/gemini-3.5-flash-lite":{"draws":166,"losses":139,"wins":199},"google/gemini-3.6-flash":{"draws":152,"losses":248,"wins":152},"google/gemini-3.8-flash":{"draws":76,"losses":153,"wins":59},"google/gemma-4-31b-it":{"draws":69,"losses":29,"wins":70},"gpt-4.1":{"draws":35,"losses":23,"wins":38},"gpt-4.1-nano":{"draws":21,"losses":0,"wins":15},"gpt-5":{"draws":82,"losses":94,"wins":76},"gpt-5.4":{"draws":81,"losses":136,"wins":59},"gpt-5.4-mini":{"draws":87,"losses":35,"wins":70},"gpt-5.4-nano":{"draws":71,"losses":96,"wins":121},"gpt-5.5":{"draws":101,"losses":115,"wins":48},"gpt-5.6-luna":{"draws":108,"losses":70,"wins":110},"gpt-5.6-sol":{"draws":37,"losses":206,"wins":45},"gpt-5.6-terra":{"draws":117,"losses":96,"wins":63},"gpt-6-astra":{"draws":19,"losses":258,"wins":11},"gpt-6-luna":{"draws":102,"losses":113,"wins":73},"gpt-6-sol":{"draws":43,"losses":211,"wins":34},"gpt-6.1-sol":{"draws":30,"losses":248,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":87,"losses":19,"wins":98},"inception/mercury-3":{"draws":30,"losses":32,"wins":24},"inclusionai/ling-3.0-flash":{"draws":101,"losses":25,"wins":78},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":93,"losses":73,"wins":146},"meta/muse-glimmer-30b":{"draws":114,"losses":43,"wins":95},"meta/muse-spark-1.2":{"draws":65,"losses":136,"wins":75},"meta/muse-spark-1.3":{"draws":58,"losses":162,"wins":68},"meta/muse-spark-open":{"draws":36,"losses":84,"wins":30},"meta/muse-wonder":{"draws":65,"losses":178,"wins":45},"minimax/minimax-m3":{"draws":47,"losses":37,"wins":72},"minimax/minimax-m3.1-flash":{"draws":44,"losses":51,"wins":51},"mistralai/mistral-large-4-0":{"draws":71,"losses":72,"wins":37},"mistralai/mistral-medium-3-5":{"draws":74,"losses":19,"wins":75},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":30,"wins":26},"moonshotai/kimi-k3":{"draws":95,"losses":111,"wins":70},"nex-agi/nex-n2-pro":{"draws":57,"losses":17,"wins":70},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":109,"losses":54,"wins":89},"nvidia/nemotron-3.5-super-vl":{"draws":21,"losses":20,"wins":21},"o3":{"draws":73,"losses":173,"wins":150},"openai/gpt-oss-120b":{"draws":95,"losses":49,"wins":108},"poolside/laguna-s-2.1":{"draws":119,"losses":65,"wins":92},"qwen/qwen3.7-max":{"draws":55,"losses":53,"wins":60},"qwen/qwen3.7-plus":{"draws":45,"losses":31,"wins":68},"qwen/qwen3.8-2.4t-a95b":{"draws":105,"losses":113,"wins":70},"qwen/qwen3.8-27b":{"draws":66,"losses":68,"wins":70},"qwen/qwen3.8-flash":{"draws":71,"losses":67,"wins":54},"qwen/qwen3.8-max":{"draws":97,"losses":114,"wins":77},"qwen/qwen3.8-max-0902":{"draws":97,"losses":134,"wins":57},"reflection/beam-1.0-501b-a23b":{"draws":50,"losses":42,"wins":38},"stealth/ox-alpha":{"draws":255,"losses":473,"wins":220},"stealth/space-bunny-alpha":{"draws":89,"losses":65,"wins":74},"stepfun/step-3.7-flash":{"draws":50,"losses":49,"wins":105},"stepfun/step-5-preview":{"draws":8,"losses":13,"wins":3},"tencent/hy3-preview":{"draws":53,"losses":47,"wins":56},"tencent/hy4-preview":{"draws":75,"losses":145,"wins":56},"thinkingmachines/inkling":{"draws":119,"losses":93,"wins":172},"thinkingmachines/inkling-small":{"draws":109,"losses":56,"wins":123},"unbiased/pareto-26.10":{"draws":3,"losses":56,"wins":1},"unbiased/pareto-26.10-preview":{"draws":4,"losses":88,"wins":4},"upstage/solar-mini4":{"draws":8,"losses":16,"wins":48},"x-ai/grok-4.5":{"draws":71,"losses":158,"wins":59},"x-ai/grok-4.6":{"draws":78,"losses":161,"wins":49},"x-ai/grok-4.7":{"draws":29,"losses":186,"wins":37},"x-ai/grok-build-0.1":{"draws":42,"losses":18,"wins":36},"xiaomi/mimo-v2.5":{"draws":166,"losses":90,"wins":188},"xiaomi/mimo-v2.5-pro":{"draws":52,"losses":49,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":39,"losses":91,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":49,"losses":106,"wins":37},"z-ai/glm-5.2":{"draws":180,"losses":150,"wins":150},"z-ai/glm-5.3":{"draws":64,"losses":173,"wins":39},"z-ai/glm-5.3-flash":{"draws":71,"losses":155,"wins":62},"z-ai/glm-5.3-flashx":{"draws":82,"losses":143,"wins":63}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":17,"wins":84},"claude-fable-5":{"draws":21,"losses":53,"wins":64},"claude-fable-5-1":{"draws":11,"losses":123,"wins":22},"claude-haiku-5-5":{"draws":24,"losses":32,"wins":76},"claude-opus-4-5":{"draws":48,"losses":31,"wins":145},"claude-opus-4-8":{"draws":21,"losses":32,"wins":73},"claude-opus-5":{"draws":33,"losses":138,"wins":63},"claude-opus-5-5":{"draws":9,"losses":116,"wins":25},"claude-sonnet-5":{"draws":28,"losses":19,"wins":91},"claude-sonnet-5-5":{"draws":24,"losses":52,"wins":62},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":44,"losses":12,"wins":150},"deepseek/deepseek-v4-pro":{"draws":23,"losses":25,"wins":78},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":25,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":27,"wins":83},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":28,"wins":37},"elorian/glimpse":{"draws":8,"losses":8,"wins":22},"fireworks/ember-1":{"draws":26,"losses":27,"wins":85},"gemini-3.1-pro-preview":{"draws":25,"losses":30,"wins":83},"gemini-4-argon":{"draws":8,"losses":39,"wins":17},"google/gemini-3.1-flash-lite":{"draws":15,"losses":1,"wins":76},"google/gemini-3.5-flash":{"draws":30,"losses":36,"wins":106},"google/gemini-3.5-flash-lite":{"draws":41,"losses":17,"wins":184},"google/gemini-3.6-flash":{"draws":52,"losses":59,"wins":153},"google/gemini-3.8-flash":{"draws":29,"losses":38,"wins":71},"google/gemma-4-31b-it":{"draws":22,"losses":7,"wins":53},"gpt-4.1":{"draws":7,"losses":8,"wins":31},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":11},"gpt-5":{"draws":18,"losses":22,"wins":80},"gpt-5.4":{"draws":25,"losses":38,"wins":69},"gpt-5.4-mini":{"draws":21,"losses":9,"wins":62},"gpt-5.4-nano":{"draws":20,"losses":21,"wins":95},"gpt-5.5":{"draws":31,"losses":23,"wins":72},"gpt-5.6-luna":{"draws":28,"losses":15,"wins":95},"gpt-5.6-sol":{"draws":23,"losses":60,"wins":55},"gpt-5.6-terra":{"draws":36,"losses":21,"wins":75},"gpt-6-astra":{"draws":18,"losses":109,"wins":11},"gpt-6-luna":{"draws":26,"losses":27,"wins":85},"gpt-6-sol":{"draws":21,"losses":70,"wins":47},"gpt-6.1-sol":{"draws":21,"losses":92,"wins":25},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":28,"losses":3,"wins":69},"inception/mercury-3":{"draws":17,"losses":7,"wins":24},"inclusionai/ling-3.0-flash":{"draws":22,"losses":3,"wins":71},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":26,"losses":11,"wins":115},"meta/muse-glimmer-30b":{"draws":25,"losses":12,"wins":83},"meta/muse-spark-1.2":{"draws":22,"losses":42,"wins":68},"meta/muse-spark-1.3":{"draws":25,"losses":40,"wins":73},"meta/muse-spark-open":{"draws":11,"losses":17,"wins":42},"meta/muse-wonder":{"draws":17,"losses":62,"wins":59},"minimax/minimax-m3":{"draws":16,"losses":6,"wins":52},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":41},"mistralai/mistral-large-4-0":{"draws":15,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":63},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":4,"wins":21},"moonshotai/kimi-k3":{"draws":29,"losses":37,"wins":66},"nex-agi/nex-n2-pro":{"draws":13,"losses":3,"wins":56},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":13,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":31},"o3":{"draws":18,"losses":35,"wins":135},"openai/gpt-oss-120b":{"draws":31,"losses":4,"wins":87},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":92},"qwen/qwen3.7-max":{"draws":19,"losses":13,"wins":48},"qwen/qwen3.7-plus":{"draws":15,"losses":6,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":28,"wins":83},"qwen/qwen3.8-27b":{"draws":26,"losses":12,"wins":58},"qwen/qwen3.8-flash":{"draws":25,"losses":14,"wins":53},"qwen/qwen3.8-max":{"draws":28,"losses":30,"wins":80},"qwen/qwen3.8-max-0902":{"draws":35,"losses":30,"wins":73},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":12,"wins":41},"stealth/ox-alpha":{"draws":82,"losses":118,"wins":258},"stealth/space-bunny-alpha":{"draws":25,"losses":9,"wins":76},"stepfun/step-3.7-flash":{"draws":15,"losses":3,"wins":78},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":6},"tencent/hy3-preview":{"draws":14,"losses":10,"wins":50},"tencent/hy4-preview":{"draws":23,"losses":24,"wins":85},"thinkingmachines/inkling":{"draws":35,"losses":20,"wins":127},"thinkingmachines/inkling-small":{"draws":25,"losses":10,"wins":103},"unbiased/pareto-26.10":{"draws":4,"losses":18,"wins":2},"unbiased/pareto-26.10-preview":{"draws":4,"losses":37,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":32},"x-ai/grok-4.5":{"draws":27,"losses":32,"wins":79},"x-ai/grok-4.6":{"draws":29,"losses":43,"wins":66},"x-ai/grok-4.7":{"draws":16,"losses":71,"wins":33},"x-ai/grok-build-0.1":{"draws":11,"losses":1,"wins":34},"xiaomi/mimo-v2.5":{"draws":47,"losses":4,"wins":159},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":5,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":18,"wins":54},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":34,"wins":43},"z-ai/glm-5.2":{"draws":64,"losses":39,"wins":173},"z-ai/glm-5.3":{"draws":20,"losses":34,"wins":34},"z-ai/glm-5.3-flash":{"draws":32,"losses":32,"wins":74},"z-ai/glm-5.3-flashx":{"draws":27,"losses":33,"wins":78}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":28,"wins":75},"claude-fable-5":{"draws":24,"losses":76,"wins":44},"claude-fable-5-1":{"draws":8,"losses":139,"wins":15},"claude-haiku-5-5":{"draws":27,"losses":54,"wins":57},"claude-opus-4-5":{"draws":55,"losses":56,"wins":123},"claude-opus-4-8":{"draws":20,"losses":51,"wins":61},"claude-opus-5":{"draws":37,"losses":163,"wins":46},"claude-opus-5-5":{"draws":13,"losses":133,"wins":10},"claude-sonnet-5":{"draws":25,"losses":41,"wins":78},"claude-sonnet-5-5":{"draws":20,"losses":69,"wins":55},"cohere/north-mini-code":{"draws":6,"losses":12,"wins":36},"deepseek/deepseek-v4-flash":{"draws":54,"losses":41,"wins":121},"deepseek/deepseek-v4-pro":{"draws":22,"losses":36,"wins":74},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":38,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":55,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":51,"wins":23},"elorian/glimpse":{"draws":6,"losses":16,"wins":18},"fireworks/ember-1":{"draws":28,"losses":46,"wins":70},"gemini-3.1-pro-preview":{"draws":36,"losses":42,"wins":66},"gemini-4-argon":{"draws":8,"losses":46,"wins":10},"google/gemini-3.1-flash-lite":{"draws":21,"losses":12,"wins":63},"google/gemini-3.5-flash":{"draws":24,"losses":60,"wins":96},"google/gemini-3.5-flash-lite":{"draws":52,"losses":47,"wins":153},"google/gemini-3.6-flash":{"draws":43,"losses":91,"wins":142},"google/gemini-3.8-flash":{"draws":20,"losses":67,"wins":57},"google/gemma-4-31b-it":{"draws":25,"losses":14,"wins":45},"gpt-4.1":{"draws":6,"losses":14,"wins":28},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":9},"gpt-5":{"draws":21,"losses":31,"wins":74},"gpt-5.4":{"draws":18,"losses":63,"wins":57},"gpt-5.4-mini":{"draws":27,"losses":16,"wins":53},"gpt-5.4-nano":{"draws":21,"losses":38,"wins":85},"gpt-5.5":{"draws":24,"losses":50,"wins":58},"gpt-5.6-luna":{"draws":37,"losses":29,"wins":78},"gpt-5.6-sol":{"draws":25,"losses":72,"wins":47},"gpt-5.6-terra":{"draws":33,"losses":40,"wins":65},"gpt-6-astra":{"draws":11,"losses":125,"wins":8},"gpt-6-luna":{"draws":38,"losses":35,"wins":71},"gpt-6-sol":{"draws":19,"losses":90,"wins":35},"gpt-6.1-sol":{"draws":13,"losses":115,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":24,"losses":13,"wins":65},"inception/mercury-3":{"draws":19,"losses":8,"wins":21},"inclusionai/ling-3.0-flash":{"draws":32,"losses":12,"wins":58},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":27,"losses":32,"wins":97},"meta/muse-glimmer-30b":{"draws":28,"losses":16,"wins":82},"meta/muse-spark-1.2":{"draws":19,"losses":58,"wins":61},"meta/muse-spark-1.3":{"draws":26,"losses":51,"wins":67},"meta/muse-spark-open":{"draws":15,"losses":33,"wins":28},"meta/muse-wonder":{"draws":30,"losses":71,"wins":43},"minimax/minimax-m3":{"draws":17,"losses":14,"wins":47},"minimax/minimax-m3.1-flash":{"draws":9,"losses":28,"wins":45},"mistralai/mistral-large-4-0":{"draws":26,"losses":22,"wins":42},"mistralai/mistral-medium-3-5":{"draws":24,"losses":9,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":17},"moonshotai/kimi-k3":{"draws":32,"losses":43,"wins":63},"nex-agi/nex-n2-pro":{"draws":14,"losses":9,"wins":49},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":34,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":20},"o3":{"draws":24,"losses":75,"wins":99},"openai/gpt-oss-120b":{"draws":27,"losses":20,"wins":79},"poolside/laguna-s-2.1":{"draws":33,"losses":29,"wins":76},"qwen/qwen3.7-max":{"draws":25,"losses":18,"wins":41},"qwen/qwen3.7-plus":{"draws":17,"losses":12,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":48,"wins":65},"qwen/qwen3.8-27b":{"draws":19,"losses":32,"wins":51},"qwen/qwen3.8-flash":{"draws":21,"losses":33,"wins":42},"qwen/qwen3.8-max":{"draws":33,"losses":54,"wins":57},"qwen/qwen3.8-max-0902":{"draws":38,"losses":53,"wins":53},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":32},"stealth/ox-alpha":{"draws":80,"losses":182,"wins":212},"stealth/space-bunny-alpha":{"draws":30,"losses":17,"wins":67},"stepfun/step-3.7-flash":{"draws":15,"losses":20,"wins":67},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":14,"wins":43},"tencent/hy4-preview":{"draws":24,"losses":51,"wins":63},"thinkingmachines/inkling":{"draws":40,"losses":31,"wins":121},"thinkingmachines/inkling-small":{"draws":34,"losses":19,"wins":91},"unbiased/pareto-26.10":{"draws":2,"losses":21,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":39,"wins":6},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":20,"losses":59,"wins":65},"x-ai/grok-4.6":{"draws":35,"losses":59,"wins":50},"x-ai/grok-4.7":{"draws":15,"losses":77,"wins":34},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":52,"losses":36,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":13,"wins":53},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":31,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":50,"wins":30},"z-ai/glm-5.2":{"draws":71,"losses":62,"wins":155},"z-ai/glm-5.3":{"draws":32,"losses":74,"wins":32},"z-ai/glm-5.3-flash":{"draws":12,"losses":42,"wins":42},"z-ai/glm-5.3-flashx":{"draws":33,"losses":52,"wins":59}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":25,"wins":83},"claude-fable-5":{"draws":27,"losses":73,"wins":44},"claude-fable-5-1":{"draws":15,"losses":134,"wins":13},"claude-haiku-5-5":{"draws":27,"losses":60,"wins":51},"claude-opus-4-5":{"draws":53,"losses":55,"wins":126},"claude-opus-4-8":{"draws":25,"losses":59,"wins":48},"claude-opus-5":{"draws":36,"losses":166,"wins":44},"claude-opus-5-5":{"draws":16,"losses":130,"wins":10},"claude-sonnet-5":{"draws":39,"losses":33,"wins":72},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":54},"cohere/north-mini-code":{"draws":9,"losses":5,"wins":40},"deepseek/deepseek-v4-flash":{"draws":58,"losses":32,"wins":126},"deepseek/deepseek-v4-pro":{"draws":32,"losses":40,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":39,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":43,"wins":24},"elorian/glimpse":{"draws":7,"losses":9,"wins":14},"fireworks/ember-1":{"draws":35,"losses":50,"wins":59},"gemini-3.1-pro-preview":{"draws":34,"losses":37,"wins":73},"gemini-4-argon":{"draws":5,"losses":57,"wins":8},"google/gemini-3.1-flash-lite":{"draws":25,"losses":7,"wins":64},"google/gemini-3.5-flash":{"draws":47,"losses":44,"wins":89},"google/gemini-3.5-flash-lite":{"draws":63,"losses":48,"wins":141},"google/gemini-3.6-flash":{"draws":67,"losses":96,"wins":113},"google/gemini-3.8-flash":{"draws":26,"losses":66,"wins":52},"google/gemma-4-31b-it":{"draws":28,"losses":11,"wins":45},"gpt-4.1":{"draws":11,"losses":7,"wins":30},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":13},"gpt-5":{"draws":36,"losses":33,"wins":57},"gpt-5.4":{"draws":34,"losses":50,"wins":54},"gpt-5.4-mini":{"draws":27,"losses":13,"wins":56},"gpt-5.4-nano":{"draws":30,"losses":34,"wins":80},"gpt-5.5":{"draws":42,"losses":43,"wins":47},"gpt-5.6-luna":{"draws":42,"losses":29,"wins":73},"gpt-5.6-sol":{"draws":23,"losses":80,"wins":41},"gpt-5.6-terra":{"draws":38,"losses":37,"wins":63},"gpt-6-astra":{"draws":14,"losses":121,"wins":9},"gpt-6-luna":{"draws":30,"losses":42,"wins":72},"gpt-6-sol":{"draws":20,"losses":87,"wins":37},"gpt-6.1-sol":{"draws":19,"losses":107,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":5,"wins":68},"inception/mercury-3":{"draws":16,"losses":10,"wins":18},"inclusionai/ling-3.0-flash":{"draws":34,"losses":8,"wins":60},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":20,"wins":102},"meta/muse-glimmer-30b":{"draws":36,"losses":19,"wins":71},"meta/muse-spark-1.2":{"draws":29,"losses":49,"wins":60},"meta/muse-spark-1.3":{"draws":28,"losses":59,"wins":57},"meta/muse-spark-open":{"draws":11,"losses":26,"wins":33},"meta/muse-wonder":{"draws":34,"losses":73,"wins":37},"minimax/minimax-m3":{"draws":20,"losses":12,"wins":46},"minimax/minimax-m3.1-flash":{"draws":14,"losses":17,"wins":49},"mistralai/mistral-large-4-0":{"draws":29,"losses":27,"wins":34},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":12,"wins":12},"moonshotai/kimi-k3":{"draws":41,"losses":34,"wins":63},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":21,"wins":74},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":8,"wins":20},"o3":{"draws":21,"losses":58,"wins":119},"openai/gpt-oss-120b":{"draws":37,"losses":13,"wins":76},"poolside/laguna-s-2.1":{"draws":40,"losses":23,"wins":75},"qwen/qwen3.7-max":{"draws":22,"losses":20,"wins":42},"qwen/qwen3.7-plus":{"draws":17,"losses":10,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":45,"wins":61},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":32,"losses":22,"wins":42},"qwen/qwen3.8-max":{"draws":40,"losses":48,"wins":56},"qwen/qwen3.8-max-0902":{"draws":36,"losses":51,"wins":57},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":18,"wins":22},"stealth/ox-alpha":{"draws":86,"losses":167,"wins":221},"stealth/space-bunny-alpha":{"draws":33,"losses":22,"wins":59},"stepfun/step-3.7-flash":{"draws":13,"losses":14,"wins":75},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":14,"wins":48},"tencent/hy4-preview":{"draws":32,"losses":57,"wins":49},"thinkingmachines/inkling":{"draws":44,"losses":25,"wins":123},"thinkingmachines/inkling-small":{"draws":36,"losses":23,"wins":85},"unbiased/pareto-26.10":{"draws":3,"losses":22,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":25,"losses":58,"wins":61},"x-ai/grok-4.6":{"draws":33,"losses":59,"wins":52},"x-ai/grok-4.7":{"draws":15,"losses":83,"wins":28},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":30},"xiaomi/mimo-v2.5":{"draws":72,"losses":16,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":14,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":34,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":82,"losses":63,"wins":143},"z-ai/glm-5.3":{"draws":27,"losses":78,"wins":33},"z-ai/glm-5.3-flash":{"draws":33,"losses":59,"wins":52},"z-ai/glm-5.3-flashx":{"draws":32,"losses":32,"wins":32}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":10},"claude-fable-5":{"draws":9,"losses":35,"wins":4},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":32,"losses":30,"wins":16},"claude-opus-4-8":{"draws":14,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":65,"wins":8},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":17,"losses":23,"wins":8},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":23,"losses":19,"wins":30},"deepseek/deepseek-v4-pro":{"draws":7,"losses":20,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":15,"wins":4},"elorian/glimpse":{"draws":4,"losses":5,"wins":7},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":16,"losses":16,"wins":16},"gemini-4-argon":{"draws":1,"losses":25,"wins":2},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":28,"wins":16},"google/gemini-3.5-flash-lite":{"draws":36,"losses":18,"wins":30},"google/gemini-3.6-flash":{"draws":31,"losses":41,"wins":20},"google/gemini-3.8-flash":{"draws":12,"losses":27,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4":{"draws":12,"losses":25,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":7,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":17,"wins":17},"gpt-5.5":{"draws":21,"losses":14,"wins":9},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":15,"losses":21,"wins":10},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":17,"wins":16},"gpt-6-sol":{"draws":7,"losses":36,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":12},"inception/mercury-3":{"draws":4,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":10,"wins":26},"meta/muse-glimmer-30b":{"draws":20,"losses":9,"wins":13},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":25,"wins":7},"meta/muse-spark-open":{"draws":9,"losses":8,"wins":5},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"minimax/minimax-m3.1-flash":{"draws":5,"losses":14,"wins":7},"mistralai/mistral-large-4-0":{"draws":12,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":14,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":22,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":12,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":0,"wins":2},"o3":{"draws":16,"losses":27,"wins":23},"openai/gpt-oss-120b":{"draws":19,"losses":7,"wins":16},"poolside/laguna-s-2.1":{"draws":25,"losses":8,"wins":13},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":19,"wins":12},"qwen/qwen3.8-27b":{"draws":9,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":17,"losses":23,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":10},"stealth/ox-alpha":{"draws":43,"losses":84,"wins":31},"stealth/space-bunny-alpha":{"draws":18,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":24,"wins":6},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":22,"losses":9,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.6":{"draws":11,"losses":33,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.2":{"draws":38,"losses":30,"wins":28},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":26,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":9}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":36},"claude-fable-5":{"draws":1,"losses":12,"wins":19},"claude-fable-5-1":{"draws":5,"losses":38,"wins":11},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":3,"losses":9,"wins":66},"claude-opus-4-8":{"draws":3,"losses":13,"wins":28},"claude-opus-5":{"draws":13,"losses":39,"wins":30},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":8,"losses":4,"wins":36},"claude-sonnet-5-5":{"draws":1,"losses":19,"wins":28},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4-pro":{"draws":3,"losses":9,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":33},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":11,"wins":20},"elorian/glimpse":{"draws":0,"losses":2,"wins":4},"fireworks/ember-1":{"draws":6,"losses":5,"wins":37},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":34},"gemini-4-argon":{"draws":4,"losses":18,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":8,"losses":3,"wins":49},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":72},"google/gemini-3.6-flash":{"draws":10,"losses":17,"wins":65},"google/gemini-3.8-flash":{"draws":7,"losses":19,"wins":22},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":9,"wins":29},"gpt-5.4":{"draws":7,"losses":17,"wins":22},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":40},"gpt-5.5":{"draws":5,"losses":17,"wins":22},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":37},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":28},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":31},"gpt-6-astra":{"draws":4,"losses":37,"wins":7},"gpt-6-luna":{"draws":7,"losses":11,"wins":30},"gpt-6-sol":{"draws":6,"losses":25,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":31},"inception/mercury-3":{"draws":3,"losses":1,"wins":12},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":41},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":1,"losses":8,"wins":37},"meta/muse-spark-1.3":{"draws":5,"losses":8,"wins":35},"meta/muse-spark-open":{"draws":0,"losses":2,"wins":12},"meta/muse-wonder":{"draws":5,"losses":15,"wins":28},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":18},"minimax/minimax-m3.1-flash":{"draws":3,"losses":0,"wins":17},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":32},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":20},"o3":{"draws":5,"losses":11,"wins":50},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":35},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":10,"wins":33},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":29},"qwen/qwen3.8-flash":{"draws":6,"losses":3,"wins":23},"qwen/qwen3.8-max":{"draws":7,"losses":9,"wins":32},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":32},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":7,"wins":9},"stealth/ox-alpha":{"draws":18,"losses":20,"wins":120},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":31},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":7,"losses":8,"wins":31},"thinkingmachines/inkling":{"draws":6,"losses":4,"wins":54},"thinkingmachines/inkling-small":{"draws":8,"losses":1,"wins":39},"unbiased/pareto-26.10":{"draws":0,"losses":9,"wins":3},"unbiased/pareto-26.10-preview":{"draws":3,"losses":9,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":34},"x-ai/grok-4.6":{"draws":11,"losses":14,"wins":23},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":17},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":21},"z-ai/glm-5.2":{"draws":13,"losses":10,"wins":73},"z-ai/glm-5.3":{"draws":9,"losses":12,"wins":25},"z-ai/glm-5.3-flash":{"draws":9,"losses":7,"wins":32},"z-ai/glm-5.3-flashx":{"draws":9,"losses":10,"wins":29}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":58},"claude-fable-5":{"draws":1,"losses":5,"wins":60},"claude-fable-5-1":{"draws":7,"losses":10,"wins":39},"claude-haiku-5-5":{"draws":4,"losses":0,"wins":58},"claude-opus-4-5":{"draws":1,"losses":2,"wins":103},"claude-opus-4-8":{"draws":0,"losses":3,"wins":55},"claude-opus-5":{"draws":7,"losses":21,"wins":86},"claude-opus-5-5":{"draws":7,"losses":32,"wins":31},"claude-sonnet-5":{"draws":0,"losses":1,"wins":65},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":52},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":25},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":94},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":59},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":5,"wins":28},"elorian/glimpse":{"draws":0,"losses":1,"wins":25},"fireworks/ember-1":{"draws":0,"losses":1,"wins":65},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":63},"gemini-4-argon":{"draws":0,"losses":0,"wins":24},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":41},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":80},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":114},"google/gemini-3.6-flash":{"draws":3,"losses":4,"wins":121},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":60},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":37},"gpt-4.1":{"draws":0,"losses":0,"wins":22},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":0,"wins":58},"gpt-5.4":{"draws":1,"losses":3,"wins":60},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":44},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":58},"gpt-5.5":{"draws":0,"losses":3,"wins":59},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":64},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":58},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":64},"gpt-6-astra":{"draws":5,"losses":23,"wins":38},"gpt-6-luna":{"draws":1,"losses":1,"wins":64},"gpt-6-sol":{"draws":2,"losses":11,"wins":53},"gpt-6.1-sol":{"draws":2,"losses":23,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":44},"inception/mercury-3":{"draws":0,"losses":0,"wins":20},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":44},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":69},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":60},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":60},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":60},"meta/muse-spark-open":{"draws":0,"losses":0,"wins":28},"meta/muse-wonder":{"draws":4,"losses":7,"wins":55},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":33},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":33},"mistralai/mistral-large-4-0":{"draws":0,"losses":4,"wins":38},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k3":{"draws":1,"losses":3,"wins":60},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"o3":{"draws":0,"losses":1,"wins":85},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":57},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":58},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":66},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":43},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":65},"qwen/qwen3.8-max-0902":{"draws":2,"losses":3,"wins":61},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":28},"stealth/ox-alpha":{"draws":10,"losses":3,"wins":221},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":53},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":31},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":60},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":90},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":65},"unbiased/pareto-26.10":{"draws":4,"losses":3,"wins":7},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":64},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":58},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":49},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":37},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":128},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":58},"z-ai/glm-5.3-flash":{"draws":1,"losses":4,"wins":61},"z-ai/glm-5.3-flashx":{"draws":6,"losses":1,"wins":59}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":34},"claude-fable-5":{"draws":5,"losses":11,"wins":26},"claude-fable-5-1":{"draws":4,"losses":39,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":20},"claude-opus-4-5":{"draws":12,"losses":6,"wins":52},"claude-opus-4-8":{"draws":7,"losses":10,"wins":25},"claude-opus-5":{"draws":10,"losses":38,"wins":22},"claude-opus-5-5":{"draws":6,"losses":32,"wins":8},"claude-sonnet-5":{"draws":5,"losses":4,"wins":33},"claude-sonnet-5-5":{"draws":5,"losses":13,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":6,"losses":5,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":4,"wins":10},"elorian/glimpse":{"draws":0,"losses":3,"wins":7},"fireworks/ember-1":{"draws":5,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":29},"gemini-4-argon":{"draws":6,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":6,"losses":5,"wins":63},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":52},"google/gemini-3.8-flash":{"draws":7,"losses":9,"wins":26},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":23},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":4,"wins":29},"gpt-5.4":{"draws":2,"losses":9,"wins":29},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":39},"gpt-5.5":{"draws":5,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":35},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":22},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":33,"wins":5},"gpt-6-luna":{"draws":6,"losses":6,"wins":30},"gpt-6-sol":{"draws":12,"losses":15,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":30,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":31},"inception/mercury-3":{"draws":2,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":30},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":34},"meta/muse-spark-open":{"draws":2,"losses":5,"wins":7},"meta/muse-wonder":{"draws":9,"losses":16,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":21},"minimax/minimax-m3.1-flash":{"draws":1,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":4,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":2,"losses":9,"wins":29},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":6},"o3":{"draws":2,"losses":11,"wins":49},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":31},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":8,"wins":28},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":3,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":2,"wins":16},"stealth/ox-alpha":{"draws":17,"losses":21,"wins":80},"stealth/space-bunny-alpha":{"draws":6,"losses":5,"wins":23},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":4,"losses":9,"wins":27},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":45},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":40},"unbiased/pareto-26.10":{"draws":1,"losses":8,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":6},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":13,"wins":25},"x-ai/grok-4.6":{"draws":4,"losses":11,"wins":27},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":6,"losses":6,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":5,"losses":9,"wins":70},"z-ai/glm-5.3":{"draws":5,"losses":16,"wins":19},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":29},"z-ai/glm-5.3-flashx":{"draws":3,"losses":9,"wins":30}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":7,"losses":33,"wins":8},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":20,"losses":19,"wins":23},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":20,"losses":10,"wins":18},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":19,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":17,"wins":6},"elorian/glimpse":{"draws":3,"losses":2,"wins":3},"fireworks/ember-1":{"draws":16,"losses":15,"wins":17},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"gemini-4-argon":{"draws":2,"losses":24,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":15,"losses":22,"wins":23},"google/gemini-3.5-flash-lite":{"draws":29,"losses":20,"wins":35},"google/gemini-3.6-flash":{"draws":25,"losses":43,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":13,"wins":17},"gpt-5.4":{"draws":14,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":12,"wins":20},"gpt-5.5":{"draws":16,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":16,"losses":11,"wins":19},"gpt-6-astra":{"draws":1,"losses":45,"wins":2},"gpt-6-luna":{"draws":14,"losses":17,"wins":17},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inception/mercury-3":{"draws":9,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":31},"meta/muse-glimmer-30b":{"draws":16,"losses":3,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":26,"wins":12},"meta/muse-spark-open":{"draws":5,"losses":6,"wins":5},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"minimax/minimax-m3.1-flash":{"draws":2,"losses":7,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":15},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":4,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":3},"o3":{"draws":10,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":24},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":14},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":10,"wins":6},"stealth/ox-alpha":{"draws":39,"losses":63,"wins":56},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":20,"losses":8,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":15,"losses":21,"wins":12},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":24,"wins":41},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":13},"z-ai/glm-5.3-flashx":{"draws":17,"losses":19,"wins":12}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":5,"wins":31},"claude-fable-5":{"draws":5,"losses":15,"wins":22},"claude-fable-5-1":{"draws":3,"losses":34,"wins":9},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":26},"claude-opus-4-5":{"draws":13,"losses":11,"wins":46},"claude-opus-4-8":{"draws":3,"losses":4,"wins":21},"claude-opus-5":{"draws":13,"losses":36,"wins":21},"claude-opus-5-5":{"draws":9,"losses":27,"wins":10},"claude-sonnet-5":{"draws":8,"losses":5,"wins":29},"claude-sonnet-5-5":{"draws":10,"losses":11,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":5,"losses":4,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":6,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":13,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":4,"wins":16},"elorian/glimpse":{"draws":1,"losses":7,"wins":6},"fireworks/ember-1":{"draws":10,"losses":6,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":28},"gemini-4-argon":{"draws":1,"losses":11,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":40},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":63},"google/gemini-3.6-flash":{"draws":13,"losses":21,"wins":46},"google/gemini-3.8-flash":{"draws":8,"losses":12,"wins":22},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":21},"gpt-4.1":{"draws":4,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":5,"wins":28},"gpt-5.4":{"draws":4,"losses":14,"wins":22},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":3,"wins":37},"gpt-5.5":{"draws":8,"losses":13,"wins":17},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":29},"gpt-5.6-sol":{"draws":3,"losses":12,"wins":27},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":32},"gpt-6-astra":{"draws":5,"losses":33,"wins":4},"gpt-6-luna":{"draws":9,"losses":4,"wins":29},"gpt-6-sol":{"draws":8,"losses":18,"wins":16},"gpt-6.1-sol":{"draws":5,"losses":28,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":25},"inception/mercury-3":{"draws":1,"losses":1,"wins":14},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":37},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":28},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":24},"meta/muse-spark-open":{"draws":2,"losses":1,"wins":11},"meta/muse-wonder":{"draws":7,"losses":14,"wins":21},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":6,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":23},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":9},"o3":{"draws":6,"losses":7,"wins":49},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":3,"losses":2,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":1,"losses":3,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":22},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":32},"qwen/qwen3.8-max-0902":{"draws":9,"losses":12,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":5,"wins":11},"stealth/ox-alpha":{"draws":25,"losses":21,"wins":72},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":22},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":26},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":46},"thinkingmachines/inkling-small":{"draws":5,"losses":3,"wins":34},"unbiased/pareto-26.10":{"draws":3,"losses":7,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":24},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":21},"x-ai/grok-4.7":{"draws":7,"losses":19,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":10,"losses":8,"wins":66},"z-ai/glm-5.3":{"draws":6,"losses":14,"wins":20},"z-ai/glm-5.3-flash":{"draws":3,"losses":13,"wins":26},"z-ai/glm-5.3-flashx":{"draws":8,"losses":4,"wins":30}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":7,"wins":63},"claude-fable-5":{"draws":6,"losses":19,"wins":53},"claude-fable-5-1":{"draws":9,"losses":38,"wins":41},"claude-haiku-5-5":{"draws":1,"losses":11,"wins":62},"claude-opus-4-5":{"draws":7,"losses":11,"wins":108},"claude-opus-4-8":{"draws":4,"losses":13,"wins":53},"claude-opus-5":{"draws":14,"losses":37,"wins":75},"claude-opus-5-5":{"draws":4,"losses":43,"wins":39},"claude-sonnet-5":{"draws":4,"losses":6,"wins":68},"claude-sonnet-5-5":{"draws":2,"losses":18,"wins":58},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":104},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":3,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":8,"wins":62},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":7,"wins":34},"elorian/glimpse":{"draws":0,"losses":3,"wins":17},"fireworks/ember-1":{"draws":3,"losses":14,"wins":61},"gemini-3.1-pro-preview":{"draws":3,"losses":5,"wins":70},"gemini-4-argon":{"draws":2,"losses":10,"wins":16},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":42},"google/gemini-3.5-flash":{"draws":9,"losses":5,"wins":82},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":123},"google/gemini-3.6-flash":{"draws":10,"losses":19,"wins":119},"google/gemini-3.8-flash":{"draws":3,"losses":11,"wins":64},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":40},"gpt-4.1":{"draws":0,"losses":1,"wins":25},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":4,"wins":66},"gpt-5.4":{"draws":3,"losses":8,"wins":63},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":45},"gpt-5.4-nano":{"draws":1,"losses":6,"wins":67},"gpt-5.5":{"draws":3,"losses":9,"wins":62},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":72},"gpt-5.6-sol":{"draws":5,"losses":14,"wins":59},"gpt-5.6-terra":{"draws":4,"losses":3,"wins":67},"gpt-6-astra":{"draws":8,"losses":47,"wins":23},"gpt-6-luna":{"draws":9,"losses":5,"wins":64},"gpt-6-sol":{"draws":7,"losses":25,"wins":46},"gpt-6.1-sol":{"draws":13,"losses":36,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":1,"wins":47},"inception/mercury-3":{"draws":1,"losses":2,"wins":29},"inclusionai/ling-3.0-flash":{"draws":1,"losses":5,"wins":46},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":6,"wins":72},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":68},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":70},"meta/muse-spark-1.3":{"draws":4,"losses":9,"wins":65},"meta/muse-spark-open":{"draws":1,"losses":4,"wins":37},"meta/muse-wonder":{"draws":5,"losses":17,"wins":56},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":42},"minimax/minimax-m3.1-flash":{"draws":0,"losses":5,"wins":23},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":44},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":20},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":64},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":62},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":17},"o3":{"draws":2,"losses":6,"wins":88},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":59},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":73},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":39},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":6,"wins":69},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":46},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":49},"qwen/qwen3.8-max":{"draws":2,"losses":6,"wins":70},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":65},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":1,"wins":35},"stealth/ox-alpha":{"draws":19,"losses":21,"wins":226},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":55},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":38},"tencent/hy4-preview":{"draws":4,"losses":7,"wins":63},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":94},"thinkingmachines/inkling-small":{"draws":4,"losses":6,"wins":68},"unbiased/pareto-26.10":{"draws":3,"losses":7,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":14},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":13},"x-ai/grok-4.5":{"draws":9,"losses":12,"wins":57},"x-ai/grok-4.6":{"draws":5,"losses":8,"wins":65},"x-ai/grok-4.7":{"draws":6,"losses":18,"wins":46},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.5":{"draws":4,"losses":7,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":41},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":138},"z-ai/glm-5.3":{"draws":6,"losses":8,"wins":60},"z-ai/glm-5.3-flash":{"draws":10,"losses":7,"wins":61},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":64}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":0,"losses":3,"wins":45},"claude-fable-5-1":{"draws":4,"losses":8,"wins":42},"claude-haiku-5-5":{"draws":2,"losses":1,"wins":43},"claude-opus-4-5":{"draws":0,"losses":1,"wins":77},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":5,"losses":10,"wins":67},"claude-opus-5-5":{"draws":4,"losses":6,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":4,"losses":5,"wins":39},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":72},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":45},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":4,"wins":20},"elorian/glimpse":{"draws":0,"losses":0,"wins":12},"fireworks/ember-1":{"draws":0,"losses":0,"wins":48},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"gemini-4-argon":{"draws":0,"losses":4,"wins":20},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":58},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":83},"google/gemini-3.6-flash":{"draws":1,"losses":3,"wins":88},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":45},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":0,"wins":42},"gpt-5.4":{"draws":0,"losses":4,"wins":42},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":45},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":44},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":4,"losses":14,"wins":30},"gpt-6-luna":{"draws":1,"losses":0,"wins":47},"gpt-6-sol":{"draws":2,"losses":1,"wins":45},"gpt-6.1-sol":{"draws":8,"losses":7,"wins":33},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inception/mercury-3":{"draws":0,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":52},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":42},"meta/muse-spark-1.3":{"draws":1,"losses":3,"wins":44},"meta/muse-spark-open":{"draws":0,"losses":0,"wins":22},"meta/muse-wonder":{"draws":1,"losses":4,"wins":43},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":22},"mistralai/mistral-large-4-0":{"draws":1,"losses":0,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":14},"o3":{"draws":1,"losses":1,"wins":64},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":5,"wins":43},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":31},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":43},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":26},"stealth/ox-alpha":{"draws":2,"losses":1,"wins":155},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":45},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":6},"unbiased/pareto-26.10-preview":{"draws":1,"losses":3,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":44},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":1,"losses":3,"wins":42},"z-ai/glm-5.3-flash":{"draws":1,"losses":1,"wins":46},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":43}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":4,"wins":29},"claude-fable-5":{"draws":9,"losses":25,"wins":14},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":23},"claude-opus-4-5":{"draws":23,"losses":21,"wins":34},"claude-opus-4-8":{"draws":10,"losses":14,"wins":20},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":9,"losses":4,"wins":19},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":18},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":47},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":8,"wins":13},"elorian/glimpse":{"draws":3,"losses":2,"wins":3},"fireworks/ember-1":{"draws":11,"losses":17,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"gemini-4-argon":{"draws":1,"losses":19,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":15,"losses":21,"wins":24},"google/gemini-3.5-flash-lite":{"draws":18,"losses":10,"wins":56},"google/gemini-3.6-flash":{"draws":14,"losses":33,"wins":45},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":7,"wins":23},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":30},"gpt-5.5":{"draws":11,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":22},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":23},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":8,"losses":31,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":21},"inception/mercury-3":{"draws":9,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":37},"meta/muse-glimmer-30b":{"draws":8,"losses":6,"wins":28},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":17},"meta/muse-spark-1.3":{"draws":8,"losses":24,"wins":16},"meta/muse-spark-open":{"draws":8,"losses":11,"wins":5},"meta/muse-wonder":{"draws":11,"losses":23,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":4,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":7},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":28},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":18},"qwen/qwen3.8-27b":{"draws":9,"losses":8,"wins":17},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":10,"losses":14,"wins":24},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":6,"wins":13},"stealth/ox-alpha":{"draws":34,"losses":59,"wins":65},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":12},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":21,"wins":16},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":5,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":20,"losses":26,"wins":50},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":4,"losses":25,"wins":19},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":0,"wins":37},"claude-fable-5":{"draws":5,"losses":2,"wins":41},"claude-fable-5-1":{"draws":7,"losses":16,"wins":31},"claude-haiku-5-5":{"draws":5,"losses":2,"wins":39},"claude-opus-4-5":{"draws":8,"losses":2,"wins":68},"claude-opus-4-8":{"draws":5,"losses":1,"wins":38},"claude-opus-5":{"draws":5,"losses":16,"wins":61},"claude-opus-5-5":{"draws":10,"losses":17,"wins":25},"claude-sonnet-5":{"draws":1,"losses":0,"wins":47},"claude-sonnet-5-5":{"draws":0,"losses":1,"wins":31},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":69},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":1,"wins":21},"elorian/glimpse":{"draws":1,"losses":0,"wins":9},"fireworks/ember-1":{"draws":5,"losses":0,"wins":43},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":45},"gemini-4-argon":{"draws":5,"losses":4,"wins":19},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":3,"losses":2,"wins":55},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":77},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":39},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":0,"wins":39},"gpt-5.4":{"draws":9,"losses":1,"wins":36},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":4,"losses":1,"wins":39},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":42},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":42},"gpt-6-astra":{"draws":7,"losses":16,"wins":25},"gpt-6-luna":{"draws":8,"losses":1,"wins":39},"gpt-6-sol":{"draws":7,"losses":6,"wins":35},"gpt-6.1-sol":{"draws":2,"losses":14,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":2,"losses":0,"wins":16},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":43},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":44},"meta/muse-spark-open":{"draws":0,"losses":1,"wins":15},"meta/muse-wonder":{"draws":5,"losses":1,"wins":42},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":20},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":40},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":9},"o3":{"draws":2,"losses":1,"wins":63},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":40},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":44},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":46},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":41},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":0,"wins":21},"stealth/ox-alpha":{"draws":10,"losses":4,"wins":144},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":3,"losses":0,"wins":43},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":57},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10":{"draws":2,"losses":3,"wins":5},"unbiased/pareto-26.10-preview":{"draws":2,"losses":5,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":1,"wins":41},"x-ai/grok-4.6":{"draws":5,"losses":0,"wins":43},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":90},"z-ai/glm-5.3":{"draws":6,"losses":4,"wins":36},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":39},"z-ai/glm-5.3-flashx":{"draws":6,"losses":3,"wins":39}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":12},"claude-fable-5":{"draws":7,"losses":28,"wins":7},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":20,"losses":31,"wins":17},"claude-opus-4-8":{"draws":10,"losses":21,"wins":7},"claude-opus-5":{"draws":13,"losses":48,"wins":9},"claude-opus-5-5":{"draws":4,"losses":40,"wins":2},"claude-sonnet-5":{"draws":15,"losses":18,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":14,"wins":20},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":18,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":7},"elorian/glimpse":{"draws":1,"losses":2,"wins":3},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":13,"wins":13},"gemini-4-argon":{"draws":7,"losses":15,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":18,"losses":21,"wins":13},"google/gemini-3.5-flash-lite":{"draws":29,"losses":25,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":44,"wins":11},"google/gemini-3.8-flash":{"draws":9,"losses":26,"wins":7},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":9},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":13,"wins":8},"gpt-5.4":{"draws":15,"losses":16,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":12},"gpt-5.5":{"draws":16,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":20,"losses":9,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":14,"wins":11},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":19,"losses":13,"wins":10},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":11},"inception/mercury-3":{"draws":8,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":7,"wins":19},"meta/muse-glimmer-30b":{"draws":23,"losses":5,"wins":8},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":25,"wins":5},"meta/muse-spark-open":{"draws":7,"losses":13,"wins":2},"meta/muse-wonder":{"draws":8,"losses":25,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":7},"minimax/minimax-m3.1-flash":{"draws":6,"losses":5,"wins":9},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":5},"mistralai/mistral-medium-3-5":{"draws":15,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":17,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":3},"o3":{"draws":13,"losses":22,"wins":19},"openai/gpt-oss-120b":{"draws":18,"losses":12,"wins":6},"poolside/laguna-s-2.1":{"draws":19,"losses":10,"wins":9},"qwen/qwen3.7-max":{"draws":15,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":15,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":19,"losses":15,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":5,"wins":5},"stealth/ox-alpha":{"draws":40,"losses":70,"wins":30},"stealth/space-bunny-alpha":{"draws":17,"losses":7,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":17,"wins":10},"thinkingmachines/inkling":{"draws":28,"losses":11,"wins":15},"thinkingmachines/inkling-small":{"draws":22,"losses":7,"wins":13},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":16,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":3,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":37,"losses":27,"wins":20},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":19,"wins":7}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":10,"wins":24},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":22,"losses":25,"wins":31},"claude-opus-4-8":{"draws":10,"losses":20,"wins":14},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":13,"losses":20,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":15,"wins":4},"elorian/glimpse":{"draws":6,"losses":9,"wins":3},"fireworks/ember-1":{"draws":15,"losses":16,"wins":17},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"gemini-4-argon":{"draws":5,"losses":16,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":16,"losses":24,"wins":20},"google/gemini-3.5-flash-lite":{"draws":25,"losses":22,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":39,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":10},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4":{"draws":15,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":15,"wins":28},"gpt-5.5":{"draws":15,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":12,"losses":20,"wins":16},"gpt-6-sol":{"draws":6,"losses":32,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inception/mercury-3":{"draws":9,"losses":4,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":28},"meta/muse-glimmer-30b":{"draws":12,"losses":11,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":22,"wins":14},"meta/muse-spark-1.3":{"draws":9,"losses":27,"wins":12},"meta/muse-spark-open":{"draws":7,"losses":14,"wins":7},"meta/muse-wonder":{"draws":14,"losses":23,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":4,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":6,"losses":23,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":5,"wins":4},"o3":{"draws":8,"losses":23,"wins":35},"openai/gpt-oss-120b":{"draws":14,"losses":10,"wins":18},"poolside/laguna-s-2.1":{"draws":12,"losses":18,"wins":16},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":24,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":7},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":24,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":4,"wins":5},"stealth/ox-alpha":{"draws":35,"losses":79,"wins":44},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":21,"wins":15},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":16,"losses":2,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":19,"wins":17},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":31,"losses":29,"wins":36},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":8},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":18,"wins":19}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":26},"claude-fable-5":{"draws":6,"losses":29,"wins":13},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":21,"wins":14},"claude-opus-4-5":{"draws":16,"losses":20,"wins":42},"claude-opus-4-8":{"draws":11,"losses":14,"wins":19},"claude-opus-5":{"draws":5,"losses":67,"wins":10},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":14,"losses":11,"wins":23},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":16,"losses":15,"wins":41},"deepseek/deepseek-v4-pro":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":9,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":24,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":18,"wins":10},"elorian/glimpse":{"draws":2,"losses":3,"wins":9},"fireworks/ember-1":{"draws":10,"losses":13,"wins":25},"gemini-3.1-pro-preview":{"draws":8,"losses":14,"wins":26},"gemini-4-argon":{"draws":1,"losses":20,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":20,"wins":28},"google/gemini-3.5-flash-lite":{"draws":21,"losses":7,"wins":56},"google/gemini-3.6-flash":{"draws":17,"losses":34,"wins":41},"google/gemini-3.8-flash":{"draws":8,"losses":20,"wins":20},"google/gemma-4-31b-it":{"draws":12,"losses":0,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":10,"wins":26},"gpt-5.4":{"draws":8,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":10,"losses":4,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":28},"gpt-5.5":{"draws":8,"losses":22,"wins":14},"gpt-5.6-luna":{"draws":16,"losses":8,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":21},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":13,"wins":23},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":4,"wins":19},"inception/mercury-3":{"draws":4,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":11,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":21},"meta/muse-spark-1.3":{"draws":11,"losses":17,"wins":20},"meta/muse-spark-open":{"draws":0,"losses":9,"wins":13},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":5,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":10,"losses":7,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":10,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":3},"o3":{"draws":8,"losses":12,"wins":46},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":23},"poolside/laguna-s-2.1":{"draws":8,"losses":7,"wins":31},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":6,"wins":5},"stealth/ox-alpha":{"draws":29,"losses":54,"wins":75},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":24},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":4,"losses":20,"wins":22},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":20},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":19,"wins":11},"z-ai/glm-5.2":{"draws":22,"losses":29,"wins":45},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":19}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":13,"losses":16,"wins":19},"claude-fable-5-1":{"draws":6,"losses":42,"wins":6},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":15,"losses":12,"wins":51},"claude-opus-4-8":{"draws":7,"losses":11,"wins":26},"claude-opus-5":{"draws":7,"losses":56,"wins":19},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":13,"losses":7,"wins":28},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":13,"losses":1,"wins":58},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":6,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":4,"wins":10},"elorian/glimpse":{"draws":1,"losses":5,"wins":8},"fireworks/ember-1":{"draws":11,"losses":10,"wins":27},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"gemini-4-argon":{"draws":2,"losses":19,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":13,"losses":8,"wins":39},"google/gemini-3.5-flash-lite":{"draws":12,"losses":7,"wins":65},"google/gemini-3.6-flash":{"draws":19,"losses":26,"wins":47},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":30},"google/gemma-4-31b-it":{"draws":7,"losses":1,"wins":20},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":4,"wins":25},"gpt-5.4":{"draws":10,"losses":11,"wins":25},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":37},"gpt-5.5":{"draws":11,"losses":8,"wins":25},"gpt-5.6-luna":{"draws":12,"losses":3,"wins":33},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":23},"gpt-5.6-terra":{"draws":16,"losses":4,"wins":26},"gpt-6-astra":{"draws":7,"losses":38,"wins":3},"gpt-6-luna":{"draws":12,"losses":6,"wins":30},"gpt-6-sol":{"draws":8,"losses":27,"wins":13},"gpt-6.1-sol":{"draws":2,"losses":37,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":3,"losses":0,"wins":13},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":38},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":13,"wins":26},"meta/muse-spark-1.3":{"draws":10,"losses":13,"wins":25},"meta/muse-spark-open":{"draws":1,"losses":3,"wins":14},"meta/muse-wonder":{"draws":12,"losses":17,"wins":19},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":3,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":6,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":9},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":34},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":9,"wins":27},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":23},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":12,"losses":11,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":10,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":7,"wins":14},"stealth/ox-alpha":{"draws":31,"losses":41,"wins":86},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":26},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":9,"losses":13,"wins":24},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":35},"unbiased/pareto-26.10":{"draws":1,"losses":10,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":26},"x-ai/grok-4.7":{"draws":1,"losses":24,"wins":17},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":23,"losses":10,"wins":63},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":13,"wins":28},"z-ai/glm-5.3-flashx":{"draws":13,"losses":12,"wins":23}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":12},"claude-fable-5":{"draws":5,"losses":8,"wins":15},"claude-fable-5-1":{"draws":3,"losses":18,"wins":5},"claude-haiku-5-5":{"draws":7,"losses":4,"wins":13},"claude-opus-4-5":{"draws":6,"losses":2,"wins":26},"claude-opus-4-8":{"draws":4,"losses":3,"wins":15},"claude-opus-5":{"draws":4,"losses":26,"wins":12},"claude-opus-5-5":{"draws":2,"losses":19,"wins":7},"claude-sonnet-5":{"draws":4,"losses":5,"wins":21},"claude-sonnet-5-5":{"draws":2,"losses":7,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":1,"losses":3,"wins":30},"deepseek/deepseek-v4-pro":{"draws":7,"losses":5,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":5,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":6,"wins":15},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":9,"losses":4,"wins":17},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":28},"gemini-4-argon":{"draws":9,"losses":27,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":14},"google/gemini-3.5-flash":{"draws":1,"losses":6,"wins":19},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":44},"google/gemini-3.6-flash":{"draws":5,"losses":15,"wins":30},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":19},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":12},"gpt-4.1":{"draws":1,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":7,"wins":9},"gpt-5.4":{"draws":2,"losses":6,"wins":14},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":13},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":29},"gpt-5.5":{"draws":4,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":27},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":10},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":15},"gpt-6-astra":{"draws":3,"losses":19,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":17},"gpt-6-sol":{"draws":2,"losses":12,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":22,"wins":5},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":15},"inception/mercury-3":{"draws":9,"losses":2,"wins":21},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":15},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":18},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":18},"meta/muse-spark-1.2":{"draws":1,"losses":10,"wins":15},"meta/muse-spark-1.3":{"draws":2,"losses":10,"wins":18},"meta/muse-spark-open":{"draws":8,"losses":8,"wins":26},"meta/muse-wonder":{"draws":10,"losses":7,"wins":13},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":12},"minimax/minimax-m3.1-flash":{"draws":12,"losses":2,"wins":22},"mistralai/mistral-large-4-0":{"draws":2,"losses":2,"wins":10},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":18},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":12},"o3":{"draws":2,"losses":4,"wins":32},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":21},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":11},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":13},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":13},"qwen/qwen3.8-max":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":4,"wins":30},"stealth/ox-alpha":{"draws":10,"losses":25,"wins":53},"stealth/space-bunny-alpha":{"draws":3,"losses":4,"wins":15},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":12},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":9},"tencent/hy4-preview":{"draws":3,"losses":6,"wins":19},"thinkingmachines/inkling":{"draws":10,"losses":0,"wins":18},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":23},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":18},"x-ai/grok-4.6":{"draws":3,"losses":10,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":11,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":11,"wins":7},"z-ai/glm-5.2":{"draws":10,"losses":12,"wins":42},"z-ai/glm-5.3":{"draws":5,"losses":8,"wins":11},"z-ai/glm-5.3-flash":{"draws":3,"losses":3,"wins":20},"z-ai/glm-5.3-flashx":{"draws":0,"losses":8,"wins":22}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":4,"wins":31},"claude-fable-5":{"draws":5,"losses":27,"wins":16},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":18,"losses":14,"wins":46},"claude-opus-4-8":{"draws":10,"losses":11,"wins":23},"claude-opus-5":{"draws":8,"losses":49,"wins":25},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":10,"losses":8,"wins":30},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":6,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":15,"wins":6},"elorian/glimpse":{"draws":2,"losses":3,"wins":7},"fireworks/ember-1":{"draws":7,"losses":6,"wins":19},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":30},"gemini-4-argon":{"draws":4,"losses":12,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":14,"wins":35},"google/gemini-3.5-flash-lite":{"draws":21,"losses":11,"wins":52},"google/gemini-3.6-flash":{"draws":16,"losses":27,"wins":49},"google/gemini-3.8-flash":{"draws":11,"losses":15,"wins":22},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":18},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":7,"wins":30},"gpt-5.4":{"draws":8,"losses":14,"wins":24},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":33},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":29},"gpt-5.6-sol":{"draws":7,"losses":22,"wins":19},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":9,"losses":28,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":4,"losses":2,"wins":10},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":35},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":18,"wins":22},"meta/muse-spark-open":{"draws":6,"losses":8,"wins":10},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"minimax/minimax-m3.1-flash":{"draws":3,"losses":1,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":8,"wins":29},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":7},"o3":{"draws":7,"losses":6,"wins":53},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":10,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":17},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":12,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":8,"wins":14},"stealth/ox-alpha":{"draws":23,"losses":44,"wins":91},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":8,"losses":15,"wins":23},"thinkingmachines/inkling":{"draws":12,"losses":2,"wins":50},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":35},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":23},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":5,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":31},"claude-fable-5":{"draws":4,"losses":24,"wins":20},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":26},"claude-opus-4-5":{"draws":10,"losses":18,"wins":50},"claude-opus-4-8":{"draws":7,"losses":11,"wins":26},"claude-opus-5":{"draws":4,"losses":52,"wins":26},"claude-opus-5-5":{"draws":2,"losses":41,"wins":9},"claude-sonnet-5":{"draws":7,"losses":12,"wins":29},"claude-sonnet-5-5":{"draws":5,"losses":20,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":51},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":13,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":10,"wins":12},"elorian/glimpse":{"draws":0,"losses":2,"wins":8},"fireworks/ember-1":{"draws":5,"losses":12,"wins":31},"gemini-3.1-pro-preview":{"draws":5,"losses":6,"wins":21},"gemini-4-argon":{"draws":2,"losses":20,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":36},"google/gemini-3.5-flash-lite":{"draws":15,"losses":10,"wins":59},"google/gemini-3.6-flash":{"draws":11,"losses":25,"wins":56},"google/gemini-3.8-flash":{"draws":6,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":5,"losses":5,"wins":32},"gpt-5.4":{"draws":3,"losses":16,"wins":27},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":5,"losses":18,"wins":21},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":31},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":23},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":28},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":5,"losses":8,"wins":35},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":23},"inception/mercury-3":{"draws":3,"losses":4,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":38},"meta/muse-glimmer-30b":{"draws":7,"losses":3,"wins":32},"meta/muse-spark-1.2":{"draws":9,"losses":10,"wins":27},"meta/muse-spark-1.3":{"draws":4,"losses":20,"wins":24},"meta/muse-spark-open":{"draws":2,"losses":4,"wins":16},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"minimax/minimax-m3.1-flash":{"draws":5,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":5,"losses":6,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":14,"wins":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":10},"o3":{"draws":2,"losses":16,"wins":48},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":30},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":37},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":15,"wins":28},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":10,"losses":14,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":4,"wins":8},"stealth/ox-alpha":{"draws":21,"losses":46,"wins":91},"stealth/space-bunny-alpha":{"draws":6,"losses":7,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":2,"losses":15,"wins":29},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":43},"thinkingmachines/inkling-small":{"draws":7,"losses":5,"wins":36},"unbiased/pareto-26.10":{"draws":2,"losses":3,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":16,"wins":25},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"x-ai/grok-4.7":{"draws":4,"losses":25,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":18,"wins":22},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":8,"losses":14,"wins":26}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":25},"claude-fable-5":{"draws":4,"losses":5,"wins":17},"claude-fable-5-1":{"draws":2,"losses":5,"wins":15},"claude-haiku-5-5":{"draws":1,"losses":2,"wins":13},"claude-opus-4-5":{"draws":1,"losses":1,"wins":34},"claude-opus-4-8":{"draws":0,"losses":2,"wins":24},"claude-opus-5":{"draws":5,"losses":4,"wins":25},"claude-opus-5-5":{"draws":1,"losses":11,"wins":14},"claude-sonnet-5":{"draws":0,"losses":1,"wins":21},"claude-sonnet-5-5":{"draws":2,"losses":7,"wins":19},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":31},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":3,"wins":36},"elorian/glimpse":{"draws":0,"losses":4,"wins":22},"fireworks/ember-1":{"draws":1,"losses":2,"wins":17},"gemini-3.1-pro-preview":{"draws":0,"losses":0,"wins":14},"gemini-4-argon":{"draws":3,"losses":5,"wins":24},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":32},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":51},"google/gemini-3.6-flash":{"draws":1,"losses":4,"wins":35},"google/gemini-3.8-flash":{"draws":2,"losses":0,"wins":20},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":12},"gpt-4.1":{"draws":0,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":0,"wins":22},"gpt-5.4":{"draws":1,"losses":1,"wins":16},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":13},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":28},"gpt-5.5":{"draws":2,"losses":3,"wins":11},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":21},"gpt-5.6-sol":{"draws":2,"losses":1,"wins":19},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":18},"gpt-6-astra":{"draws":3,"losses":8,"wins":11},"gpt-6-luna":{"draws":0,"losses":1,"wins":27},"gpt-6-sol":{"draws":1,"losses":3,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":7,"wins":12},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":16},"inception/mercury-3":{"draws":2,"losses":1,"wins":27},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":15},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":20},"meta/muse-glimmer-30b":{"draws":1,"losses":1,"wins":16},"meta/muse-spark-1.2":{"draws":0,"losses":2,"wins":16},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":27},"meta/muse-spark-open":{"draws":1,"losses":2,"wins":41},"meta/muse-wonder":{"draws":0,"losses":5,"wins":19},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":12},"minimax/minimax-m3.1-flash":{"draws":3,"losses":3,"wins":34},"mistralai/mistral-large-4-0":{"draws":0,"losses":0,"wins":12},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":20},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":0,"losses":0,"wins":32},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":15},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":20},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":17},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":3,"wins":23},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":13},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":20},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":43},"stealth/ox-alpha":{"draws":9,"losses":5,"wins":42},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":16},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":1,"losses":1,"wins":16},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":18},"thinkingmachines/inkling-small":{"draws":0,"losses":3,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":18},"x-ai/grok-4.6":{"draws":2,"losses":0,"wins":22},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":20},"z-ai/glm-5.2":{"draws":1,"losses":3,"wins":48},"z-ai/glm-5.3":{"draws":1,"losses":2,"wins":21},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":21},"z-ai/glm-5.3-flashx":{"draws":1,"losses":0,"wins":23}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":7},"claude-fable-5":{"draws":4,"losses":25,"wins":1},"claude-fable-5-1":{"draws":2,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":4},"claude-opus-4-5":{"draws":11,"losses":36,"wins":3},"claude-opus-4-8":{"draws":6,"losses":22,"wins":2},"claude-opus-5":{"draws":6,"losses":38,"wins":2},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":10,"losses":18,"wins":2},"claude-sonnet-5-5":{"draws":3,"losses":24,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":15,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":15,"wins":1},"elorian/glimpse":{"draws":2,"losses":2,"wins":2},"fireworks/ember-1":{"draws":7,"losses":22,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":15,"wins":7},"gemini-4-argon":{"draws":0,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":3},"google/gemini-3.5-flash-lite":{"draws":21,"losses":26,"wins":9},"google/gemini-3.6-flash":{"draws":13,"losses":40,"wins":5},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":15,"wins":1},"gpt-5.4":{"draws":8,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":6,"losses":20,"wins":6},"gpt-5.5":{"draws":8,"losses":19,"wins":1},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":24,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":14,"wins":3},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":8,"losses":18,"wins":4},"gpt-6-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":8,"wins":7},"inception/mercury-3":{"draws":0,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":17,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":6,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":21,"wins":4},"meta/muse-spark-open":{"draws":4,"losses":11,"wins":3},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":6},"minimax/minimax-m3.1-flash":{"draws":4,"losses":14,"wins":2},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":6,"wins":0},"o3":{"draws":10,"losses":35,"wins":5},"openai/gpt-oss-120b":{"draws":10,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":12,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":1},"qwen/qwen3.8-max-0902":{"draws":9,"losses":19,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":9,"wins":5},"stealth/ox-alpha":{"draws":21,"losses":58,"wins":7},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":15,"wins":13},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":24,"wins":1},"x-ai/grok-4.6":{"draws":5,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":21,"losses":18,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":37,"wins":7},"z-ai/glm-5.3":{"draws":4,"losses":25,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":20,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":31},"claude-fable-5":{"draws":7,"losses":26,"wins":15},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":12,"losses":14,"wins":20},"claude-opus-4-5":{"draws":24,"losses":10,"wins":44},"claude-opus-4-8":{"draws":8,"losses":17,"wins":19},"claude-opus-5":{"draws":12,"losses":57,"wins":13},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"claude-sonnet-5":{"draws":12,"losses":12,"wins":24},"claude-sonnet-5-5":{"draws":6,"losses":25,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":9,"losses":9,"wins":54},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":12,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":12,"wins":17},"elorian/glimpse":{"draws":4,"losses":4,"wins":4},"fireworks/ember-1":{"draws":9,"losses":13,"wins":26},"gemini-3.1-pro-preview":{"draws":6,"losses":9,"wins":33},"gemini-4-argon":{"draws":4,"losses":30,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":10,"losses":4,"wins":30},"google/gemini-3.5-flash-lite":{"draws":17,"losses":10,"wins":57},"google/gemini-3.6-flash":{"draws":12,"losses":23,"wins":57},"google/gemini-3.8-flash":{"draws":5,"losses":21,"wins":22},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":17},"gpt-4.1":{"draws":2,"losses":1,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":8,"wins":26},"gpt-5.4":{"draws":8,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":36},"gpt-5.5":{"draws":10,"losses":12,"wins":22},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":22},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":7,"losses":13,"wins":28},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":4,"losses":33,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inception/mercury-3":{"draws":2,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":28},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":44},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":12,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-spark-open":{"draws":3,"losses":10,"wins":15},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"minimax/minimax-m3.1-flash":{"draws":4,"losses":4,"wins":16},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":25},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":4,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":6},"o3":{"draws":6,"losses":12,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":39},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":21},"qwen/qwen3.8-max":{"draws":14,"losses":11,"wins":23},"qwen/qwen3.8-max-0902":{"draws":9,"losses":22,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":5,"wins":10},"stealth/ox-alpha":{"draws":28,"losses":48,"wins":82},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":20},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":36},"unbiased/pareto-26.10":{"draws":2,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":28},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":20},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":13},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":9,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":18,"losses":20,"wins":58},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":14},"z-ai/glm-5.3-flash":{"draws":3,"losses":20,"wins":25},"z-ai/glm-5.3-flashx":{"draws":11,"losses":19,"wins":18}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":23,"wins":26},"claude-fable-5":{"draws":12,"losses":55,"wins":11},"claude-fable-5-1":{"draws":6,"losses":84,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":48,"wins":11},"claude-opus-4-5":{"draws":35,"losses":55,"wins":36},"claude-opus-4-8":{"draws":15,"losses":45,"wins":10},"claude-opus-5":{"draws":12,"losses":105,"wins":11},"claude-opus-5-5":{"draws":8,"losses":74,"wins":0},"claude-sonnet-5":{"draws":19,"losses":37,"wins":22},"claude-sonnet-5-5":{"draws":16,"losses":49,"wins":13},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":14},"deepseek/deepseek-v4-flash":{"draws":32,"losses":32,"wins":50},"deepseek/deepseek-v4-pro":{"draws":17,"losses":36,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":31,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":33,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":38,"wins":4},"elorian/glimpse":{"draws":5,"losses":7,"wins":4},"fireworks/ember-1":{"draws":29,"losses":35,"wins":14},"gemini-3.1-pro-preview":{"draws":17,"losses":36,"wins":25},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":12,"wins":31},"google/gemini-3.5-flash":{"draws":23,"losses":48,"wins":27},"google/gemini-3.5-flash-lite":{"draws":32,"losses":42,"wins":40},"google/gemini-3.6-flash":{"draws":40,"losses":82,"wins":30},"google/gemini-3.8-flash":{"draws":11,"losses":59,"wins":8},"google/gemma-4-31b-it":{"draws":15,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":9,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":31,"wins":18},"gpt-5.4":{"draws":13,"losses":47,"wins":16},"gpt-5.4-mini":{"draws":18,"losses":16,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":27,"wins":35},"gpt-5.5":{"draws":24,"losses":33,"wins":15},"gpt-5.6-luna":{"draws":26,"losses":27,"wins":25},"gpt-5.6-sol":{"draws":14,"losses":57,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":35,"wins":17},"gpt-6-astra":{"draws":4,"losses":73,"wins":1},"gpt-6-luna":{"draws":22,"losses":38,"wins":18},"gpt-6-sol":{"draws":11,"losses":62,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":74,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":21,"losses":10,"wins":25},"inception/mercury-3":{"draws":7,"losses":13,"wins":2},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":26},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":24,"wins":43},"meta/muse-glimmer-30b":{"draws":23,"losses":18,"wins":27},"meta/muse-spark-1.2":{"draws":17,"losses":42,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":53,"wins":13},"meta/muse-spark-open":{"draws":4,"losses":23,"wins":7},"meta/muse-wonder":{"draws":10,"losses":59,"wins":9},"minimax/minimax-m3":{"draws":12,"losses":14,"wins":14},"minimax/minimax-m3.1-flash":{"draws":10,"losses":21,"wins":11},"mistralai/mistral-large-4-0":{"draws":14,"losses":21,"wins":13},"mistralai/mistral-medium-3-5":{"draws":13,"losses":11,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":39,"wins":17},"nex-agi/nex-n2-pro":{"draws":11,"losses":10,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":21,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":3,"wins":3},"o3":{"draws":17,"losses":61,"wins":32},"openai/gpt-oss-120b":{"draws":20,"losses":21,"wins":27},"poolside/laguna-s-2.1":{"draws":23,"losses":29,"wins":20},"qwen/qwen3.7-max":{"draws":9,"losses":19,"wins":16},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":39,"wins":17},"qwen/qwen3.8-27b":{"draws":9,"losses":34,"wins":13},"qwen/qwen3.8-flash":{"draws":16,"losses":29,"wins":7},"qwen/qwen3.8-max":{"draws":26,"losses":38,"wins":14},"qwen/qwen3.8-max-0902":{"draws":20,"losses":43,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":21,"wins":13},"stealth/ox-alpha":{"draws":45,"losses":160,"wins":63},"stealth/space-bunny-alpha":{"draws":13,"losses":29,"wins":22},"stepfun/step-3.7-flash":{"draws":13,"losses":19,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":17,"wins":12},"tencent/hy4-preview":{"draws":14,"losses":45,"wins":17},"thinkingmachines/inkling":{"draws":25,"losses":33,"wins":48},"thinkingmachines/inkling-small":{"draws":26,"losses":30,"wins":22},"unbiased/pareto-26.10":{"draws":1,"losses":17,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":9},"x-ai/grok-4.5":{"draws":20,"losses":40,"wins":18},"x-ai/grok-4.6":{"draws":19,"losses":47,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":52,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.5":{"draws":38,"losses":38,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":33,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":38,"wins":9},"z-ai/glm-5.2":{"draws":42,"losses":66,"wins":48},"z-ai/glm-5.3":{"draws":10,"losses":59,"wins":7},"z-ai/glm-5.3-flash":{"draws":15,"losses":51,"wins":12},"z-ai/glm-5.3-flashx":{"draws":16,"losses":45,"wins":17}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":12,"wins":57},"claude-fable-5":{"draws":12,"losses":42,"wins":42},"claude-fable-5-1":{"draws":7,"losses":93,"wins":8},"claude-haiku-5-5":{"draws":22,"losses":24,"wins":46},"claude-opus-4-5":{"draws":38,"losses":25,"wins":93},"claude-opus-4-8":{"draws":15,"losses":30,"wins":43},"claude-opus-5":{"draws":27,"losses":104,"wins":33},"claude-opus-5-5":{"draws":13,"losses":84,"wins":7},"claude-sonnet-5":{"draws":14,"losses":21,"wins":61},"claude-sonnet-5-5":{"draws":20,"losses":34,"wins":42},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":29},"deepseek/deepseek-v4-flash":{"draws":24,"losses":7,"wins":113},"deepseek/deepseek-v4-pro":{"draws":17,"losses":20,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":19,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":24,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":13,"wins":25},"elorian/glimpse":{"draws":7,"losses":6,"wins":13},"fireworks/ember-1":{"draws":23,"losses":26,"wins":47},"gemini-3.1-pro-preview":{"draws":16,"losses":24,"wins":56},"gemini-4-argon":{"draws":3,"losses":41,"wins":6},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":54},"google/gemini-3.5-flash":{"draws":23,"losses":34,"wins":63},"google/gemini-3.5-flash-lite":{"draws":36,"losses":19,"wins":113},"google/gemini-3.6-flash":{"draws":25,"losses":42,"wins":85},"google/gemini-3.8-flash":{"draws":20,"losses":40,"wins":36},"google/gemma-4-31b-it":{"draws":15,"losses":2,"wins":39},"gpt-4.1":{"draws":6,"losses":6,"wins":20},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":9},"gpt-5":{"draws":10,"losses":20,"wins":54},"gpt-5.4":{"draws":18,"losses":35,"wins":39},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":44},"gpt-5.4-nano":{"draws":13,"losses":12,"wins":71},"gpt-5.5":{"draws":20,"losses":25,"wins":43},"gpt-5.6-luna":{"draws":20,"losses":18,"wins":58},"gpt-5.6-sol":{"draws":16,"losses":40,"wins":40},"gpt-5.6-terra":{"draws":22,"losses":16,"wins":54},"gpt-6-astra":{"draws":5,"losses":79,"wins":12},"gpt-6-luna":{"draws":26,"losses":16,"wins":54},"gpt-6-sol":{"draws":14,"losses":54,"wins":28},"gpt-6.1-sol":{"draws":9,"losses":74,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":3,"wins":48},"inception/mercury-3":{"draws":6,"losses":3,"wins":21},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":46},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":77},"meta/muse-glimmer-30b":{"draws":19,"losses":9,"wins":56},"meta/muse-spark-1.2":{"draws":15,"losses":27,"wins":50},"meta/muse-spark-1.3":{"draws":16,"losses":37,"wins":43},"meta/muse-spark-open":{"draws":4,"losses":11,"wins":17},"meta/muse-wonder":{"draws":21,"losses":44,"wins":31},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":36},"minimax/minimax-m3.1-flash":{"draws":12,"losses":11,"wins":29},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":32},"mistralai/mistral-medium-3-5":{"draws":16,"losses":2,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":22,"losses":20,"wins":50},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":59},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":2,"wins":13},"o3":{"draws":15,"losses":24,"wins":93},"openai/gpt-oss-120b":{"draws":15,"losses":8,"wins":61},"poolside/laguna-s-2.1":{"draws":20,"losses":13,"wins":59},"qwen/qwen3.7-max":{"draws":19,"losses":7,"wins":30},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":26,"wins":50},"qwen/qwen3.8-27b":{"draws":16,"losses":13,"wins":39},"qwen/qwen3.8-flash":{"draws":16,"losses":11,"wins":37},"qwen/qwen3.8-max":{"draws":22,"losses":19,"wins":55},"qwen/qwen3.8-max-0902":{"draws":27,"losses":34,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":8,"wins":35},"stealth/ox-alpha":{"draws":54,"losses":98,"wins":164},"stealth/space-bunny-alpha":{"draws":13,"losses":9,"wins":54},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":58},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":30},"tencent/hy4-preview":{"draws":18,"losses":22,"wins":52},"thinkingmachines/inkling":{"draws":33,"losses":16,"wins":79},"thinkingmachines/inkling-small":{"draws":24,"losses":6,"wins":66},"unbiased/pareto-26.10":{"draws":3,"losses":20,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":25,"wins":5},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":19},"x-ai/grok-4.5":{"draws":18,"losses":32,"wins":46},"x-ai/grok-4.6":{"draws":21,"losses":31,"wins":44},"x-ai/grok-4.7":{"draws":8,"losses":54,"wins":22},"x-ai/grok-build-0.1":{"draws":9,"losses":1,"wins":22},"xiaomi/mimo-v2.5":{"draws":33,"losses":7,"wins":108},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":21,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":30,"wins":22},"z-ai/glm-5.2":{"draws":42,"losses":27,"wins":123},"z-ai/glm-5.3":{"draws":19,"losses":40,"wins":33},"z-ai/glm-5.3-flash":{"draws":14,"losses":40,"wins":42},"z-ai/glm-5.3-flashx":{"draws":26,"losses":34,"wins":36}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":34},"claude-fable-5":{"draws":6,"losses":23,"wins":19},"claude-fable-5-1":{"draws":4,"losses":43,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":11,"losses":19,"wins":48},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":3,"losses":58,"wins":21},"claude-opus-5-5":{"draws":3,"losses":37,"wins":12},"claude-sonnet-5":{"draws":4,"losses":11,"wins":33},"claude-sonnet-5-5":{"draws":4,"losses":22,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":65},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":13,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":17,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":13,"wins":10},"elorian/glimpse":{"draws":1,"losses":2,"wins":11},"fireworks/ember-1":{"draws":5,"losses":17,"wins":26},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":34},"gemini-4-argon":{"draws":0,"losses":19,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":45},"google/gemini-3.5-flash-lite":{"draws":5,"losses":9,"wins":70},"google/gemini-3.6-flash":{"draws":10,"losses":28,"wins":54},"google/gemini-3.8-flash":{"draws":4,"losses":12,"wins":16},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":3,"losses":9,"wins":30},"gpt-5.4":{"draws":4,"losses":18,"wins":24},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":6,"losses":10,"wins":32},"gpt-5.5":{"draws":6,"losses":19,"wins":19},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":32},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":23},"gpt-5.6-terra":{"draws":8,"losses":15,"wins":23},"gpt-6-astra":{"draws":6,"losses":38,"wins":4},"gpt-6-luna":{"draws":11,"losses":8,"wins":29},"gpt-6-sol":{"draws":7,"losses":28,"wins":13},"gpt-6.1-sol":{"draws":7,"losses":32,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":3,"wins":26},"inception/mercury-3":{"draws":2,"losses":4,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":42},"meta/muse-glimmer-30b":{"draws":4,"losses":7,"wins":31},"meta/muse-spark-1.2":{"draws":3,"losses":14,"wins":29},"meta/muse-spark-1.3":{"draws":8,"losses":18,"wins":22},"meta/muse-spark-open":{"draws":1,"losses":3,"wins":18},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":22},"minimax/minimax-m3.1-flash":{"draws":1,"losses":5,"wins":16},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":10,"wins":30},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":8,"wins":3},"o3":{"draws":4,"losses":10,"wins":52},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":38},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":38},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":14,"wins":30},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":26},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":19},"qwen/qwen3.8-max":{"draws":7,"losses":19,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":15,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":6,"wins":16},"stealth/ox-alpha":{"draws":22,"losses":43,"wins":93},"stealth/space-bunny-alpha":{"draws":2,"losses":8,"wins":28},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":28},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":5,"losses":21,"wins":20},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":47},"thinkingmachines/inkling-small":{"draws":6,"losses":10,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":23,"wins":21},"x-ai/grok-4.6":{"draws":4,"losses":16,"wins":28},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":7,"losses":15,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":9},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":13},"z-ai/glm-5.3-flash":{"draws":6,"losses":15,"wins":27},"z-ai/glm-5.3-flashx":{"draws":6,"losses":16,"wins":26}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":9,"wins":17},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":22,"wins":11},"claude-opus-4-5":{"draws":33,"losses":18,"wins":27},"claude-opus-4-8":{"draws":14,"losses":16,"wins":14},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":26,"losses":5,"wins":41},"deepseek/deepseek-v4-pro":{"draws":15,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":11,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":11,"wins":6},"elorian/glimpse":{"draws":6,"losses":7,"wins":5},"fireworks/ember-1":{"draws":15,"losses":18,"wins":15},"gemini-3.1-pro-preview":{"draws":16,"losses":19,"wins":13},"gemini-4-argon":{"draws":1,"losses":26,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":18,"losses":19,"wins":23},"google/gemini-3.5-flash-lite":{"draws":33,"losses":16,"wins":35},"google/gemini-3.6-flash":{"draws":27,"losses":40,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":1,"wins":14},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":5,"wins":13},"gpt-5.4":{"draws":10,"losses":22,"wins":14},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":32},"gpt-5.5":{"draws":19,"losses":15,"wins":10},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":15,"wins":18},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":19,"losses":12,"wins":17},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inception/mercury-3":{"draws":4,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":19,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":18,"wins":15},"meta/muse-spark-1.3":{"draws":15,"losses":20,"wins":13},"meta/muse-spark-open":{"draws":6,"losses":9,"wins":7},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":3,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":2},"o3":{"draws":9,"losses":24,"wins":33},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":20},"poolside/laguna-s-2.1":{"draws":19,"losses":13,"wins":14},"qwen/qwen3.7-max":{"draws":13,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":16,"wins":15},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":14},"qwen/qwen3.8-flash":{"draws":10,"losses":8,"wins":14},"qwen/qwen3.8-max":{"draws":24,"losses":11,"wins":13},"qwen/qwen3.8-max-0902":{"draws":15,"losses":20,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":9,"wins":5},"stealth/ox-alpha":{"draws":41,"losses":68,"wins":49},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":16,"losses":15,"wins":15},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":20,"losses":5,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.6":{"draws":17,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":27,"losses":11,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":36,"losses":21,"wins":39},"z-ai/glm-5.3":{"draws":7,"losses":30,"wins":9},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":13},"z-ai/glm-5.3-flashx":{"draws":19,"losses":13,"wins":16}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":28},"claude-fable-5":{"draws":10,"losses":13,"wins":19},"claude-fable-5-1":{"draws":5,"losses":35,"wins":8},"claude-haiku-5-5":{"draws":6,"losses":12,"wins":22},"claude-opus-4-5":{"draws":11,"losses":8,"wins":49},"claude-opus-4-8":{"draws":5,"losses":10,"wins":23},"claude-opus-5":{"draws":8,"losses":45,"wins":17},"claude-opus-5-5":{"draws":4,"losses":34,"wins":8},"claude-sonnet-5":{"draws":6,"losses":7,"wins":29},"claude-sonnet-5-5":{"draws":9,"losses":12,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":5,"wins":49},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":10,"wins":16},"elorian/glimpse":{"draws":0,"losses":0,"wins":8},"fireworks/ember-1":{"draws":5,"losses":9,"wins":28},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":28},"gemini-4-argon":{"draws":1,"losses":12,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":4,"losses":7,"wins":43},"google/gemini-3.5-flash-lite":{"draws":9,"losses":5,"wins":62},"google/gemini-3.6-flash":{"draws":15,"losses":12,"wins":55},"google/gemini-3.8-flash":{"draws":2,"losses":13,"wins":27},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":33},"gpt-5.4":{"draws":5,"losses":2,"wins":21},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":21},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":36},"gpt-5.5":{"draws":8,"losses":9,"wins":23},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":32},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":21},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":31},"gpt-6-astra":{"draws":2,"losses":35,"wins":5},"gpt-6-luna":{"draws":8,"losses":8,"wins":26},"gpt-6-sol":{"draws":2,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":20},"inception/mercury-3":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":24},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":39},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":33},"meta/muse-spark-1.2":{"draws":5,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":27},"meta/muse-spark-open":{"draws":6,"losses":5,"wins":13},"meta/muse-wonder":{"draws":5,"losses":17,"wins":20},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":4,"losses":1,"wins":19},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":8,"wins":27},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":11},"o3":{"draws":2,"losses":7,"wins":55},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":29},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":34},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":11,"wins":26},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":21},"qwen/qwen3.8-max":{"draws":7,"losses":11,"wins":24},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":5,"wins":8},"stealth/ox-alpha":{"draws":34,"losses":28,"wins":80},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":28},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":15},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":28},"thinkingmachines/inkling":{"draws":11,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":8,"losses":3,"wins":31},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":8,"wins":25},"x-ai/grok-4.6":{"draws":9,"losses":9,"wins":24},"x-ai/grok-4.7":{"draws":3,"losses":21,"wins":12},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":10,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":55},"z-ai/glm-5.3":{"draws":4,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":29},"z-ai/glm-5.3-flashx":{"draws":6,"losses":13,"wins":23}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":3,"wins":26},"claude-fable-5":{"draws":8,"losses":16,"wins":18},"claude-fable-5-1":{"draws":0,"losses":37,"wins":11},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":22},"claude-opus-4-5":{"draws":15,"losses":9,"wins":44},"claude-opus-4-8":{"draws":7,"losses":7,"wins":24},"claude-opus-5":{"draws":5,"losses":34,"wins":31},"claude-opus-5-5":{"draws":2,"losses":35,"wins":9},"claude-sonnet-5":{"draws":7,"losses":7,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":11,"losses":2,"wins":49},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":8,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":5,"wins":15},"elorian/glimpse":{"draws":4,"losses":5,"wins":13},"fireworks/ember-1":{"draws":8,"losses":8,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":5,"wins":29},"gemini-4-argon":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":33},"google/gemini-3.5-flash-lite":{"draws":17,"losses":6,"wins":53},"google/gemini-3.6-flash":{"draws":20,"losses":15,"wins":47},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":17},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":5,"wins":24},"gpt-5.4":{"draws":14,"losses":11,"wins":17},"gpt-5.4-mini":{"draws":9,"losses":1,"wins":18},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":32},"gpt-5.5":{"draws":10,"losses":5,"wins":11},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":13,"wins":23},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":25},"gpt-6-astra":{"draws":0,"losses":37,"wins":5},"gpt-6-luna":{"draws":15,"losses":3,"wins":24},"gpt-6-sol":{"draws":4,"losses":23,"wins":15},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inception/mercury-3":{"draws":2,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":5,"wins":33},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":25},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":29},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":24},"meta/muse-spark-open":{"draws":2,"losses":7,"wins":7},"meta/muse-wonder":{"draws":8,"losses":14,"wins":20},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":15},"minimax/minimax-m3.1-flash":{"draws":7,"losses":3,"wins":14},"mistralai/mistral-large-4-0":{"draws":4,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":19},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":1,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":11},"o3":{"draws":6,"losses":7,"wins":51},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":26},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":11,"losses":9,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":22},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":4,"wins":12},"stealth/ox-alpha":{"draws":31,"losses":30,"wins":81},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":11,"losses":10,"wins":21},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":44},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":6,"wins":24},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":19},"x-ai/grok-4.7":{"draws":4,"losses":17,"wins":15},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":1,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":24,"losses":7,"wins":53},"z-ai/glm-5.3":{"draws":7,"losses":23,"wins":10},"z-ai/glm-5.3-flash":{"draws":2,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":10,"losses":9,"wins":23}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":9,"wins":19},"claude-fable-5":{"draws":13,"losses":23,"wins":12},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":30,"losses":17,"wins":31},"claude-opus-4-8":{"draws":15,"losses":10,"wins":19},"claude-opus-5":{"draws":8,"losses":64,"wins":10},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":14,"losses":13,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":28,"losses":3,"wins":41},"deepseek/deepseek-v4-pro":{"draws":13,"losses":9,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":7,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":12,"wins":6},"elorian/glimpse":{"draws":6,"losses":4,"wins":6},"fireworks/ember-1":{"draws":18,"losses":8,"wins":22},"gemini-3.1-pro-preview":{"draws":14,"losses":13,"wins":21},"gemini-4-argon":{"draws":1,"losses":15,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":21,"losses":10,"wins":29},"google/gemini-3.5-flash-lite":{"draws":30,"losses":12,"wins":42},"google/gemini-3.6-flash":{"draws":24,"losses":32,"wins":36},"google/gemini-3.8-flash":{"draws":14,"losses":16,"wins":18},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":14},"gpt-4.1":{"draws":8,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":19,"losses":18,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":18,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":13,"losses":5,"wins":14},"gpt-5.6-sol":{"draws":10,"losses":24,"wins":14},"gpt-5.6-terra":{"draws":17,"losses":7,"wins":22},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":17},"inception/mercury-3":{"draws":8,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":17},"meta/muse-spark-open":{"draws":10,"losses":7,"wins":9},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"minimax/minimax-m3.1-flash":{"draws":7,"losses":3,"wins":14},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":13,"wins":17},"nex-agi/nex-n2-pro":{"draws":7,"losses":1,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":1,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":8},"o3":{"draws":17,"losses":14,"wins":35},"openai/gpt-oss-120b":{"draws":19,"losses":4,"wins":19},"poolside/laguna-s-2.1":{"draws":19,"losses":5,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":11,"wins":20},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":15,"wins":15},"qwen/qwen3.8-max-0902":{"draws":18,"losses":9,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":6,"wins":8},"stealth/ox-alpha":{"draws":44,"losses":57,"wins":57},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":18,"losses":12,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":5,"wins":38},"thinkingmachines/inkling-small":{"draws":19,"losses":6,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":8,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":25},"x-ai/grok-4.6":{"draws":13,"losses":20,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":3,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":39,"losses":23,"wins":34},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":15},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":37},"claude-fable-5":{"draws":4,"losses":16,"wins":28},"claude-fable-5-1":{"draws":5,"losses":34,"wins":15},"claude-haiku-5-5":{"draws":7,"losses":5,"wins":34},"claude-opus-4-5":{"draws":6,"losses":14,"wins":58},"claude-opus-4-8":{"draws":5,"losses":5,"wins":34},"claude-opus-5":{"draws":7,"losses":40,"wins":35},"claude-opus-5-5":{"draws":6,"losses":31,"wins":15},"claude-sonnet-5":{"draws":0,"losses":3,"wins":45},"claude-sonnet-5-5":{"draws":2,"losses":14,"wins":32},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":66},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":2,"wins":21},"elorian/glimpse":{"draws":0,"losses":4,"wins":12},"fireworks/ember-1":{"draws":5,"losses":8,"wins":35},"gemini-3.1-pro-preview":{"draws":5,"losses":1,"wins":42},"gemini-4-argon":{"draws":0,"losses":15,"wins":9},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":50},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":10,"losses":15,"wins":67},"google/gemini-3.8-flash":{"draws":4,"losses":10,"wins":34},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":0,"losses":3,"wins":39},"gpt-5.4":{"draws":2,"losses":12,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":5,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":2,"losses":6,"wins":40},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":26},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":38},"gpt-6-astra":{"draws":6,"losses":35,"wins":7},"gpt-6-luna":{"draws":9,"losses":2,"wins":37},"gpt-6-sol":{"draws":6,"losses":17,"wins":25},"gpt-6.1-sol":{"draws":5,"losses":32,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":2,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":46},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":39},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":42},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-spark-open":{"draws":2,"losses":6,"wins":14},"meta/muse-wonder":{"draws":2,"losses":16,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":1,"losses":3,"wins":22},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":40},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":11},"o3":{"draws":1,"losses":8,"wins":57},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":37},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":44},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":6,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":1,"wins":11},"stealth/ox-alpha":{"draws":14,"losses":16,"wins":128},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":24},"tencent/hy4-preview":{"draws":3,"losses":14,"wins":29},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":58},"thinkingmachines/inkling-small":{"draws":1,"losses":1,"wins":46},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":39},"x-ai/grok-4.6":{"draws":6,"losses":12,"wins":30},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":19},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.2":{"draws":5,"losses":4,"wins":87},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":5,"losses":12,"wins":31},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":33}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":14,"losses":24,"wins":10},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":26,"losses":25,"wins":27},"claude-opus-4-8":{"draws":6,"losses":19,"wins":19},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":18,"losses":11,"wins":19},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":19,"losses":9,"wins":44},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":10,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":20,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":15,"wins":7},"elorian/glimpse":{"draws":2,"losses":0,"wins":4},"fireworks/ember-1":{"draws":15,"losses":14,"wins":19},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":19},"gemini-4-argon":{"draws":1,"losses":19,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":19,"losses":11,"wins":30},"google/gemini-3.5-flash-lite":{"draws":23,"losses":11,"wins":50},"google/gemini-3.6-flash":{"draws":30,"losses":34,"wins":28},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":14},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":11,"wins":20},"gpt-5.4":{"draws":12,"losses":20,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":13,"losses":18,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":21},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":10},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"gpt-6-sol":{"draws":11,"losses":29,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":7,"losses":7,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":29},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":15},"meta/muse-spark-open":{"draws":6,"losses":9,"wins":9},"meta/muse-wonder":{"draws":8,"losses":26,"wins":14},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"minimax/minimax-m3.1-flash":{"draws":4,"losses":6,"wins":12},"mistralai/mistral-large-4-0":{"draws":15,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":11,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":5},"o3":{"draws":11,"losses":19,"wins":36},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":22,"wins":13},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.8-max":{"draws":18,"losses":17,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":7,"wins":6},"stealth/ox-alpha":{"draws":39,"losses":62,"wins":57},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":13},"tencent/hy4-preview":{"draws":10,"losses":18,"wins":18},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":30},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":20,"wins":15},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":2,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":21,"wins":38},"z-ai/glm-5.3":{"draws":13,"losses":22,"wins":11},"z-ai/glm-5.3-flash":{"draws":9,"losses":20,"wins":19},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":0,"losses":8,"wins":40},"claude-fable-5-1":{"draws":4,"losses":14,"wins":36},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":1,"losses":6,"wins":71},"claude-opus-4-8":{"draws":1,"losses":2,"wins":41},"claude-opus-5":{"draws":3,"losses":9,"wins":70},"claude-opus-5-5":{"draws":4,"losses":16,"wins":32},"claude-sonnet-5":{"draws":0,"losses":2,"wins":46},"claude-sonnet-5-5":{"draws":2,"losses":8,"wins":38},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":72},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":46},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":0,"wins":21},"elorian/glimpse":{"draws":0,"losses":1,"wins":15},"fireworks/ember-1":{"draws":0,"losses":1,"wins":47},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"gemini-4-argon":{"draws":4,"losses":4,"wins":16},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":58},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":81},"google/gemini-3.6-flash":{"draws":1,"losses":4,"wins":87},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":44},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":0,"losses":3,"wins":43},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":46},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":41},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":0,"losses":6,"wins":26},"gpt-6-luna":{"draws":3,"losses":0,"wins":45},"gpt-6-sol":{"draws":6,"losses":4,"wins":38},"gpt-6.1-sol":{"draws":5,"losses":8,"wins":35},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inception/mercury-3":{"draws":1,"losses":0,"wins":11},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":52},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":46},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":46},"meta/muse-spark-open":{"draws":1,"losses":0,"wins":17},"meta/muse-wonder":{"draws":3,"losses":3,"wins":42},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":44},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":14},"o3":{"draws":1,"losses":1,"wins":64},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":30},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":22},"stealth/ox-alpha":{"draws":5,"losses":4,"wins":149},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":0,"losses":3,"wins":43},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":3,"losses":1,"wins":6},"unbiased/pareto-26.10-preview":{"draws":3,"losses":5,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":46},"x-ai/grok-4.6":{"draws":0,"losses":1,"wins":47},"x-ai/grok-4.7":{"draws":3,"losses":3,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":28},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":39},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":45},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":45}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":24},"claude-fable-5":{"draws":9,"losses":26,"wins":13},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":20,"wins":21},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":7,"losses":17,"wins":20},"claude-opus-5":{"draws":9,"losses":62,"wins":11},"claude-opus-5-5":{"draws":7,"losses":43,"wins":2},"claude-sonnet-5":{"draws":8,"losses":14,"wins":26},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":10,"losses":13,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":13,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":12,"wins":9},"elorian/glimpse":{"draws":3,"losses":10,"wins":7},"fireworks/ember-1":{"draws":6,"losses":21,"wins":21},"gemini-3.1-pro-preview":{"draws":3,"losses":22,"wins":23},"gemini-4-argon":{"draws":2,"losses":25,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":10,"losses":21,"wins":29},"google/gemini-3.5-flash-lite":{"draws":12,"losses":20,"wins":52},"google/gemini-3.6-flash":{"draws":16,"losses":35,"wins":41},"google/gemini-3.8-flash":{"draws":8,"losses":21,"wins":19},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":19},"gpt-4.1":{"draws":1,"losses":6,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":14,"wins":23},"gpt-5.4":{"draws":11,"losses":18,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":32},"gpt-5.5":{"draws":9,"losses":18,"wins":17},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":28},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":13},"gpt-5.6-terra":{"draws":8,"losses":14,"wins":24},"gpt-6-astra":{"draws":8,"losses":36,"wins":4},"gpt-6-luna":{"draws":5,"losses":13,"wins":14},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inception/mercury-3":{"draws":1,"losses":5,"wins":8},"inclusionai/ling-3.0-flash":{"draws":2,"losses":6,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":9,"wins":38},"meta/muse-glimmer-30b":{"draws":4,"losses":8,"wins":30},"meta/muse-spark-1.2":{"draws":9,"losses":19,"wins":18},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-spark-open":{"draws":1,"losses":9,"wins":6},"meta/muse-wonder":{"draws":7,"losses":26,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"minimax/minimax-m3.1-flash":{"draws":5,"losses":9,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":9,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":16,"wins":22},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":9,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":10},"o3":{"draws":2,"losses":20,"wins":44},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":29},"poolside/laguna-s-2.1":{"draws":4,"losses":14,"wins":28},"qwen/qwen3.7-max":{"draws":2,"losses":8,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":9,"wins":22},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":30,"losses":57,"wins":71},"stealth/space-bunny-alpha":{"draws":7,"losses":8,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":20},"thinkingmachines/inkling":{"draws":8,"losses":11,"wins":45},"thinkingmachines/inkling-small":{"draws":4,"losses":10,"wins":34},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":11,"losses":26,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":13,"losses":13,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":20,"losses":27,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":7,"wins":36},"claude-fable-5":{"draws":4,"losses":10,"wins":34},"claude-fable-5-1":{"draws":4,"losses":24,"wins":26},"claude-haiku-5-5":{"draws":5,"losses":8,"wins":33},"claude-opus-4-5":{"draws":3,"losses":11,"wins":64},"claude-opus-4-8":{"draws":3,"losses":10,"wins":31},"claude-opus-5":{"draws":12,"losses":25,"wins":45},"claude-opus-5-5":{"draws":6,"losses":27,"wins":19},"claude-sonnet-5":{"draws":1,"losses":6,"wins":41},"claude-sonnet-5-5":{"draws":5,"losses":10,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":61},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":6,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":6,"wins":17},"elorian/glimpse":{"draws":1,"losses":3,"wins":12},"fireworks/ember-1":{"draws":3,"losses":6,"wins":39},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":34},"gemini-4-argon":{"draws":1,"losses":13,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":46},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":6,"losses":17,"wins":69},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":38},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":26},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":6,"wins":36},"gpt-5.4":{"draws":3,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":1,"losses":4,"wins":27},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":42},"gpt-5.5":{"draws":3,"losses":7,"wins":34},"gpt-5.6-luna":{"draws":1,"losses":6,"wins":41},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":37},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":37},"gpt-6-astra":{"draws":4,"losses":32,"wins":12},"gpt-6-luna":{"draws":6,"losses":4,"wins":38},"gpt-6-sol":{"draws":3,"losses":9,"wins":20},"gpt-6.1-sol":{"draws":5,"losses":23,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":31},"inception/mercury-3":{"draws":0,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":4,"losses":5,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":6,"wins":34},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":40},"meta/muse-spark-open":{"draws":1,"losses":0,"wins":19},"meta/muse-wonder":{"draws":2,"losses":8,"wins":38},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":21},"minimax/minimax-m3.1-flash":{"draws":1,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":3,"losses":5,"wins":22},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":7,"wins":39},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":9,"wins":57},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":36},"poolside/laguna-s-2.1":{"draws":1,"losses":6,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":1,"losses":5,"wins":26},"qwen/qwen3.8-max":{"draws":0,"losses":8,"wins":40},"qwen/qwen3.8-max-0902":{"draws":0,"losses":9,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":18},"stealth/ox-alpha":{"draws":13,"losses":20,"wins":125},"stealth/space-bunny-alpha":{"draws":0,"losses":4,"wins":34},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":22},"tencent/hy4-preview":{"draws":4,"losses":6,"wins":36},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":55},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":45},"unbiased/pareto-26.10":{"draws":2,"losses":7,"wins":3},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":1,"losses":10,"wins":37},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":40},"x-ai/grok-4.7":{"draws":5,"losses":12,"wins":25},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":5,"losses":13,"wins":78},"z-ai/glm-5.3":{"draws":5,"losses":12,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":34},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":36}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":44},"claude-fable-5":{"draws":3,"losses":5,"wins":40},"claude-fable-5-1":{"draws":6,"losses":17,"wins":31},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":0,"losses":2,"wins":76},"claude-opus-4-8":{"draws":1,"losses":1,"wins":42},"claude-opus-5":{"draws":7,"losses":13,"wins":62},"claude-opus-5-5":{"draws":5,"losses":22,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":7,"wins":39},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":71},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":5,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":5,"wins":21},"elorian/glimpse":{"draws":0,"losses":0,"wins":8},"fireworks/ember-1":{"draws":0,"losses":2,"wins":46},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":46},"gemini-4-argon":{"draws":2,"losses":2,"wins":16},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":55},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":84},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":82},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":42},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":3,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":5,"wins":38},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":45},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":38},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":44},"gpt-6-astra":{"draws":8,"losses":15,"wins":25},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":4,"wins":39},"gpt-6.1-sol":{"draws":2,"losses":7,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inception/mercury-3":{"draws":0,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":51},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":47},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":25},"meta/muse-wonder":{"draws":4,"losses":4,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":42},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":5},"o3":{"draws":0,"losses":2,"wins":64},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":41},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":30},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":30},"stealth/ox-alpha":{"draws":2,"losses":5,"wins":151},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":1,"losses":3,"wins":6},"unbiased/pareto-26.10-preview":{"draws":1,"losses":6,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":46},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":42},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":6,"losses":3,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":2,"wins":43},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":42}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":11,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":27,"wins":0},"claude-opus-4-5":{"draws":28,"losses":30,"wins":2},"claude-opus-4-8":{"draws":10,"losses":24,"wins":2},"claude-opus-5":{"draws":11,"losses":45,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":12,"losses":23,"wins":1},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":23,"losses":26,"wins":7},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":17,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":13,"wins":0},"elorian/glimpse":{"draws":1,"losses":6,"wins":3},"fireworks/ember-1":{"draws":15,"losses":20,"wins":1},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":5},"gemini-4-argon":{"draws":1,"losses":11,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":20,"losses":25,"wins":1},"google/gemini-3.5-flash-lite":{"draws":28,"losses":27,"wins":7},"google/gemini-3.6-flash":{"draws":26,"losses":40,"wins":2},"google/gemini-3.8-flash":{"draws":8,"losses":27,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":8},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":12,"losses":16,"wins":2},"gpt-5.4":{"draws":13,"losses":21,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":4},"gpt-5.5":{"draws":13,"losses":17,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":12,"losses":22,"wins":2},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":2},"gpt-6-sol":{"draws":4,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":0},"inception/mercury-3":{"draws":8,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":13,"losses":10,"wins":7},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":17,"wins":4},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-open":{"draws":5,"losses":11,"wins":0},"meta/muse-wonder":{"draws":8,"losses":28,"wins":0},"minimax/minimax-m3":{"draws":12,"losses":7,"wins":1},"minimax/minimax-m3.1-flash":{"draws":8,"losses":9,"wins":1},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":10,"wins":3},"o3":{"draws":9,"losses":37,"wins":4},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":11,"wins":2},"qwen/qwen3.8-max":{"draws":17,"losses":17,"wins":2},"qwen/qwen3.8-max-0902":{"draws":17,"losses":16,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":34,"losses":57,"wins":9},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":1},"stepfun/step-3.7-flash":{"draws":8,"losses":13,"wins":5},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"tencent/hy4-preview":{"draws":14,"losses":18,"wins":2},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":7},"thinkingmachines/inkling-small":{"draws":18,"losses":13,"wins":5},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":0},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":29,"losses":27,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":32,"losses":34,"wins":6},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":2}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":10},"claude-fable-5":{"draws":8,"losses":8,"wins":2},"claude-fable-5-1":{"draws":1,"losses":17,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":7,"wins":8},"claude-opus-4-5":{"draws":15,"losses":6,"wins":13},"claude-opus-4-8":{"draws":5,"losses":7,"wins":2},"claude-opus-5":{"draws":5,"losses":27,"wins":2},"claude-opus-5-5":{"draws":1,"losses":18,"wins":1},"claude-sonnet-5":{"draws":7,"losses":4,"wins":5},"claude-sonnet-5-5":{"draws":4,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":2,"wins":15},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":11,"wins":6},"elorian/glimpse":{"draws":0,"losses":7,"wins":7},"fireworks/ember-1":{"draws":10,"losses":2,"wins":8},"gemini-3.1-pro-preview":{"draws":7,"losses":1,"wins":10},"gemini-4-argon":{"draws":5,"losses":22,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":14},"google/gemini-3.5-flash-lite":{"draws":12,"losses":1,"wins":17},"google/gemini-3.6-flash":{"draws":8,"losses":16,"wins":12},"google/gemini-3.8-flash":{"draws":6,"losses":7,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":2,"wins":7},"gpt-5.4":{"draws":3,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":3,"wins":4},"gpt-5.5":{"draws":8,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":9,"losses":1,"wins":6},"gpt-5.6-sol":{"draws":4,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":7},"gpt-6-astra":{"draws":1,"losses":9,"wins":0},"gpt-6-luna":{"draws":9,"losses":5,"wins":8},"gpt-6-sol":{"draws":4,"losses":13,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":9,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":4},"inception/mercury-3":{"draws":4,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":0,"wins":10},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":6,"wins":5},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":1},"meta/muse-spark-open":{"draws":6,"losses":12,"wins":8},"meta/muse-wonder":{"draws":7,"losses":5,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":5},"minimax/minimax-m3.1-flash":{"draws":5,"losses":4,"wins":11},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":8},"o3":{"draws":4,"losses":2,"wins":6},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":13,"losses":0,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":1,"wins":3},"qwen/qwen3.8-27b":{"draws":6,"losses":2,"wins":10},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-max":{"draws":7,"losses":3,"wins":6},"qwen/qwen3.8-max-0902":{"draws":8,"losses":6,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":4,"wins":12},"stealth/ox-alpha":{"draws":18,"losses":12,"wins":12},"stealth/space-bunny-alpha":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":5},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":7,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":11},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":9},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":2},"x-ai/grok-4.6":{"draws":10,"losses":2,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":12,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":13,"losses":0,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":6,"wins":9},"z-ai/glm-5.3":{"draws":5,"losses":4,"wins":5},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":6,"wins":6}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":8,"wins":15},"claude-fable-5":{"draws":8,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":43,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":17,"wins":8},"claude-opus-4-5":{"draws":28,"losses":27,"wins":13},"claude-opus-4-8":{"draws":12,"losses":18,"wins":8},"claude-opus-5":{"draws":8,"losses":66,"wins":6},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":15,"losses":18,"wins":9},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":12},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":30,"losses":11,"wins":21},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":16,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":14,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":17,"wins":3},"elorian/glimpse":{"draws":2,"losses":0,"wins":6},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":16,"losses":18,"wins":8},"gemini-4-argon":{"draws":2,"losses":19,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":19,"losses":21,"wins":12},"google/gemini-3.5-flash-lite":{"draws":29,"losses":21,"wins":22},"google/gemini-3.6-flash":{"draws":29,"losses":31,"wins":20},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":6},"google/gemma-4-31b-it":{"draws":15,"losses":4,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":16,"losses":14,"wins":8},"gpt-5.4":{"draws":11,"losses":22,"wins":7},"gpt-5.4-mini":{"draws":17,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":15},"gpt-5.5":{"draws":21,"losses":16,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":20,"losses":15,"wins":5},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":8},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":9},"inception/mercury-3":{"draws":1,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":3},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":6,"wins":17},"meta/muse-glimmer-30b":{"draws":15,"losses":2,"wins":9},"meta/muse-spark-1.2":{"draws":13,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":14,"losses":20,"wins":8},"meta/muse-spark-open":{"draws":7,"losses":11,"wins":8},"meta/muse-wonder":{"draws":12,"losses":25,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":8},"minimax/minimax-m3.1-flash":{"draws":6,"losses":8,"wins":8},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":5,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":4,"wins":1},"o3":{"draws":11,"losses":27,"wins":16},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":12},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":14,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":6,"wins":3},"stealth/ox-alpha":{"draws":35,"losses":80,"wins":27},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":16,"losses":18,"wins":6},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":23},"thinkingmachines/inkling-small":{"draws":22,"losses":3,"wins":17},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":13,"losses":23,"wins":6},"x-ai/grok-4.6":{"draws":12,"losses":26,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":26,"losses":10,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":4,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":6},"z-ai/glm-5.2":{"draws":41,"losses":28,"wins":15},"z-ai/glm-5.3":{"draws":12,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":10}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":29},"claude-fable-5":{"draws":8,"losses":26,"wins":14},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":19},"claude-opus-4-5":{"draws":18,"losses":18,"wins":42},"claude-opus-4-8":{"draws":8,"losses":14,"wins":22},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":9,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":16,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":7,"wins":8},"elorian/glimpse":{"draws":1,"losses":7,"wins":2},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":14,"wins":24},"gemini-4-argon":{"draws":3,"losses":23,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":17,"wins":33},"google/gemini-3.5-flash-lite":{"draws":16,"losses":15,"wins":53},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":18,"wins":23},"google/gemma-4-31b-it":{"draws":5,"losses":5,"wins":18},"gpt-4.1":{"draws":7,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":6,"losses":5,"wins":31},"gpt-5.4":{"draws":9,"losses":20,"wins":17},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":27},"gpt-5.5":{"draws":8,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":15},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":24},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":11,"losses":11,"wins":26},"gpt-6-sol":{"draws":7,"losses":31,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":34,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":18},"inception/mercury-3":{"draws":3,"losses":2,"wins":13},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":28},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":15},"meta/muse-spark-1.3":{"draws":6,"losses":21,"wins":21},"meta/muse-spark-open":{"draws":3,"losses":6,"wins":9},"meta/muse-wonder":{"draws":9,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":5,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":23},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":9},"o3":{"draws":6,"losses":21,"wins":39},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":34},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":21},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-max-0902":{"draws":7,"losses":16,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":8,"wins":8},"stealth/ox-alpha":{"draws":30,"losses":57,"wins":71},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":4,"losses":18,"wins":24},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":20,"wins":17},"x-ai/grok-4.6":{"draws":10,"losses":22,"wins":16},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":52},"z-ai/glm-5.3":{"draws":6,"losses":19,"wins":21},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":6,"wins":33},"claude-fable-5":{"draws":6,"losses":21,"wins":21},"claude-fable-5-1":{"draws":4,"losses":41,"wins":9},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":12,"losses":11,"wins":55},"claude-opus-4-8":{"draws":7,"losses":10,"wins":27},"claude-opus-5":{"draws":11,"losses":51,"wins":20},"claude-opus-5-5":{"draws":1,"losses":42,"wins":9},"claude-sonnet-5":{"draws":6,"losses":8,"wins":34},"claude-sonnet-5-5":{"draws":5,"losses":19,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":62},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":11,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":8,"wins":11},"elorian/glimpse":{"draws":2,"losses":2,"wins":6},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":6,"losses":11,"wins":31},"gemini-4-argon":{"draws":1,"losses":12,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":25},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":68},"google/gemini-3.6-flash":{"draws":11,"losses":21,"wins":60},"google/gemini-3.8-flash":{"draws":10,"losses":16,"wins":22},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":6,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":2,"wins":31},"gpt-5.4":{"draws":11,"losses":13,"wins":22},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":6,"losses":12,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":33},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":28},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":31},"gpt-6-astra":{"draws":5,"losses":36,"wins":7},"gpt-6-luna":{"draws":6,"losses":6,"wins":36},"gpt-6-sol":{"draws":8,"losses":27,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":27},"inception/mercury-3":{"draws":3,"losses":2,"wins":9},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":5,"losses":6,"wins":31},"meta/muse-spark-1.2":{"draws":6,"losses":11,"wins":29},"meta/muse-spark-1.3":{"draws":5,"losses":3,"wins":24},"meta/muse-spark-open":{"draws":4,"losses":5,"wins":9},"meta/muse-wonder":{"draws":8,"losses":21,"wins":19},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":28},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":13},"o3":{"draws":3,"losses":9,"wins":54},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":33},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":36},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":22},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":27},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":6,"losses":12,"wins":30},"qwen/qwen3.8-max-0902":{"draws":11,"losses":15,"wins":22},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":3,"wins":15},"stealth/ox-alpha":{"draws":23,"losses":31,"wins":104},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":29},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":53},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":42},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.6":{"draws":9,"losses":14,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":24,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":10,"losses":15,"wins":71},"z-ai/glm-5.3":{"draws":10,"losses":16,"wins":20},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":29}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":14},"claude-fable-5":{"draws":2,"losses":15,"wins":9},"claude-fable-5-1":{"draws":1,"losses":19,"wins":6},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":10},"claude-opus-4-5":{"draws":3,"losses":7,"wins":26},"claude-opus-4-8":{"draws":3,"losses":6,"wins":7},"claude-opus-5":{"draws":1,"losses":26,"wins":5},"claude-opus-5-5":{"draws":3,"losses":24,"wins":3},"claude-sonnet-5":{"draws":4,"losses":7,"wins":17},"claude-sonnet-5-5":{"draws":1,"losses":9,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":32},"deepseek/deepseek-v4-pro":{"draws":5,"losses":6,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":8,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":13,"wins":17},"elorian/glimpse":{"draws":2,"losses":11,"wins":7},"fireworks/ember-1":{"draws":1,"losses":6,"wins":15},"gemini-3.1-pro-preview":{"draws":1,"losses":8,"wins":17},"gemini-4-argon":{"draws":3,"losses":28,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":16},"google/gemini-3.5-flash-lite":{"draws":2,"losses":8,"wins":28},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":25},"google/gemini-3.8-flash":{"draws":2,"losses":7,"wins":9},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":14},"gpt-4.1":{"draws":1,"losses":1,"wins":6},"gpt-5":{"draws":0,"losses":5,"wins":11},"gpt-5.4":{"draws":4,"losses":14,"wins":14},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":11},"gpt-5.5":{"draws":3,"losses":5,"wins":16},"gpt-5.6-luna":{"draws":4,"losses":4,"wins":16},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":9},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":14},"gpt-6-astra":{"draws":1,"losses":16,"wins":1},"gpt-6-luna":{"draws":2,"losses":10,"wins":12},"gpt-6-sol":{"draws":1,"losses":21,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":16,"wins":5},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":16},"inception/mercury-3":{"draws":1,"losses":9,"wins":14},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":16},"meituan/longcat-2.0":{"draws":4,"losses":3,"wins":19},"meta/muse-glimmer-30b":{"draws":5,"losses":3,"wins":14},"meta/muse-spark-1.2":{"draws":5,"losses":10,"wins":15},"meta/muse-spark-1.3":{"draws":1,"losses":5,"wins":10},"meta/muse-spark-open":{"draws":4,"losses":10,"wins":10},"meta/muse-wonder":{"draws":4,"losses":12,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":12},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":20},"mistralai/mistral-large-4-0":{"draws":1,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":8},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":2,"wins":13},"o3":{"draws":1,"losses":8,"wins":31},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":16},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":18},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":12},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":13},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":1,"losses":10,"wins":11},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":9,"wins":17},"stealth/ox-alpha":{"draws":8,"losses":18,"wins":40},"stealth/space-bunny-alpha":{"draws":4,"losses":6,"wins":14},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":9},"tencent/hy4-preview":{"draws":1,"losses":6,"wins":19},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":24},"thinkingmachines/inkling-small":{"draws":4,"losses":5,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":8,"wins":11},"x-ai/grok-4.6":{"draws":4,"losses":13,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":12,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":8,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":8},"z-ai/glm-5.2":{"draws":3,"losses":9,"wins":36},"z-ai/glm-5.3":{"draws":0,"losses":21,"wins":9},"z-ai/glm-5.3-flash":{"draws":2,"losses":8,"wins":10},"z-ai/glm-5.3-flashx":{"draws":2,"losses":9,"wins":5}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":35},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":5,"losses":35,"wins":14},"claude-haiku-5-5":{"draws":6,"losses":6,"wins":34},"claude-opus-4-5":{"draws":9,"losses":9,"wins":60},"claude-opus-4-8":{"draws":9,"losses":8,"wins":27},"claude-opus-5":{"draws":11,"losses":34,"wins":37},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":6,"losses":5,"wins":37},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":62},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":5,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":10,"wins":8},"elorian/glimpse":{"draws":4,"losses":1,"wins":11},"fireworks/ember-1":{"draws":12,"losses":5,"wins":31},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":32},"gemini-4-argon":{"draws":0,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":47},"google/gemini-3.5-flash-lite":{"draws":8,"losses":5,"wins":71},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":73},"google/gemini-3.8-flash":{"draws":9,"losses":12,"wins":27},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":4,"wins":33},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":43},"gpt-5.5":{"draws":8,"losses":10,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":13,"wins":30},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":31},"gpt-6-astra":{"draws":6,"losses":33,"wins":9},"gpt-6-luna":{"draws":7,"losses":5,"wins":36},"gpt-6-sol":{"draws":4,"losses":23,"wins":21},"gpt-6.1-sol":{"draws":9,"losses":26,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inception/mercury-3":{"draws":6,"losses":1,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":40},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":1,"losses":10,"wins":35},"meta/muse-spark-1.3":{"draws":6,"losses":6,"wins":36},"meta/muse-spark-open":{"draws":4,"losses":5,"wins":13},"meta/muse-wonder":{"draws":6,"losses":7,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":21},"minimax/minimax-m3.1-flash":{"draws":1,"losses":0,"wins":21},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":34},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":8},"o3":{"draws":3,"losses":7,"wins":56},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":42},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":26},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":32},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":25},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":39},"qwen/qwen3.8-max-0902":{"draws":9,"losses":7,"wins":32},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":2,"wins":24},"stealth/ox-alpha":{"draws":21,"losses":21,"wins":116},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":32},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":32},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":52},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":40},"unbiased/pareto-26.10":{"draws":4,"losses":9,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":33},"x-ai/grok-4.6":{"draws":14,"losses":7,"wins":27},"x-ai/grok-4.7":{"draws":6,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":2,"losses":16,"wins":28},"z-ai/glm-5.3-flash":{"draws":11,"losses":10,"wins":27},"z-ai/glm-5.3-flashx":{"draws":9,"losses":6,"wins":33}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":5,"wins":12},"claude-fable-5":{"draws":2,"losses":12,"wins":4},"claude-fable-5-1":{"draws":1,"losses":25,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":18,"wins":3},"claude-opus-4-5":{"draws":10,"losses":16,"wins":8},"claude-opus-4-8":{"draws":9,"losses":10,"wins":5},"claude-opus-5":{"draws":5,"losses":17,"wins":2},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":5,"losses":10,"wins":7},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":8,"losses":11,"wins":15},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":11,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":11,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":15,"wins":9},"elorian/glimpse":{"draws":7,"losses":8,"wins":5},"fireworks/ember-1":{"draws":6,"losses":11,"wins":3},"gemini-3.1-pro-preview":{"draws":8,"losses":7,"wins":7},"gemini-4-argon":{"draws":6,"losses":29,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":12,"wins":8},"google/gemini-3.5-flash-lite":{"draws":8,"losses":14,"wins":18},"google/gemini-3.6-flash":{"draws":5,"losses":26,"wins":11},"google/gemini-3.8-flash":{"draws":2,"losses":16,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":9},"gpt-4.1":{"draws":4,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":7,"wins":8},"gpt-5.4":{"draws":2,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":3,"losses":14,"wins":9},"gpt-5.5":{"draws":7,"losses":5,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":13,"wins":11},"gpt-5.6-sol":{"draws":2,"losses":15,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":7,"wins":12},"gpt-6-astra":{"draws":1,"losses":19,"wins":0},"gpt-6-luna":{"draws":8,"losses":13,"wins":13},"gpt-6-sol":{"draws":3,"losses":15,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":21,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":3,"wins":10},"inception/mercury-3":{"draws":6,"losses":10,"wins":8},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":12},"meituan/longcat-2.0":{"draws":4,"losses":8,"wins":10},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":9},"meta/muse-spark-1.2":{"draws":7,"losses":7,"wins":12},"meta/muse-spark-1.3":{"draws":5,"losses":16,"wins":7},"meta/muse-spark-open":{"draws":5,"losses":19,"wins":14},"meta/muse-wonder":{"draws":2,"losses":17,"wins":5},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":8},"minimax/minimax-m3.1-flash":{"draws":4,"losses":8,"wins":8},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":9,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":3,"wins":7},"o3":{"draws":0,"losses":14,"wins":8},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":11},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":15,"wins":5},"qwen/qwen3.8-27b":{"draws":1,"losses":5,"wins":6},"qwen/qwen3.8-flash":{"draws":3,"losses":6,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":13,"wins":6},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":11,"wins":15},"stealth/ox-alpha":{"draws":15,"losses":32,"wins":13},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":9,"wins":7},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":5},"tencent/hy4-preview":{"draws":5,"losses":8,"wins":7},"thinkingmachines/inkling":{"draws":8,"losses":10,"wins":11},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":5},"x-ai/grok-4.6":{"draws":5,"losses":10,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":21,"wins":5},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":9,"losses":13,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":13,"losses":13,"wins":20},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.3-flash":{"draws":4,"losses":12,"wins":6},"z-ai/glm-5.3-flashx":{"draws":6,"losses":19,"wins":5}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":23},"claude-fable-5":{"draws":8,"losses":25,"wins":15},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":22,"losses":22,"wins":34},"claude-opus-4-8":{"draws":7,"losses":14,"wins":23},"claude-opus-5":{"draws":13,"losses":57,"wins":12},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"claude-sonnet-5":{"draws":14,"losses":18,"wins":16},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":14,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":9,"wins":10},"elorian/glimpse":{"draws":3,"losses":3,"wins":2},"fireworks/ember-1":{"draws":10,"losses":14,"wins":24},"gemini-3.1-pro-preview":{"draws":7,"losses":15,"wins":26},"gemini-4-argon":{"draws":1,"losses":13,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash-lite":{"draws":17,"losses":14,"wins":53},"google/gemini-3.6-flash":{"draws":14,"losses":30,"wins":48},"google/gemini-3.8-flash":{"draws":14,"losses":15,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":11,"losses":6,"wins":25},"gpt-5.4":{"draws":15,"losses":18,"wins":13},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":31},"gpt-5.5":{"draws":10,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":15},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":17},"gpt-6-astra":{"draws":7,"losses":36,"wins":5},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":8,"losses":35,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inception/mercury-3":{"draws":5,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":6,"wins":33},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":5,"losses":21,"wins":20},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":17},"meta/muse-spark-open":{"draws":3,"losses":11,"wins":6},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"minimax/minimax-m3.1-flash":{"draws":2,"losses":8,"wins":14},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":8},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":12,"losses":11,"wins":23},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":20},"qwen/qwen3.8-27b":{"draws":8,"losses":8,"wins":18},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":11,"wins":22},"qwen/qwen3.8-max-0902":{"draws":15,"losses":20,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":9,"wins":13},"stealth/ox-alpha":{"draws":50,"losses":53,"wins":55},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":2,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":18,"losses":7,"wins":39},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":11,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":23},"x-ai/grok-4.6":{"draws":16,"losses":17,"wins":15},"x-ai/grok-4.7":{"draws":9,"losses":20,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":8,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":18,"wins":49},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":13,"losses":19,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":18}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":11,"wins":10},"claude-fable-5":{"draws":13,"losses":25,"wins":4},"claude-fable-5-1":{"draws":2,"losses":45,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":21,"losses":37,"wins":10},"claude-opus-4-8":{"draws":11,"losses":24,"wins":3},"claude-opus-5":{"draws":11,"losses":53,"wins":6},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":19,"losses":15,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":25,"losses":17,"wins":20},"deepseek/deepseek-v4-pro":{"draws":11,"losses":22,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":18,"wins":1},"elorian/glimpse":{"draws":5,"losses":6,"wins":5},"fireworks/ember-1":{"draws":14,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":18,"losses":16,"wins":8},"gemini-4-argon":{"draws":1,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":17,"losses":26,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":27,"wins":17},"google/gemini-3.6-flash":{"draws":28,"losses":43,"wins":9},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":4},"google/gemma-4-31b-it":{"draws":11,"losses":10,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":16,"wins":8},"gpt-5.4":{"draws":14,"losses":22,"wins":4},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":20,"wins":11},"gpt-5.5":{"draws":14,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":19,"wins":4},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":2},"gpt-5.6-terra":{"draws":14,"losses":21,"wins":5},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":22,"wins":5},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":7,"wins":11},"inception/mercury-3":{"draws":5,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":16,"wins":12},"meta/muse-glimmer-30b":{"draws":18,"losses":13,"wins":5},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":8},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":3},"meta/muse-spark-open":{"draws":4,"losses":16,"wins":6},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":9},"minimax/minimax-m3.1-flash":{"draws":6,"losses":6,"wins":4},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":2},"o3":{"draws":14,"losses":33,"wins":9},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":15,"wins":9},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":11,"wins":2},"stealth/ox-alpha":{"draws":38,"losses":78,"wins":26},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":17,"losses":19,"wins":4},"thinkingmachines/inkling":{"draws":18,"losses":21,"wins":15},"thinkingmachines/inkling-small":{"draws":19,"losses":17,"wins":6},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":1},"x-ai/grok-4.5":{"draws":12,"losses":26,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":17,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":38,"losses":34,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":14,"losses":24,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":17},"claude-fable-5":{"draws":6,"losses":24,"wins":12},"claude-fable-5-1":{"draws":0,"losses":41,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":16,"wins":14},"claude-opus-4-5":{"draws":19,"losses":23,"wins":26},"claude-opus-4-8":{"draws":8,"losses":17,"wins":13},"claude-opus-5":{"draws":11,"losses":53,"wins":16},"claude-opus-5-5":{"draws":2,"losses":41,"wins":3},"claude-sonnet-5":{"draws":10,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":27},"deepseek/deepseek-v4-pro":{"draws":10,"losses":11,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":12,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":21,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":15,"wins":9},"elorian/glimpse":{"draws":2,"losses":4,"wins":8},"fireworks/ember-1":{"draws":13,"losses":14,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":10,"wins":19},"gemini-4-argon":{"draws":1,"losses":16,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":16,"losses":14,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":11,"wins":34},"google/gemini-3.6-flash":{"draws":16,"losses":32,"wins":32},"google/gemini-3.8-flash":{"draws":8,"losses":18,"wins":16},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":10},"gpt-4.1":{"draws":3,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":15,"wins":18},"gpt-5.4":{"draws":9,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":16},"gpt-5.5":{"draws":9,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":15,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":25,"wins":13},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":17},"gpt-6-astra":{"draws":5,"losses":36,"wins":1},"gpt-6-luna":{"draws":12,"losses":9,"wins":21},"gpt-6-sol":{"draws":4,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":10},"inception/mercury-3":{"draws":2,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":9,"losses":7,"wins":12},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":22},"meta/muse-spark-1.2":{"draws":6,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":15},"meta/muse-spark-open":{"draws":6,"losses":4,"wins":12},"meta/muse-wonder":{"draws":6,"losses":27,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":3,"losses":6,"wins":5},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":15},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":16,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":3},"o3":{"draws":9,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":12},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":17,"wins":16},"qwen/qwen3.8-max-0902":{"draws":7,"losses":24,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":3,"wins":5},"stealth/ox-alpha":{"draws":30,"losses":50,"wins":62},"stealth/space-bunny-alpha":{"draws":8,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":19,"wins":17},"x-ai/grok-4.6":{"draws":7,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":22,"losses":12,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":8,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":5},"z-ai/glm-5.2":{"draws":24,"losses":24,"wins":36},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":15},"z-ai/glm-5.3-flash":{"draws":11,"losses":17,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":16,"wins":15}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":3},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":1,"wins":1},"claude-opus-4-5":{"draws":0,"losses":3,"wins":3},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":3,"wins":1},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":5,"wins":1},"elorian/glimpse":{"draws":0,"losses":3,"wins":1},"fireworks/ember-1":{"draws":0,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":2},"gemini-4-argon":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.8-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":4},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":2},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"gpt-6-luna":{"draws":0,"losses":3,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":1,"wins":1},"inception/mercury-3":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meta/muse-glimmer-30b":{"draws":0,"losses":2,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":3,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":2},"meta/muse-spark-open":{"draws":0,"losses":5,"wins":1},"meta/muse-wonder":{"draws":0,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3.1-flash":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":0,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":1},"o3":{"draws":0,"losses":0,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":0,"losses":3,"wins":1},"stealth/space-bunny-alpha":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":1},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.3":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":5,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":12,"wins":13},"claude-fable-5":{"draws":14,"losses":39,"wins":1},"claude-fable-5-1":{"draws":4,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":16,"losses":31,"wins":7},"claude-opus-4-5":{"draws":38,"losses":42,"wins":10},"claude-opus-4-8":{"draws":15,"losses":32,"wins":7},"claude-opus-5":{"draws":15,"losses":81,"wins":2},"claude-opus-5-5":{"draws":2,"losses":59,"wins":1},"claude-sonnet-5":{"draws":25,"losses":22,"wins":7},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":39,"losses":24,"wins":19},"deepseek/deepseek-v4-pro":{"draws":19,"losses":23,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":20,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":18,"wins":2},"elorian/glimpse":{"draws":7,"losses":11,"wins":0},"fireworks/ember-1":{"draws":26,"losses":24,"wins":4},"gemini-3.1-pro-preview":{"draws":25,"losses":17,"wins":12},"gemini-4-argon":{"draws":0,"losses":27,"wins":1},"google/gemini-3.1-flash-lite":{"draws":14,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":25,"losses":28,"wins":15},"google/gemini-3.5-flash-lite":{"draws":39,"losses":28,"wins":27},"google/gemini-3.6-flash":{"draws":42,"losses":50,"wins":8},"google/gemini-3.8-flash":{"draws":19,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":21,"losses":7,"wins":6},"gpt-4.1":{"draws":10,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":24,"wins":5},"gpt-5.4":{"draws":20,"losses":29,"wins":1},"gpt-5.4-mini":{"draws":19,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":21,"losses":25,"wins":16},"gpt-5.5":{"draws":25,"losses":22,"wins":1},"gpt-5.6-luna":{"draws":27,"losses":16,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":2},"gpt-5.6-terra":{"draws":25,"losses":22,"wins":3},"gpt-6-astra":{"draws":4,"losses":50,"wins":0},"gpt-6-luna":{"draws":19,"losses":28,"wins":7},"gpt-6-sol":{"draws":6,"losses":46,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":49,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":25,"losses":8,"wins":9},"inception/mercury-3":{"draws":7,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":23,"losses":5,"wins":8},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":13,"wins":20},"meta/muse-glimmer-30b":{"draws":28,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":15,"losses":32,"wins":5},"meta/muse-spark-1.3":{"draws":17,"losses":36,"wins":1},"meta/muse-spark-open":{"draws":5,"losses":15,"wins":0},"meta/muse-wonder":{"draws":20,"losses":33,"wins":1},"minimax/minimax-m3":{"draws":15,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":12,"losses":4,"wins":4},"mistralai/mistral-large-4-0":{"draws":12,"losses":17,"wins":5},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":9,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":21,"wins":9},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":8,"wins":2},"o3":{"draws":19,"losses":42,"wins":13},"openai/gpt-oss-120b":{"draws":25,"losses":10,"wins":13},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":11},"qwen/qwen3.7-max":{"draws":20,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":14,"losses":12,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":19,"losses":14,"wins":3},"qwen/qwen3.8-max":{"draws":27,"losses":23,"wins":4},"qwen/qwen3.8-max-0902":{"draws":28,"losses":22,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":57,"losses":81,"wins":12},"stealth/space-bunny-alpha":{"draws":20,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":12,"wins":10},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":20,"losses":27,"wins":3},"thinkingmachines/inkling":{"draws":25,"losses":19,"wins":24},"thinkingmachines/inkling-small":{"draws":31,"losses":11,"wins":12},"unbiased/pareto-26.10":{"draws":2,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":18,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":16,"losses":37,"wins":1},"x-ai/grok-4.6":{"draws":25,"losses":24,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":47,"losses":21,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":20,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":56,"losses":40,"wins":12},"z-ai/glm-5.3":{"draws":13,"losses":36,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":36,"wins":57},"claude-fable-5":{"draws":4,"losses":92,"wins":18},"claude-fable-5-1":{"draws":0,"losses":117,"wins":7},"claude-haiku-5-5":{"draws":11,"losses":57,"wins":44},"claude-opus-4-5":{"draws":13,"losses":119,"wins":56},"claude-opus-4-8":{"draws":7,"losses":66,"wins":37},"claude-opus-5":{"draws":6,"losses":156,"wins":10},"claude-opus-5-5":{"draws":2,"losses":122,"wins":2},"claude-sonnet-5":{"draws":7,"losses":52,"wins":55},"claude-sonnet-5-5":{"draws":4,"losses":82,"wins":28},"cohere/north-mini-code":{"draws":4,"losses":11,"wins":39},"deepseek/deepseek-v4-flash":{"draws":14,"losses":54,"wins":112},"deepseek/deepseek-v4-pro":{"draws":3,"losses":55,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":64,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":58,"wins":40},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":46,"wins":22},"elorian/glimpse":{"draws":1,"losses":15,"wins":14},"fireworks/ember-1":{"draws":10,"losses":70,"wins":34},"gemini-3.1-pro-preview":{"draws":11,"losses":45,"wins":58},"gemini-4-argon":{"draws":0,"losses":48,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":82},"google/gemini-3.5-flash":{"draws":9,"losses":89,"wins":52},"google/gemini-3.5-flash-lite":{"draws":13,"losses":65,"wins":128},"google/gemini-3.6-flash":{"draws":13,"losses":132,"wins":77},"google/gemini-3.8-flash":{"draws":5,"losses":78,"wins":31},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":46},"gpt-4.1":{"draws":4,"losses":18,"wins":16},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":2,"losses":61,"wins":43},"gpt-5.4":{"draws":3,"losses":83,"wins":28},"gpt-5.4-mini":{"draws":9,"losses":18,"wins":49},"gpt-5.4-nano":{"draws":5,"losses":67,"wins":66},"gpt-5.5":{"draws":13,"losses":65,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":45,"wins":55},"gpt-5.6-sol":{"draws":5,"losses":88,"wins":21},"gpt-5.6-terra":{"draws":12,"losses":50,"wins":44},"gpt-6-astra":{"draws":4,"losses":109,"wins":1},"gpt-6-luna":{"draws":15,"losses":62,"wins":37},"gpt-6-sol":{"draws":2,"losses":100,"wins":12},"gpt-6.1-sol":{"draws":0,"losses":107,"wins":7},"inception/mercury-2.5-preview":{"draws":9,"losses":11,"wins":56},"inception/mercury-3":{"draws":3,"losses":15,"wins":10},"inclusionai/ling-3.0-flash":{"draws":10,"losses":16,"wins":54},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":40,"wins":85},"meta/muse-glimmer-30b":{"draws":10,"losses":20,"wins":68},"meta/muse-spark-1.2":{"draws":3,"losses":49,"wins":54},"meta/muse-spark-1.3":{"draws":2,"losses":73,"wins":39},"meta/muse-spark-open":{"draws":2,"losses":41,"wins":15},"meta/muse-wonder":{"draws":4,"losses":86,"wins":24},"minimax/minimax-m3":{"draws":3,"losses":18,"wins":45},"minimax/minimax-m3.1-flash":{"draws":1,"losses":24,"wins":27},"mistralai/mistral-large-4-0":{"draws":10,"losses":34,"wins":24},"mistralai/mistral-medium-3-5":{"draws":6,"losses":8,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":13,"wins":15},"moonshotai/kimi-k3":{"draws":8,"losses":51,"wins":47},"nex-agi/nex-n2-pro":{"draws":3,"losses":15,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":28,"wins":70},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":16,"wins":11},"o3":{"draws":10,"losses":77,"wins":83},"openai/gpt-oss-120b":{"draws":6,"losses":21,"wins":73},"poolside/laguna-s-2.1":{"draws":13,"losses":40,"wins":61},"qwen/qwen3.7-max":{"draws":10,"losses":29,"wins":35},"qwen/qwen3.7-plus":{"draws":2,"losses":17,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":67,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":43,"wins":38},"qwen/qwen3.8-flash":{"draws":8,"losses":36,"wins":32},"qwen/qwen3.8-max":{"draws":13,"losses":61,"wins":40},"qwen/qwen3.8-max-0902":{"draws":13,"losses":55,"wins":46},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":30,"wins":26},"stealth/ox-alpha":{"draws":27,"losses":173,"wins":144},"stealth/space-bunny-alpha":{"draws":7,"losses":36,"wins":49},"stepfun/step-3.7-flash":{"draws":8,"losses":32,"wins":58},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":23,"wins":28},"tencent/hy4-preview":{"draws":11,"losses":66,"wins":37},"thinkingmachines/inkling":{"draws":12,"losses":34,"wins":108},"thinkingmachines/inkling-small":{"draws":14,"losses":29,"wins":71},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":35,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":9,"wins":25},"x-ai/grok-4.5":{"draws":5,"losses":72,"wins":37},"x-ai/grok-4.6":{"draws":14,"losses":69,"wins":31},"x-ai/grok-4.7":{"draws":3,"losses":76,"wins":25},"x-ai/grok-build-0.1":{"draws":3,"losses":12,"wins":23},"xiaomi/mimo-v2.5":{"draws":16,"losses":34,"wins":130},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":25,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":44,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":51,"wins":21},"z-ai/glm-5.2":{"draws":21,"losses":96,"wins":111},"z-ai/glm-5.3":{"draws":5,"losses":79,"wins":24},"z-ai/glm-5.3-flash":{"draws":3,"losses":57,"wins":54},"z-ai/glm-5.3-flashx":{"draws":7,"losses":68,"wins":39}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":14,"wins":11},"claude-fable-5":{"draws":10,"losses":25,"wins":7},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":26,"wins":4},"claude-opus-4-5":{"draws":19,"losses":31,"wins":18},"claude-opus-4-8":{"draws":13,"losses":17,"wins":8},"claude-opus-5":{"draws":13,"losses":55,"wins":2},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":11,"losses":25,"wins":6},"claude-sonnet-5-5":{"draws":8,"losses":25,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":17,"wins":23},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":19,"wins":4},"elorian/glimpse":{"draws":3,"losses":3,"wins":4},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":14},"gemini-4-argon":{"draws":1,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":14},"google/gemini-3.5-flash":{"draws":15,"losses":19,"wins":18},"google/gemini-3.5-flash-lite":{"draws":21,"losses":20,"wins":33},"google/gemini-3.6-flash":{"draws":23,"losses":45,"wins":12},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":12},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":18,"wins":9},"gpt-5.4":{"draws":10,"losses":18,"wins":12},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":16},"gpt-5.5":{"draws":14,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":22,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":18,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":18,"wins":11},"gpt-6-sol":{"draws":7,"losses":34,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":12},"inception/mercury-3":{"draws":5,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":18,"wins":17},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":15},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":0,"losses":6,"wins":2},"meta/muse-wonder":{"draws":9,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":12,"losses":8,"wins":2},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":3},"o3":{"draws":6,"losses":33,"wins":17},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":14,"losses":7,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":22,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":10,"losses":27,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":6,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":74,"wins":34},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":21,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":16,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":11,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":8},"x-ai/grok-4.7":{"draws":1,"losses":33,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":28,"losses":36,"wins":20},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":13,"losses":26,"wins":3}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":1,"wins":32},"claude-fable-5":{"draws":13,"losses":12,"wins":23},"claude-fable-5-1":{"draws":5,"losses":44,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":11,"wins":25},"claude-opus-4-5":{"draws":23,"losses":7,"wins":48},"claude-opus-4-8":{"draws":8,"losses":6,"wins":30},"claude-opus-5":{"draws":13,"losses":52,"wins":17},"claude-opus-5-5":{"draws":4,"losses":37,"wins":11},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":9,"losses":16,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":16,"losses":5,"wins":51},"deepseek/deepseek-v4-pro":{"draws":11,"losses":4,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":11,"wins":14},"elorian/glimpse":{"draws":1,"losses":3,"wins":4},"fireworks/ember-1":{"draws":11,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"gemini-4-argon":{"draws":2,"losses":23,"wins":5},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":10,"wins":39},"google/gemini-3.5-flash-lite":{"draws":18,"losses":5,"wins":61},"google/gemini-3.6-flash":{"draws":22,"losses":19,"wins":51},"google/gemini-3.8-flash":{"draws":12,"losses":14,"wins":22},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":10,"losses":6,"wins":26},"gpt-5.4":{"draws":7,"losses":10,"wins":29},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":1,"wins":39},"gpt-5.5":{"draws":11,"losses":11,"wins":22},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":8,"losses":17,"wins":23},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":1,"losses":42,"wins":5},"gpt-6-luna":{"draws":12,"losses":8,"wins":28},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":33,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":7,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":38},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":12,"losses":11,"wins":23},"meta/muse-spark-1.3":{"draws":9,"losses":11,"wins":28},"meta/muse-spark-open":{"draws":5,"losses":4,"wins":9},"meta/muse-wonder":{"draws":8,"losses":16,"wins":24},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":5,"losses":2,"wins":13},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":23},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":7},"o3":{"draws":3,"losses":12,"wins":51},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":35},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":5,"wins":22},"qwen/qwen3.8-27b":{"draws":13,"losses":3,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":19},"qwen/qwen3.8-max":{"draws":14,"losses":9,"wins":25},"qwen/qwen3.8-max-0902":{"draws":14,"losses":10,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":5,"wins":18},"stealth/ox-alpha":{"draws":31,"losses":37,"wins":90},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":12,"losses":11,"wins":23},"thinkingmachines/inkling":{"draws":19,"losses":2,"wins":43},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":11,"wins":24},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":15},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":25,"losses":3,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":28,"losses":13,"wins":55},"z-ai/glm-5.3":{"draws":11,"losses":19,"wins":16},"z-ai/glm-5.3-flash":{"draws":9,"losses":11,"wins":28},"z-ai/glm-5.3-flashx":{"draws":16,"losses":10,"wins":22}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":24},"claude-fable-5":{"draws":3,"losses":22,"wins":11},"claude-fable-5-1":{"draws":2,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":14,"wins":18},"claude-opus-4-5":{"draws":8,"losses":15,"wins":37},"claude-opus-4-8":{"draws":4,"losses":14,"wins":18},"claude-opus-5":{"draws":6,"losses":46,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":6,"losses":11,"wins":19},"claude-sonnet-5-5":{"draws":3,"losses":18,"wins":15},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":13,"wins":39},"deepseek/deepseek-v4-pro":{"draws":2,"losses":11,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":9,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":10,"wins":8},"elorian/glimpse":{"draws":0,"losses":4,"wins":8},"fireworks/ember-1":{"draws":3,"losses":11,"wins":22},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":23},"gemini-4-argon":{"draws":3,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":31},"google/gemini-3.5-flash-lite":{"draws":6,"losses":8,"wins":52},"google/gemini-3.6-flash":{"draws":8,"losses":25,"wins":37},"google/gemini-3.8-flash":{"draws":3,"losses":17,"wins":16},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":16},"gpt-4.1":{"draws":2,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":8,"wins":23},"gpt-5.4":{"draws":5,"losses":20,"wins":11},"gpt-5.4-mini":{"draws":1,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":24},"gpt-5.5":{"draws":4,"losses":15,"wins":15},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":11},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":16},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":4,"losses":13,"wins":19},"gpt-6-sol":{"draws":5,"losses":23,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":22},"inception/mercury-3":{"draws":1,"losses":3,"wins":6},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":34},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":27},"meta/muse-spark-1.2":{"draws":1,"losses":12,"wins":21},"meta/muse-spark-1.3":{"draws":4,"losses":12,"wins":20},"meta/muse-spark-open":{"draws":2,"losses":14,"wins":10},"meta/muse-wonder":{"draws":3,"losses":28,"wins":5},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":2,"losses":10,"wins":4},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":4,"losses":16,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":5,"wins":7},"o3":{"draws":2,"losses":19,"wins":39},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":15},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":8,"losses":13,"wins":15},"qwen/qwen3.8-max-0902":{"draws":6,"losses":13,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":7,"wins":9},"stealth/ox-alpha":{"draws":16,"losses":36,"wins":50},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":0,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":32},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":0,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":6,"losses":16,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":3,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":9},"z-ai/glm-5.2":{"draws":12,"losses":21,"wins":39},"z-ai/glm-5.3":{"draws":8,"losses":21,"wins":5},"z-ai/glm-5.3-flash":{"draws":4,"losses":11,"wins":21},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":17}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":25,"losses":19,"wins":34},"claude-opus-4-8":{"draws":5,"losses":22,"wins":17},"claude-opus-5":{"draws":7,"losses":64,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":7,"losses":23,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":43},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":15,"wins":4},"elorian/glimpse":{"draws":4,"losses":5,"wins":7},"fireworks/ember-1":{"draws":14,"losses":18,"wins":16},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"gemini-4-argon":{"draws":1,"losses":16,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":22,"wins":21},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":18,"losses":38,"wins":36},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":14,"wins":17},"gpt-5.4":{"draws":11,"losses":16,"wins":19},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":27},"gpt-5.5":{"draws":13,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":29},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":20,"losses":10,"wins":16},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":9,"losses":17,"wins":22},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":22},"inception/mercury-3":{"draws":7,"losses":5,"wins":8},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":6,"wins":34},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":15},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":16},"meta/muse-spark-open":{"draws":0,"losses":7,"wins":11},"meta/muse-wonder":{"draws":9,"losses":27,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"minimax/minimax-m3.1-flash":{"draws":7,"losses":6,"wins":15},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":16,"wins":19},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":7,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":3,"wins":11},"o3":{"draws":8,"losses":24,"wins":34},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":14,"losses":9,"wins":23},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":15},"qwen/qwen3.8-27b":{"draws":9,"losses":8,"wins":17},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":17},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":4,"wins":5},"stealth/ox-alpha":{"draws":38,"losses":63,"wins":57},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":2,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":18,"wins":17},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":20},"x-ai/grok-4.6":{"draws":13,"losses":17,"wins":18},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":25,"losses":8,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":29,"losses":30,"wins":37},"z-ai/glm-5.3":{"draws":5,"losses":30,"wins":11},"z-ai/glm-5.3-flash":{"draws":13,"losses":12,"wins":23},"z-ai/glm-5.3-flashx":{"draws":17,"losses":15,"wins":16}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":33},"claude-fable-5":{"draws":10,"losses":16,"wins":22},"claude-fable-5-1":{"draws":3,"losses":37,"wins":14},"claude-haiku-5-5":{"draws":10,"losses":9,"wins":27},"claude-opus-4-5":{"draws":14,"losses":12,"wins":52},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":8,"losses":44,"wins":30},"claude-opus-5-5":{"draws":8,"losses":35,"wins":9},"claude-sonnet-5":{"draws":12,"losses":7,"wins":29},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":53},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":9,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":5,"wins":9},"elorian/glimpse":{"draws":4,"losses":3,"wins":7},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":6,"wins":30},"gemini-4-argon":{"draws":3,"losses":14,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":41},"google/gemini-3.5-flash-lite":{"draws":12,"losses":5,"wins":67},"google/gemini-3.6-flash":{"draws":19,"losses":15,"wins":58},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":30},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":22},"gpt-4.1":{"draws":5,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":10,"losses":4,"wins":28},"gpt-5.4":{"draws":12,"losses":13,"wins":21},"gpt-5.4-mini":{"draws":11,"losses":1,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":14,"losses":9,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":7,"wins":32},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":4,"losses":4,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":8,"wins":29},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":31},"meta/muse-spark-open":{"draws":4,"losses":3,"wins":15},"meta/muse-wonder":{"draws":13,"losses":19,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":3,"wins":20},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":30},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":10},"o3":{"draws":8,"losses":14,"wins":44},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":36},"qwen/qwen3.7-max":{"draws":8,"losses":2,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":7,"wins":28},"qwen/qwen3.8-27b":{"draws":6,"losses":1,"wins":27},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":9,"losses":10,"wins":29},"qwen/qwen3.8-max-0902":{"draws":9,"losses":2,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":4,"wins":14},"stealth/ox-alpha":{"draws":32,"losses":40,"wins":86},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":8,"wins":28},"thinkingmachines/inkling":{"draws":11,"losses":4,"wins":49},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":6,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":26},"x-ai/grok-4.6":{"draws":15,"losses":14,"wins":19},"x-ai/grok-4.7":{"draws":6,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":22,"losses":2,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":15},"z-ai/glm-5.2":{"draws":19,"losses":12,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":18},"z-ai/glm-5.3-flash":{"draws":13,"losses":11,"wins":24},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":5,"wins":18},"claude-fable-5":{"draws":8,"losses":3,"wins":7},"claude-fable-5-1":{"draws":3,"losses":25,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":9,"wins":7},"claude-opus-4-5":{"draws":9,"losses":12,"wins":11},"claude-opus-4-8":{"draws":4,"losses":11,"wins":11},"claude-opus-5":{"draws":4,"losses":33,"wins":5},"claude-opus-5-5":{"draws":0,"losses":28,"wins":0},"claude-sonnet-5":{"draws":5,"losses":9,"wins":6},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":9},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":2,"losses":6,"wins":12},"deepseek/deepseek-v4-pro":{"draws":5,"losses":2,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":18,"wins":15},"elorian/glimpse":{"draws":5,"losses":12,"wins":7},"fireworks/ember-1":{"draws":4,"losses":9,"wins":19},"gemini-3.1-pro-preview":{"draws":3,"losses":8,"wins":7},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":14},"google/gemini-3.5-flash-lite":{"draws":6,"losses":11,"wins":25},"google/gemini-3.6-flash":{"draws":10,"losses":19,"wins":19},"google/gemini-3.8-flash":{"draws":8,"losses":9,"wins":5},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":8},"gpt-4.1":{"draws":2,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":4,"wins":13},"gpt-5.4":{"draws":5,"losses":8,"wins":11},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":8},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":17},"gpt-5.5":{"draws":5,"losses":6,"wins":7},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":13},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":10,"wins":6},"gpt-6-astra":{"draws":3,"losses":23,"wins":0},"gpt-6-luna":{"draws":5,"losses":4,"wins":13},"gpt-6-sol":{"draws":1,"losses":18,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":28,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":12},"inception/mercury-3":{"draws":9,"losses":5,"wins":16},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":14},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":13},"meta/muse-glimmer-30b":{"draws":2,"losses":4,"wins":16},"meta/muse-spark-1.2":{"draws":5,"losses":4,"wins":11},"meta/muse-spark-1.3":{"draws":2,"losses":11,"wins":3},"meta/muse-spark-open":{"draws":11,"losses":16,"wins":17},"meta/muse-wonder":{"draws":5,"losses":21,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":9},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":7,"wins":12},"nex-agi/nex-n2-pro":{"draws":1,"losses":3,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":3,"wins":14},"o3":{"draws":3,"losses":10,"wins":19},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":13},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":10},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":8},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":2,"wins":9},"qwen/qwen3.8-max-0902":{"draws":2,"losses":6,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":10,"wins":9},"stealth/ox-alpha":{"draws":10,"losses":30,"wins":28},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":9},"stepfun/step-3.7-flash":{"draws":3,"losses":9,"wins":10},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":9,"losses":10,"wins":11},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":24},"thinkingmachines/inkling-small":{"draws":2,"losses":5,"wins":13},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":10},"x-ai/grok-4.6":{"draws":8,"losses":14,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":11,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":11,"losses":5,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":9,"wins":19},"z-ai/glm-5.3":{"draws":3,"losses":11,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":14,"wins":5},"z-ai/glm-5.3-flashx":{"draws":4,"losses":9,"wins":7}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":107},"claude-fable-5":{"draws":16,"losses":79,"wins":55},"claude-fable-5-1":{"draws":18,"losses":136,"wins":18},"claude-haiku-5-5":{"draws":17,"losses":43,"wins":80},"claude-opus-4-5":{"draws":27,"losses":50,"wins":163},"claude-opus-4-8":{"draws":19,"losses":34,"wins":77},"claude-opus-5":{"draws":37,"losses":168,"wins":53},"claude-opus-5-5":{"draws":9,"losses":131,"wins":22},"claude-sonnet-5":{"draws":14,"losses":31,"wins":105},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":74},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":50},"deepseek/deepseek-v4-flash":{"draws":16,"losses":21,"wins":185},"deepseek/deepseek-v4-pro":{"draws":13,"losses":33,"wins":94},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":31,"wins":91},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":43,"wins":90},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":31,"wins":41},"elorian/glimpse":{"draws":5,"losses":14,"wins":27},"fireworks/ember-1":{"draws":21,"losses":35,"wins":94},"gemini-3.1-pro-preview":{"draws":15,"losses":38,"wins":97},"gemini-4-argon":{"draws":10,"losses":43,"wins":15},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":80},"google/gemini-3.5-flash":{"draws":21,"losses":38,"wins":127},"google/gemini-3.5-flash-lite":{"draws":19,"losses":32,"wins":213},"google/gemini-3.6-flash":{"draws":31,"losses":78,"wins":181},"google/gemini-3.8-flash":{"draws":15,"losses":57,"wins":78},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":69},"gpt-4.1":{"draws":8,"losses":9,"wins":33},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":14},"gpt-5":{"draws":11,"losses":30,"wins":93},"gpt-5.4":{"draws":22,"losses":47,"wins":77},"gpt-5.4-mini":{"draws":15,"losses":11,"wins":74},"gpt-5.4-nano":{"draws":7,"losses":35,"wins":100},"gpt-5.5":{"draws":18,"losses":41,"wins":81},"gpt-5.6-luna":{"draws":23,"losses":22,"wins":105},"gpt-5.6-sol":{"draws":16,"losses":70,"wins":64},"gpt-5.6-terra":{"draws":21,"losses":38,"wins":85},"gpt-6-astra":{"draws":15,"losses":121,"wins":14},"gpt-6-luna":{"draws":20,"losses":29,"wins":101},"gpt-6-sol":{"draws":18,"losses":91,"wins":41},"gpt-6.1-sol":{"draws":17,"losses":116,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":10,"wins":73},"inception/mercury-3":{"draws":6,"losses":12,"wins":36},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":92},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":15,"losses":19,"wins":130},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":114},"meta/muse-spark-1.2":{"draws":18,"losses":27,"wins":99},"meta/muse-spark-1.3":{"draws":17,"losses":49,"wins":84},"meta/muse-spark-open":{"draws":6,"losses":20,"wins":36},"meta/muse-wonder":{"draws":12,"losses":76,"wins":62},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":64},"minimax/minimax-m3.1-flash":{"draws":5,"losses":19,"wins":52},"mistralai/mistral-large-4-0":{"draws":15,"losses":24,"wins":55},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":69},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":7,"wins":22},"moonshotai/kimi-k3":{"draws":18,"losses":39,"wins":87},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":65},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":19,"wins":86},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":26},"o3":{"draws":9,"losses":41,"wins":154},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":112},"poolside/laguna-s-2.1":{"draws":17,"losses":17,"wins":114},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":67},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":59},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":44,"wins":87},"qwen/qwen3.8-27b":{"draws":8,"losses":22,"wins":76},"qwen/qwen3.8-flash":{"draws":10,"losses":24,"wins":66},"qwen/qwen3.8-max":{"draws":21,"losses":32,"wins":97},"qwen/qwen3.8-max-0902":{"draws":21,"losses":42,"wins":87},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":17,"wins":45},"stealth/ox-alpha":{"draws":53,"losses":129,"wins":306},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":91},"stepfun/step-3.7-flash":{"draws":1,"losses":13,"wins":94},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":13,"losses":11,"wins":54},"tencent/hy4-preview":{"draws":20,"losses":49,"wins":77},"thinkingmachines/inkling":{"draws":22,"losses":23,"wins":161},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":125},"unbiased/pareto-26.10":{"draws":1,"losses":22,"wins":1},"unbiased/pareto-26.10-preview":{"draws":10,"losses":35,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":33},"x-ai/grok-4.5":{"draws":14,"losses":63,"wins":73},"x-ai/grok-4.6":{"draws":29,"losses":54,"wins":67},"x-ai/grok-4.7":{"draws":10,"losses":76,"wins":42},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":44},"xiaomi/mimo-v2.5":{"draws":21,"losses":18,"wins":177},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":65},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":22,"wins":64},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":39,"wins":46},"z-ai/glm-5.2":{"draws":33,"losses":48,"wins":219},"z-ai/glm-5.3":{"draws":17,"losses":63,"wins":64},"z-ai/glm-5.3-flash":{"draws":16,"losses":43,"wins":91},"z-ai/glm-5.3-flashx":{"draws":19,"losses":49,"wins":82}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":15},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":1,"losses":37,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":18,"wins":11},"claude-opus-4-5":{"draws":18,"losses":27,"wins":15},"claude-opus-4-8":{"draws":8,"losses":15,"wins":13},"claude-opus-5":{"draws":11,"losses":41,"wins":6},"claude-opus-5-5":{"draws":1,"losses":38,"wins":1},"claude-sonnet-5":{"draws":6,"losses":13,"wins":17},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":28},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":14,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":13,"wins":1},"elorian/glimpse":{"draws":0,"losses":6,"wins":2},"fireworks/ember-1":{"draws":8,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":7,"losses":11,"wins":18},"gemini-4-argon":{"draws":1,"losses":21,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":15},"google/gemini-3.5-flash-lite":{"draws":16,"losses":16,"wins":34},"google/gemini-3.6-flash":{"draws":14,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":8},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":6,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":12,"wins":15},"gpt-5.4":{"draws":5,"losses":25,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":20},"gpt-5.5":{"draws":11,"losses":15,"wins":8},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":8,"losses":13,"wins":13},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":12},"gpt-6-sol":{"draws":1,"losses":27,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":12},"inception/mercury-3":{"draws":0,"losses":7,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":15},"meta/muse-spark-open":{"draws":2,"losses":13,"wins":5},"meta/muse-wonder":{"draws":5,"losses":24,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":13},"minimax/minimax-m3.1-flash":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":14,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":4},"o3":{"draws":8,"losses":27,"wins":25},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":20},"poolside/laguna-s-2.1":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":14,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":5,"wins":5},"stealth/ox-alpha":{"draws":22,"losses":45,"wins":35},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":13,"wins":15},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":24},"thinkingmachines/inkling-small":{"draws":8,"losses":6,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":7},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":18,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":17,"wins":9},"claude-fable-5":{"draws":0,"losses":28,"wins":2},"claude-fable-5-1":{"draws":0,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":22,"wins":5},"claude-opus-4-5":{"draws":4,"losses":37,"wins":9},"claude-opus-4-8":{"draws":2,"losses":24,"wins":4},"claude-opus-5":{"draws":1,"losses":44,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":0,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":5,"losses":30,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":25,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":24,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":10,"wins":0},"elorian/glimpse":{"draws":0,"losses":11,"wins":1},"fireworks/ember-1":{"draws":4,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":0,"losses":19,"wins":11},"gemini-4-argon":{"draws":0,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":2,"losses":28,"wins":10},"google/gemini-3.5-flash-lite":{"draws":6,"losses":32,"wins":16},"google/gemini-3.6-flash":{"draws":3,"losses":49,"wins":6},"google/gemini-3.8-flash":{"draws":0,"losses":29,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":10},"gpt-4.1":{"draws":0,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":27,"wins":1},"gpt-5.4":{"draws":0,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":2,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":25,"wins":13},"gpt-5.5":{"draws":4,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":17,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":20,"wins":6},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":20,"wins":8},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":13},"inception/mercury-3":{"draws":0,"losses":15,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":11,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":23,"wins":12},"meta/muse-glimmer-30b":{"draws":0,"losses":19,"wins":7},"meta/muse-spark-1.2":{"draws":1,"losses":20,"wins":7},"meta/muse-spark-1.3":{"draws":0,"losses":30,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":10,"wins":2},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":12,"wins":4},"minimax/minimax-m3.1-flash":{"draws":0,"losses":8,"wins":2},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":24,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":18,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":9,"wins":1},"o3":{"draws":3,"losses":41,"wins":12},"openai/gpt-oss-120b":{"draws":2,"losses":12,"wins":12},"poolside/laguna-s-2.1":{"draws":2,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":4,"losses":13,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":12,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":24,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":0,"losses":14,"wins":6},"qwen/qwen3.8-max":{"draws":3,"losses":26,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":19,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":14,"wins":8},"stealth/ox-alpha":{"draws":2,"losses":68,"wins":14},"stealth/space-bunny-alpha":{"draws":2,"losses":14,"wins":8},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":12,"wins":21},"thinkingmachines/inkling-small":{"draws":3,"losses":17,"wins":10},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":28,"wins":2},"x-ai/grok-4.6":{"draws":1,"losses":26,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":8,"losses":26,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":15,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":1},"z-ai/glm-5.2":{"draws":5,"losses":42,"wins":13},"z-ai/glm-5.3":{"draws":2,"losses":26,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":26,"wins":4},"z-ai/glm-5.3-flashx":{"draws":0,"losses":25,"wins":5}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":14},"claude-fable-5":{"draws":13,"losses":24,"wins":5},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":18,"wins":13},"claude-opus-4-5":{"draws":23,"losses":29,"wins":18},"claude-opus-4-8":{"draws":10,"losses":22,"wins":10},"claude-opus-5":{"draws":12,"losses":56,"wins":2},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":21,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":14,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":21,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":18,"wins":3},"elorian/glimpse":{"draws":4,"losses":3,"wins":1},"fireworks/ember-1":{"draws":15,"losses":21,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":14},"gemini-4-argon":{"draws":3,"losses":18,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":20,"losses":20,"wins":34},"google/gemini-3.6-flash":{"draws":22,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":9,"losses":11,"wins":16},"gpt-5.4":{"draws":11,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":21},"gpt-5.5":{"draws":17,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":16,"wins":9},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":12},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":8,"wins":11},"inception/mercury-3":{"draws":5,"losses":4,"wins":5},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":15,"wins":20},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":7,"losses":13,"wins":0},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":10},"minimax/minimax-m3.1-flash":{"draws":2,"losses":7,"wins":13},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":12},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":8,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":9,"wins":1},"o3":{"draws":10,"losses":24,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":36,"losses":57,"wins":25},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":11,"losses":17,"wins":12},"thinkingmachines/inkling":{"draws":15,"losses":9,"wins":30},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":18},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":29,"wins":3},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":21,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":22,"losses":33,"wins":29},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":8},"z-ai/glm-5.3-flashx":{"draws":6,"losses":27,"wins":9}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":2,"wins":26},"claude-fable-5":{"draws":11,"losses":19,"wins":18},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":21,"losses":14,"wins":43},"claude-opus-4-8":{"draws":12,"losses":11,"wins":21},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":14,"losses":4,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":22,"losses":6,"wins":44},"deepseek/deepseek-v4-pro":{"draws":11,"losses":8,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":5,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":8,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":8,"wins":16},"elorian/glimpse":{"draws":2,"losses":4,"wins":6},"fireworks/ember-1":{"draws":14,"losses":7,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"gemini-4-argon":{"draws":1,"losses":11,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":5,"wins":38},"google/gemini-3.5-flash-lite":{"draws":26,"losses":7,"wins":51},"google/gemini-3.6-flash":{"draws":24,"losses":23,"wins":45},"google/gemini-3.8-flash":{"draws":11,"losses":13,"wins":24},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":17,"losses":7,"wins":18},"gpt-5.4":{"draws":12,"losses":14,"wins":20},"gpt-5.4-mini":{"draws":13,"losses":1,"wins":18},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":14,"losses":10,"wins":20},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":20,"wins":22},"gpt-5.6-terra":{"draws":15,"losses":7,"wins":24},"gpt-6-astra":{"draws":5,"losses":40,"wins":3},"gpt-6-luna":{"draws":13,"losses":8,"wins":27},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":1,"wins":16},"inception/mercury-3":{"draws":2,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":16,"losses":0,"wins":26},"meta/muse-spark-1.2":{"draws":4,"losses":14,"wins":28},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":17},"meta/muse-spark-open":{"draws":2,"losses":13,"wins":15},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":3,"losses":10,"wins":9},"mistralai/mistral-large-4-0":{"draws":11,"losses":5,"wins":14},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":26},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":4,"wins":6},"o3":{"draws":14,"losses":14,"wins":38},"openai/gpt-oss-120b":{"draws":17,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":18,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":26},"qwen/qwen3.8-27b":{"draws":10,"losses":5,"wins":19},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":13,"losses":10,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":11,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":5,"wins":12},"stealth/ox-alpha":{"draws":36,"losses":26,"wins":96},"stealth/space-bunny-alpha":{"draws":10,"losses":4,"wins":24},"stepfun/step-3.7-flash":{"draws":10,"losses":4,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":7,"losses":5,"wins":18},"thinkingmachines/inkling":{"draws":19,"losses":9,"wins":36},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":31},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":14,"wins":30},"x-ai/grok-4.6":{"draws":18,"losses":15,"wins":15},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":14},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":28,"losses":0,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":24,"losses":8,"wins":64},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":12},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":32,"wins":20},"claude-fable-5":{"draws":14,"losses":65,"wins":5},"claude-fable-5-1":{"draws":2,"losses":92,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":43,"wins":9},"claude-opus-4-5":{"draws":44,"losses":71,"wins":21},"claude-opus-4-8":{"draws":19,"losses":46,"wins":11},"claude-opus-5":{"draws":21,"losses":119,"wins":10},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":28,"losses":45,"wins":11},"claude-sonnet-5-5":{"draws":19,"losses":47,"wins":18},"cohere/north-mini-code":{"draws":7,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":44,"losses":29,"wins":55},"deepseek/deepseek-v4-pro":{"draws":24,"losses":39,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":33,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":43,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":28,"wins":6},"elorian/glimpse":{"draws":8,"losses":9,"wins":9},"fireworks/ember-1":{"draws":28,"losses":45,"wins":11},"gemini-3.1-pro-preview":{"draws":29,"losses":35,"wins":20},"gemini-4-argon":{"draws":5,"losses":28,"wins":1},"google/gemini-3.1-flash-lite":{"draws":18,"losses":6,"wins":30},"google/gemini-3.5-flash":{"draws":28,"losses":49,"wins":27},"google/gemini-3.5-flash-lite":{"draws":46,"losses":48,"wins":50},"google/gemini-3.6-flash":{"draws":44,"losses":84,"wins":32},"google/gemini-3.8-flash":{"draws":28,"losses":47,"wins":9},"google/gemma-4-31b-it":{"draws":17,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":10,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":36,"wins":21},"gpt-5.4":{"draws":21,"losses":44,"wins":15},"gpt-5.4-mini":{"draws":23,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":26,"losses":26,"wins":34},"gpt-5.5":{"draws":24,"losses":42,"wins":12},"gpt-5.6-luna":{"draws":30,"losses":34,"wins":20},"gpt-5.6-sol":{"draws":13,"losses":62,"wins":9},"gpt-5.6-terra":{"draws":24,"losses":39,"wins":17},"gpt-6-astra":{"draws":6,"losses":76,"wins":2},"gpt-6-luna":{"draws":23,"losses":41,"wins":20},"gpt-6-sol":{"draws":8,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":74,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":27,"losses":10,"wins":19},"inception/mercury-3":{"draws":4,"losses":13,"wins":11},"inclusionai/ling-3.0-flash":{"draws":25,"losses":10,"wins":23},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":23,"losses":28,"wins":39},"meta/muse-glimmer-30b":{"draws":26,"losses":23,"wins":27},"meta/muse-spark-1.2":{"draws":22,"losses":49,"wins":11},"meta/muse-spark-1.3":{"draws":14,"losses":61,"wins":9},"meta/muse-spark-open":{"draws":14,"losses":21,"wins":3},"meta/muse-wonder":{"draws":24,"losses":52,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":15,"wins":21},"minimax/minimax-m3.1-flash":{"draws":4,"losses":21,"wins":19},"mistralai/mistral-large-4-0":{"draws":19,"losses":25,"wins":10},"mistralai/mistral-medium-3-5":{"draws":17,"losses":7,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":40,"wins":17},"nex-agi/nex-n2-pro":{"draws":10,"losses":13,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":21,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":4},"o3":{"draws":25,"losses":59,"wins":32},"openai/gpt-oss-120b":{"draws":23,"losses":19,"wins":34},"poolside/laguna-s-2.1":{"draws":29,"losses":31,"wins":26},"qwen/qwen3.7-max":{"draws":16,"losses":25,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":15,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":8},"qwen/qwen3.8-27b":{"draws":19,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":21,"losses":24,"wins":11},"qwen/qwen3.8-max":{"draws":27,"losses":39,"wins":18},"qwen/qwen3.8-max-0902":{"draws":26,"losses":44,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":18,"wins":8},"stealth/ox-alpha":{"draws":71,"losses":156,"wins":55},"stealth/space-bunny-alpha":{"draws":21,"losses":23,"wins":22},"stepfun/step-3.7-flash":{"draws":19,"losses":17,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":20,"wins":11},"tencent/hy4-preview":{"draws":19,"losses":45,"wins":16},"thinkingmachines/inkling":{"draws":25,"losses":29,"wins":32},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":38},"unbiased/pareto-26.10":{"draws":0,"losses":18,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":7,"wins":8},"x-ai/grok-4.5":{"draws":27,"losses":47,"wins":10},"x-ai/grok-4.6":{"draws":26,"losses":51,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":58,"wins":5},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":46,"losses":40,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":25,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":40,"wins":7},"z-ai/glm-5.2":{"draws":45,"losses":74,"wins":49},"z-ai/glm-5.3":{"draws":18,"losses":53,"wins":9},"z-ai/glm-5.3-flash":{"draws":19,"losses":50,"wins":15},"z-ai/glm-5.3-flashx":{"draws":22,"losses":50,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":17,"wins":11},"claude-fable-5":{"draws":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":30,"wins":5},"claude-opus-4-5":{"draws":30,"losses":30,"wins":18},"claude-opus-4-8":{"draws":13,"losses":25,"wins":6},"claude-opus-5":{"draws":13,"losses":67,"wins":2},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":14,"losses":24,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":25,"losses":25,"wins":22},"deepseek/deepseek-v4-pro":{"draws":17,"losses":19,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":23,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":25,"wins":1},"elorian/glimpse":{"draws":3,"losses":12,"wins":3},"fireworks/ember-1":{"draws":17,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":16},"gemini-4-argon":{"draws":2,"losses":22,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":16},"google/gemini-3.5-flash":{"draws":18,"losses":30,"wins":12},"google/gemini-3.5-flash-lite":{"draws":27,"losses":21,"wins":36},"google/gemini-3.6-flash":{"draws":32,"losses":46,"wins":14},"google/gemini-3.8-flash":{"draws":13,"losses":29,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":19,"wins":7},"gpt-5.4":{"draws":11,"losses":29,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":18,"losses":13,"wins":17},"gpt-5.5":{"draws":20,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":21,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":21,"wins":11},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":15,"losses":19,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":5,"wins":12},"inception/mercury-3":{"draws":6,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":11,"wins":20},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":23,"wins":10},"meta/muse-spark-1.3":{"draws":15,"losses":28,"wins":5},"meta/muse-spark-open":{"draws":6,"losses":17,"wins":7},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":7,"losses":7,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":16,"wins":5},"mistralai/mistral-medium-3-5":{"draws":11,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":2},"o3":{"draws":15,"losses":31,"wins":20},"openai/gpt-oss-120b":{"draws":18,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":18,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":12,"losses":16,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":5,"wins":3},"stealth/ox-alpha":{"draws":41,"losses":93,"wins":24},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":9,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":16,"losses":25,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":16,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":17,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":18,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":23,"wins":4},"z-ai/glm-5.2":{"draws":36,"losses":35,"wins":25},"z-ai/glm-5.3":{"draws":7,"losses":35,"wins":4},"z-ai/glm-5.3-flash":{"draws":14,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":10},"claude-fable-5":{"draws":0,"losses":14,"wins":4},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":0,"losses":20,"wins":10},"claude-opus-4-8":{"draws":0,"losses":15,"wins":3},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":0,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":0,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":0,"losses":15,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":12,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":14,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":15,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":11,"wins":1},"elorian/glimpse":{"draws":0,"losses":2,"wins":0},"fireworks/ember-1":{"draws":0,"losses":11,"wins":7},"gemini-3.1-pro-preview":{"draws":0,"losses":8,"wins":10},"gemini-4-argon":{"draws":0,"losses":10,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":0,"losses":15,"wins":9},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":22},"google/gemini-3.6-flash":{"draws":1,"losses":28,"wins":7},"google/gemini-3.8-flash":{"draws":0,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":9},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":13,"wins":3},"gpt-5.4":{"draws":0,"losses":16,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":11,"wins":11},"gpt-5.5":{"draws":0,"losses":11,"wins":5},"gpt-5.6-luna":{"draws":1,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":12,"wins":4},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":0,"losses":9,"wins":9},"gpt-6-sol":{"draws":0,"losses":17,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":7,"wins":7},"inception/mercury-3":{"draws":0,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":1,"losses":9,"wins":14},"meta/muse-glimmer-30b":{"draws":0,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":0,"losses":13,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":14,"wins":4},"meta/muse-spark-open":{"draws":0,"losses":9,"wins":3},"meta/muse-wonder":{"draws":0,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"minimax/minimax-m3.1-flash":{"draws":0,"losses":7,"wins":3},"mistralai/mistral-large-4-0":{"draws":0,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":6,"wins":2},"o3":{"draws":2,"losses":22,"wins":12},"openai/gpt-oss-120b":{"draws":0,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":14,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":9,"wins":5},"qwen/qwen3.8-flash":{"draws":0,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":11,"wins":7},"qwen/qwen3.8-max-0902":{"draws":0,"losses":15,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":0,"losses":40,"wins":12},"stealth/space-bunny-alpha":{"draws":0,"losses":9,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":15,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":19},"thinkingmachines/inkling-small":{"draws":0,"losses":3,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":4,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":13,"wins":5},"x-ai/grok-4.6":{"draws":0,"losses":14,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":0,"losses":5,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":12,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":0,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":12,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":15,"wins":3}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":1,"wins":33},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":19,"losses":19,"wins":40},"claude-opus-4-8":{"draws":11,"losses":15,"wins":18},"claude-opus-5":{"draws":11,"losses":55,"wins":16},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"claude-sonnet-5":{"draws":9,"losses":11,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":20},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":9,"losses":9,"wins":54},"deepseek/deepseek-v4-pro":{"draws":14,"losses":8,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":12,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":16,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":7,"wins":19},"elorian/glimpse":{"draws":0,"losses":2,"wins":4},"fireworks/ember-1":{"draws":5,"losses":12,"wins":31},"gemini-3.1-pro-preview":{"draws":8,"losses":12,"wins":28},"gemini-4-argon":{"draws":0,"losses":20,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":6,"losses":18,"wins":36},"google/gemini-3.5-flash-lite":{"draws":16,"losses":17,"wins":51},"google/gemini-3.6-flash":{"draws":14,"losses":29,"wins":49},"google/gemini-3.8-flash":{"draws":5,"losses":16,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":9,"wins":24},"gpt-5.4":{"draws":10,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":11,"losses":13,"wins":20},"gpt-5.6-luna":{"draws":7,"losses":13,"wins":28},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":30},"gpt-6-astra":{"draws":1,"losses":41,"wins":6},"gpt-6-luna":{"draws":6,"losses":15,"wins":27},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"inception/mercury-3":{"draws":4,"losses":2,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":11,"wins":27},"meta/muse-spark-1.3":{"draws":6,"losses":19,"wins":23},"meta/muse-spark-open":{"draws":5,"losses":11,"wins":12},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":5,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":2,"wins":11},"o3":{"draws":7,"losses":12,"wins":47},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":9,"losses":5,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":12,"wins":27},"qwen/qwen3.8-max-0902":{"draws":8,"losses":16,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":6,"wins":11},"stealth/ox-alpha":{"draws":30,"losses":51,"wins":77},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":9,"losses":16,"wins":21},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":5,"losses":7,"wins":36},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":9,"wins":11},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":23},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":14},"z-ai/glm-5.3-flash":{"draws":6,"losses":20,"wins":22},"z-ai/glm-5.3-flashx":{"draws":4,"losses":20,"wins":24}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":28},"claude-fable-5":{"draws":11,"losses":16,"wins":21},"claude-fable-5-1":{"draws":4,"losses":36,"wins":14},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":18},"claude-opus-4-5":{"draws":17,"losses":18,"wins":43},"claude-opus-4-8":{"draws":9,"losses":13,"wins":22},"claude-opus-5":{"draws":10,"losses":48,"wins":23},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":9,"losses":8,"wins":31},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":25},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":17,"losses":4,"wins":51},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":13,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":8,"wins":14},"elorian/glimpse":{"draws":3,"losses":4,"wins":5},"fireworks/ember-1":{"draws":12,"losses":13,"wins":23},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":32},"gemini-4-argon":{"draws":7,"losses":10,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":9,"wins":37},"google/gemini-3.5-flash-lite":{"draws":17,"losses":11,"wins":56},"google/gemini-3.6-flash":{"draws":17,"losses":29,"wins":46},"google/gemini-3.8-flash":{"draws":12,"losses":12,"wins":24},"google/gemma-4-31b-it":{"draws":9,"losses":0,"wins":19},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":3,"wins":28},"gpt-5.4":{"draws":13,"losses":12,"wins":21},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":17},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":13,"losses":6,"wins":25},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":32},"gpt-5.6-sol":{"draws":8,"losses":15,"wins":25},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":33},"gpt-6-astra":{"draws":4,"losses":36,"wins":8},"gpt-6-luna":{"draws":10,"losses":11,"wins":27},"gpt-6-sol":{"draws":2,"losses":36,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"inception/mercury-3":{"draws":7,"losses":2,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":2,"wins":40},"meta/muse-glimmer-30b":{"draws":11,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":8,"losses":11,"wins":27},"meta/muse-spark-1.3":{"draws":10,"losses":18,"wins":20},"meta/muse-spark-open":{"draws":2,"losses":7,"wins":13},"meta/muse-wonder":{"draws":11,"losses":20,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":3,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":6,"losses":14,"wins":26},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":4,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":9},"o3":{"draws":15,"losses":16,"wins":35},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":12,"losses":3,"wins":31},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":20,"wins":22},"qwen/qwen3.8-27b":{"draws":7,"losses":7,"wins":20},"qwen/qwen3.8-flash":{"draws":13,"losses":2,"wins":17},"qwen/qwen3.8-max":{"draws":7,"losses":16,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":13,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":4,"wins":17},"stealth/ox-alpha":{"draws":46,"losses":44,"wins":68},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":17,"losses":8,"wins":21},"thinkingmachines/inkling":{"draws":20,"losses":6,"wins":38},"thinkingmachines/inkling-small":{"draws":15,"losses":5,"wins":28},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":14,"wins":21},"x-ai/grok-4.6":{"draws":12,"losses":5,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":22,"losses":4,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":10,"wins":13},"z-ai/glm-5.2":{"draws":22,"losses":15,"wins":59},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":9,"losses":16,"wins":23},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":37},"claude-fable-5":{"draws":1,"losses":12,"wins":29},"claude-fable-5-1":{"draws":1,"losses":29,"wins":16},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":36},"claude-opus-4-5":{"draws":1,"losses":5,"wins":62},"claude-opus-4-8":{"draws":3,"losses":7,"wins":28},"claude-opus-5":{"draws":4,"losses":30,"wins":36},"claude-opus-5-5":{"draws":0,"losses":32,"wins":14},"claude-sonnet-5":{"draws":0,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":3,"wins":16},"elorian/glimpse":{"draws":0,"losses":2,"wins":4},"fireworks/ember-1":{"draws":3,"losses":8,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":4,"wins":36},"gemini-4-argon":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":48},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":71},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":67},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":32},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":3,"wins":32},"gpt-5.4":{"draws":2,"losses":8,"wins":30},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":43},"gpt-5.5":{"draws":3,"losses":9,"wins":26},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":37},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":34},"gpt-6-astra":{"draws":4,"losses":30,"wins":8},"gpt-6-luna":{"draws":0,"losses":6,"wins":36},"gpt-6-sol":{"draws":1,"losses":13,"wins":28},"gpt-6.1-sol":{"draws":1,"losses":24,"wins":17},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":27},"inception/mercury-3":{"draws":2,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":34},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":35},"meta/muse-spark-1.3":{"draws":3,"losses":6,"wins":33},"meta/muse-spark-open":{"draws":0,"losses":5,"wins":19},"meta/muse-wonder":{"draws":5,"losses":10,"wins":27},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":2,"losses":0,"wins":14},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":1,"losses":4,"wins":35},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":10},"o3":{"draws":1,"losses":10,"wins":51},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":41},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":26},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":21},"stealth/ox-alpha":{"draws":6,"losses":16,"wins":118},"stealth/space-bunny-alpha":{"draws":0,"losses":5,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":32},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":49},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":39},"unbiased/pareto-26.10":{"draws":1,"losses":3,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":4,"wins":35},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":28},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":4,"losses":9,"wins":71},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":30},"z-ai/glm-5.3-flash":{"draws":2,"losses":5,"wins":35},"z-ai/glm-5.3-flashx":{"draws":3,"losses":6,"wins":33}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":7,"wins":6},"claude-fable-5":{"draws":11,"losses":19,"wins":0},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":17,"wins":1},"claude-opus-4-5":{"draws":28,"losses":19,"wins":3},"claude-opus-4-8":{"draws":11,"losses":16,"wins":3},"claude-opus-5":{"draws":9,"losses":38,"wins":3},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":15,"losses":10,"wins":5},"claude-sonnet-5-5":{"draws":11,"losses":17,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":23,"losses":13,"wins":10},"deepseek/deepseek-v4-pro":{"draws":15,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":6,"wins":0},"elorian/glimpse":{"draws":1,"losses":5,"wins":0},"fireworks/ember-1":{"draws":17,"losses":10,"wins":3},"gemini-3.1-pro-preview":{"draws":15,"losses":10,"wins":5},"gemini-4-argon":{"draws":0,"losses":12,"wins":0},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":20,"losses":14,"wins":4},"google/gemini-3.5-flash-lite":{"draws":28,"losses":15,"wins":9},"google/gemini-3.6-flash":{"draws":26,"losses":23,"wins":7},"google/gemini-3.8-flash":{"draws":12,"losses":16,"wins":2},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":3},"gpt-4.1":{"draws":6,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":10,"wins":2},"gpt-5.4":{"draws":10,"losses":15,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":4},"gpt-5.5":{"draws":15,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":3},"gpt-5.6-sol":{"draws":8,"losses":20,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":9,"wins":2},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":18,"losses":10,"wins":2},"gpt-6-sol":{"draws":5,"losses":23,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":0,"wins":7},"inception/mercury-3":{"draws":12,"losses":3,"wins":1},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":6},"meta/muse-glimmer-30b":{"draws":19,"losses":3,"wins":2},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":2},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":0},"meta/muse-spark-open":{"draws":7,"losses":9,"wins":2},"meta/muse-wonder":{"draws":9,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":2},"minimax/minimax-m3.1-flash":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":13,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":8,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":4,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":1},"o3":{"draws":13,"losses":17,"wins":8},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":17,"losses":7,"wins":2},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":9,"wins":3},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.8-flash":{"draws":16,"losses":4,"wins":0},"qwen/qwen3.8-max":{"draws":16,"losses":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":18,"losses":8,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":8,"wins":0},"stealth/ox-alpha":{"draws":37,"losses":36,"wins":9},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":3},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":22,"losses":8,"wins":6},"thinkingmachines/inkling-small":{"draws":21,"losses":4,"wins":5},"unbiased/pareto-26.10":{"draws":1,"losses":1,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":14,"losses":14,"wins":2},"x-ai/grok-4.6":{"draws":14,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":13,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":34,"losses":19,"wins":7},"z-ai/glm-5.3":{"draws":11,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":3},"z-ai/glm-5.3-flashx":{"draws":15,"losses":14,"wins":1}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":12,"losses":28,"wins":8},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":19,"losses":34,"wins":25},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":17,"losses":62,"wins":3},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":8,"losses":22,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":27,"losses":19,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":18,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":7},"elorian/glimpse":{"draws":0,"losses":5,"wins":3},"fireworks/ember-1":{"draws":13,"losses":19,"wins":16},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"gemini-4-argon":{"draws":1,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":18,"losses":26,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":18,"wins":37},"google/gemini-3.6-flash":{"draws":23,"losses":45,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4":{"draws":14,"losses":26,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":13,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":24,"losses":18,"wins":4},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":18,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":16},"inception/mercury-3":{"draws":1,"losses":7,"wins":4},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":20},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":24,"wins":13},"meta/muse-spark-1.3":{"draws":6,"losses":32,"wins":10},"meta/muse-spark-open":{"draws":7,"losses":14,"wins":7},"meta/muse-wonder":{"draws":9,"losses":31,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":13},"minimax/minimax-m3.1-flash":{"draws":7,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":5,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":20,"wins":9},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":7,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":4},"o3":{"draws":15,"losses":29,"wins":22},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":15},"qwen/qwen3.8-flash":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":19,"losses":19,"wins":10},"qwen/qwen3.8-max-0902":{"draws":15,"losses":27,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":8,"wins":7},"stealth/ox-alpha":{"draws":48,"losses":76,"wins":34},"stealth/space-bunny-alpha":{"draws":18,"losses":9,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":18,"losses":18,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":27,"wins":13},"x-ai/grok-4.6":{"draws":14,"losses":25,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":34,"losses":14,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.2":{"draws":29,"losses":27,"wins":24},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":34},"claude-fable-5":{"draws":4,"losses":7,"wins":31},"claude-fable-5-1":{"draws":2,"losses":35,"wins":11},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":32},"claude-opus-4-5":{"draws":5,"losses":4,"wins":59},"claude-opus-4-8":{"draws":5,"losses":5,"wins":28},"claude-opus-5":{"draws":6,"losses":25,"wins":39},"claude-opus-5-5":{"draws":2,"losses":32,"wins":12},"claude-sonnet-5":{"draws":5,"losses":2,"wins":35},"claude-sonnet-5-5":{"draws":6,"losses":14,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":57},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":2,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":1,"wins":11},"elorian/glimpse":{"draws":1,"losses":1,"wins":10},"fireworks/ember-1":{"draws":3,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":31},"gemini-4-argon":{"draws":4,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":43},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":69},"google/gemini-3.6-flash":{"draws":9,"losses":8,"wins":63},"google/gemini-3.8-flash":{"draws":7,"losses":5,"wins":30},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":21},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":3,"wins":33},"gpt-5.4":{"draws":5,"losses":2,"wins":33},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":26},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":35},"gpt-5.5":{"draws":3,"losses":3,"wins":32},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":31},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":31},"gpt-6-astra":{"draws":8,"losses":27,"wins":7},"gpt-6-luna":{"draws":5,"losses":1,"wins":36},"gpt-6-sol":{"draws":7,"losses":17,"wins":18},"gpt-6.1-sol":{"draws":8,"losses":23,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":28},"inception/mercury-3":{"draws":5,"losses":1,"wins":14},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":44},"meta/muse-glimmer-30b":{"draws":9,"losses":0,"wins":27},"meta/muse-spark-1.2":{"draws":5,"losses":3,"wins":32},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-open":{"draws":1,"losses":2,"wins":19},"meta/muse-wonder":{"draws":5,"losses":8,"wins":29},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":17},"minimax/minimax-m3.1-flash":{"draws":0,"losses":2,"wins":16},"mistralai/mistral-large-4-0":{"draws":2,"losses":4,"wins":20},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":29},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":11},"o3":{"draws":1,"losses":1,"wins":54},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":33},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":36},"qwen/qwen3.8-max-0902":{"draws":8,"losses":5,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":0,"wins":15},"stealth/ox-alpha":{"draws":15,"losses":12,"wins":115},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":29},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":20},"tencent/hy4-preview":{"draws":3,"losses":3,"wins":34},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":45},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":38},"unbiased/pareto-26.10":{"draws":2,"losses":4,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":4,"wins":32},"x-ai/grok-4.6":{"draws":5,"losses":6,"wins":31},"x-ai/grok-4.7":{"draws":5,"losses":13,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":5,"wins":17},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":70},"z-ai/glm-5.3":{"draws":6,"losses":1,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":5,"wins":31},"z-ai/glm-5.3-flashx":{"draws":5,"losses":2,"wins":35}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":14,"wins":27},"claude-fable-5":{"draws":5,"losses":23,"wins":20},"claude-fable-5-1":{"draws":2,"losses":44,"wins":8},"claude-haiku-5-5":{"draws":7,"losses":17,"wins":22},"claude-opus-4-5":{"draws":11,"losses":19,"wins":48},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":11,"losses":53,"wins":18},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":3,"losses":15,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":6,"losses":20,"wins":46},"deepseek/deepseek-v4-pro":{"draws":2,"losses":15,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":12,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":21,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":23,"wins":11},"elorian/glimpse":{"draws":0,"losses":4,"wins":6},"fireworks/ember-1":{"draws":7,"losses":17,"wins":24},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":22},"gemini-4-argon":{"draws":1,"losses":17,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":3,"losses":20,"wins":37},"google/gemini-3.5-flash-lite":{"draws":10,"losses":19,"wins":55},"google/gemini-3.6-flash":{"draws":6,"losses":35,"wins":51},"google/gemini-3.8-flash":{"draws":3,"losses":22,"wins":23},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":0,"losses":5,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":3},"gpt-5":{"draws":3,"losses":9,"wins":30},"gpt-5.4":{"draws":2,"losses":21,"wins":23},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":2,"losses":16,"wins":30},"gpt-5.5":{"draws":3,"losses":18,"wins":23},"gpt-5.6-luna":{"draws":7,"losses":9,"wins":32},"gpt-5.6-sol":{"draws":6,"losses":24,"wins":18},"gpt-5.6-terra":{"draws":5,"losses":16,"wins":25},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":9,"losses":12,"wins":27},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":8,"wins":22},"inception/mercury-3":{"draws":4,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":19},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":12,"wins":35},"meta/muse-glimmer-30b":{"draws":3,"losses":6,"wins":33},"meta/muse-spark-1.2":{"draws":3,"losses":20,"wins":23},"meta/muse-spark-1.3":{"draws":6,"losses":15,"wins":27},"meta/muse-spark-open":{"draws":4,"losses":14,"wins":12},"meta/muse-wonder":{"draws":7,"losses":24,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":17},"minimax/minimax-m3.1-flash":{"draws":2,"losses":7,"wins":17},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":14,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":3,"wins":8},"o3":{"draws":5,"losses":31,"wins":30},"openai/gpt-oss-120b":{"draws":3,"losses":8,"wins":31},"poolside/laguna-s-2.1":{"draws":3,"losses":12,"wins":31},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":18},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":16,"wins":28},"qwen/qwen3.8-27b":{"draws":3,"losses":12,"wins":19},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":19},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":20},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":4,"wins":16},"stealth/ox-alpha":{"draws":17,"losses":57,"wins":84},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":4,"losses":15,"wins":27},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":46},"thinkingmachines/inkling-small":{"draws":6,"losses":8,"wins":34},"unbiased/pareto-26.10":{"draws":1,"losses":3,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":19,"wins":24},"x-ai/grok-4.6":{"draws":6,"losses":23,"wins":19},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":6,"losses":20,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":12,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":11,"losses":27,"wins":58},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":15,"wins":25}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":31},"claude-fable-5":{"draws":6,"losses":16,"wins":26},"claude-fable-5-1":{"draws":8,"losses":39,"wins":7},"claude-haiku-5-5":{"draws":7,"losses":12,"wins":27},"claude-opus-4-5":{"draws":9,"losses":13,"wins":56},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":9,"losses":51,"wins":22},"claude-opus-5-5":{"draws":8,"losses":37,"wins":7},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":7,"losses":19,"wins":22},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":12,"wins":13},"elorian/glimpse":{"draws":2,"losses":1,"wins":5},"fireworks/ember-1":{"draws":6,"losses":10,"wins":32},"gemini-3.1-pro-preview":{"draws":9,"losses":10,"wins":29},"gemini-4-argon":{"draws":1,"losses":12,"wins":7},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":18,"losses":8,"wins":58},"google/gemini-3.6-flash":{"draws":20,"losses":21,"wins":51},"google/gemini-3.8-flash":{"draws":2,"losses":16,"wins":30},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":11,"losses":5,"wins":26},"gpt-5.4":{"draws":7,"losses":10,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"gpt-5.5":{"draws":10,"losses":12,"wins":22},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":18,"wins":25},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":28},"gpt-6-astra":{"draws":3,"losses":39,"wins":6},"gpt-6-luna":{"draws":7,"losses":10,"wins":31},"gpt-6-sol":{"draws":7,"losses":24,"wins":17},"gpt-6.1-sol":{"draws":10,"losses":32,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":27},"inception/mercury-3":{"draws":4,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":27},"meta/muse-spark-open":{"draws":3,"losses":6,"wins":17},"meta/muse-wonder":{"draws":11,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"minimax/minimax-m3.1-flash":{"draws":4,"losses":5,"wins":23},"mistralai/mistral-large-4-0":{"draws":10,"losses":4,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":6},"o3":{"draws":5,"losses":13,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":11,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":3,"wins":11},"stealth/ox-alpha":{"draws":19,"losses":33,"wins":106},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":26},"thinkingmachines/inkling":{"draws":7,"losses":9,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":6,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":14,"wins":30},"x-ai/grok-4.6":{"draws":7,"losses":15,"wins":26},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":5,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":14},"z-ai/glm-5.2":{"draws":20,"losses":14,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":23},"z-ai/glm-5.3-flashx":{"draws":10,"losses":5,"wins":17}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":12},"claude-fable-5":{"draws":6,"losses":26,"wins":10},"claude-fable-5-1":{"draws":2,"losses":42,"wins":2},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":17},"claude-opus-4-5":{"draws":21,"losses":22,"wins":25},"claude-opus-4-8":{"draws":9,"losses":15,"wins":14},"claude-opus-5":{"draws":11,"losses":52,"wins":11},"claude-opus-5-5":{"draws":2,"losses":39,"wins":5},"claude-sonnet-5":{"draws":14,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":19,"losses":18,"wins":25},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":13,"wins":4},"elorian/glimpse":{"draws":3,"losses":7,"wins":4},"fireworks/ember-1":{"draws":10,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"gemini-4-argon":{"draws":1,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":21,"wins":20},"google/gemini-3.5-flash-lite":{"draws":20,"losses":21,"wins":33},"google/gemini-3.6-flash":{"draws":17,"losses":41,"wins":22},"google/gemini-3.8-flash":{"draws":9,"losses":23,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":8},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":8,"losses":10,"wins":18},"gpt-5.4":{"draws":9,"losses":19,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":22},"gpt-5.5":{"draws":12,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":18,"wins":10},"gpt-6-astra":{"draws":2,"losses":35,"wins":5},"gpt-6-luna":{"draws":11,"losses":15,"wins":16},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":33,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":10,"wins":9},"inception/mercury-3":{"draws":7,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":13,"wins":22},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":23,"wins":11},"meta/muse-spark-open":{"draws":4,"losses":18,"wins":6},"meta/muse-wonder":{"draws":13,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":12},"minimax/minimax-m3.1-flash":{"draws":7,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":9,"losses":7,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":6},"o3":{"draws":9,"losses":23,"wins":22},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":17},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":14,"wins":14},"qwen/qwen3.8-max-0902":{"draws":8,"losses":25,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":8,"wins":0},"stealth/ox-alpha":{"draws":33,"losses":70,"wins":37},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":18,"losses":12,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":10,"wins":20},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":11,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":22,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":14,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":23,"losses":29,"wins":32},"z-ai/glm-5.3":{"draws":6,"losses":22,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":25,"wins":10}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":8,"wins":29},"claude-fable-5":{"draws":6,"losses":12,"wins":14},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":16,"losses":11,"wins":51},"claude-opus-4-8":{"draws":11,"losses":8,"wins":25},"claude-opus-5":{"draws":14,"losses":46,"wins":22},"claude-opus-5-5":{"draws":4,"losses":39,"wins":9},"claude-sonnet-5":{"draws":6,"losses":10,"wins":32},"claude-sonnet-5-5":{"draws":10,"losses":16,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":14,"losses":4,"wins":54},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":11,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":13,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":14,"wins":12},"elorian/glimpse":{"draws":2,"losses":3,"wins":7},"fireworks/ember-1":{"draws":9,"losses":7,"wins":32},"gemini-3.1-pro-preview":{"draws":11,"losses":8,"wins":29},"gemini-4-argon":{"draws":5,"losses":16,"wins":3},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":34},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":56},"google/gemini-3.6-flash":{"draws":17,"losses":33,"wins":42},"google/gemini-3.8-flash":{"draws":5,"losses":15,"wins":28},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":18},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":8,"wins":27},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":37},"gpt-5.5":{"draws":11,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":21,"wins":25},"gpt-5.6-terra":{"draws":15,"losses":5,"wins":26},"gpt-6-astra":{"draws":1,"losses":38,"wins":9},"gpt-6-luna":{"draws":12,"losses":7,"wins":29},"gpt-6-sol":{"draws":8,"losses":25,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"inception/mercury-3":{"draws":6,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":6,"wins":40},"meta/muse-glimmer-30b":{"draws":6,"losses":5,"wins":31},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":12,"losses":15,"wins":21},"meta/muse-spark-open":{"draws":3,"losses":7,"wins":14},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":7,"losses":3,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":10,"wins":29},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":3,"wins":7},"o3":{"draws":6,"losses":8,"wins":52},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":10,"wins":23},"qwen/qwen3.8-27b":{"draws":7,"losses":5,"wins":22},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":4,"wins":9},"stealth/ox-alpha":{"draws":27,"losses":46,"wins":85},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":11,"losses":7,"wins":28},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":8,"losses":8,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":23},"x-ai/grok-4.6":{"draws":13,"losses":18,"wins":17},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":14},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":2,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":17},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":5,"losses":23,"wins":18},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":26},"z-ai/glm-5.3-flashx":{"draws":10,"losses":15,"wins":23}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":43},"claude-fable-5":{"draws":5,"losses":9,"wins":34},"claude-fable-5-1":{"draws":3,"losses":24,"wins":11},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":6,"losses":5,"wins":67},"claude-opus-4-8":{"draws":4,"losses":5,"wins":35},"claude-opus-5":{"draws":8,"losses":37,"wins":37},"claude-opus-5-5":{"draws":6,"losses":34,"wins":12},"claude-sonnet-5":{"draws":4,"losses":2,"wins":42},"claude-sonnet-5-5":{"draws":3,"losses":10,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":67},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":0,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":6,"wins":19},"elorian/glimpse":{"draws":0,"losses":0,"wins":6},"fireworks/ember-1":{"draws":1,"losses":5,"wins":42},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":42},"gemini-4-argon":{"draws":3,"losses":14,"wins":11},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":52},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":10,"wins":73},"google/gemini-3.8-flash":{"draws":2,"losses":6,"wins":40},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":1,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":0,"wins":38},"gpt-5.4":{"draws":6,"losses":5,"wins":35},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":3,"losses":9,"wins":32},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":42},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":35},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":38},"gpt-6-astra":{"draws":5,"losses":34,"wins":9},"gpt-6-luna":{"draws":5,"losses":4,"wins":39},"gpt-6-sol":{"draws":6,"losses":12,"wins":30},"gpt-6.1-sol":{"draws":5,"losses":29,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":1,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":46},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":36},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":39},"meta/muse-spark-1.3":{"draws":3,"losses":7,"wins":38},"meta/muse-spark-open":{"draws":4,"losses":7,"wins":17},"meta/muse-wonder":{"draws":3,"losses":14,"wins":31},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":6,"losses":2,"wins":20},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":26},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":39},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":5},"o3":{"draws":3,"losses":5,"wins":58},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":41},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":43},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":39},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":26},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":43},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":18},"stealth/ox-alpha":{"draws":7,"losses":14,"wins":137},"stealth/space-bunny-alpha":{"draws":1,"losses":2,"wins":35},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":38},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":59},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":1,"losses":4,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":4,"losses":9,"wins":35},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":25},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":9,"losses":4,"wins":83},"z-ai/glm-5.3":{"draws":4,"losses":9,"wins":33},"z-ai/glm-5.3-flash":{"draws":1,"losses":9,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":36}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":26},"claude-fable-5":{"draws":10,"losses":25,"wins":13},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":9},"claude-opus-4-5":{"draws":22,"losses":19,"wins":37},"claude-opus-4-8":{"draws":6,"losses":20,"wins":18},"claude-opus-5":{"draws":15,"losses":56,"wins":11},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":21},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":6,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":11,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":14,"wins":7},"elorian/glimpse":{"draws":2,"losses":6,"wins":6},"fireworks/ember-1":{"draws":14,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"gemini-4-argon":{"draws":2,"losses":12,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":23},"google/gemini-3.5-flash-lite":{"draws":17,"losses":13,"wins":54},"google/gemini-3.6-flash":{"draws":25,"losses":32,"wins":35},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":15},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":19},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":24},"gpt-5.5":{"draws":19,"losses":10,"wins":15},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":17,"losses":11,"wins":20},"gpt-6-sol":{"draws":9,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":38,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":8,"losses":1,"wins":5},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":37},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":13,"wins":23},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":18},"meta/muse-spark-open":{"draws":2,"losses":7,"wins":5},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":16},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":5},"o3":{"draws":14,"losses":15,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":11,"losses":12,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-27b":{"draws":7,"losses":8,"wins":19},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":17},"qwen/qwen3.8-max":{"draws":13,"losses":10,"wins":25},"qwen/qwen3.8-max-0902":{"draws":15,"losses":15,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":6,"wins":18},"stealth/ox-alpha":{"draws":36,"losses":60,"wins":62},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":26},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":17},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":43},"thinkingmachines/inkling-small":{"draws":9,"losses":5,"wins":34},"unbiased/pareto-26.10":{"draws":0,"losses":7,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":24,"losses":21,"wins":51},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":16,"wins":20}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":7,"losses":33,"wins":8},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":19,"losses":15,"wins":28},"claude-opus-4-8":{"draws":12,"losses":17,"wins":15},"claude-opus-5":{"draws":13,"losses":61,"wins":8},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":13,"losses":11,"wins":24},"claude-sonnet-5-5":{"draws":10,"losses":21,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":13,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":14,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":13,"wins":7},"elorian/glimpse":{"draws":3,"losses":8,"wins":3},"fireworks/ember-1":{"draws":16,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"gemini-4-argon":{"draws":0,"losses":19,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":17,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":13,"wins":45},"google/gemini-3.6-flash":{"draws":24,"losses":39,"wins":29},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":12},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":13,"wins":17},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":8,"wins":27},"gpt-5.5":{"draws":18,"losses":17,"wins":9},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":33,"wins":8},"gpt-5.6-terra":{"draws":16,"losses":13,"wins":17},"gpt-6-astra":{"draws":6,"losses":39,"wins":3},"gpt-6-luna":{"draws":16,"losses":11,"wins":21},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":5,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":11,"losses":8,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":26,"wins":15},"meta/muse-spark-open":{"draws":8,"losses":10,"wins":2},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":10,"losses":7,"wins":15},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":5},"o3":{"draws":9,"losses":19,"wins":38},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":26},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":25},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":18,"wins":13},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":8,"wins":12},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":9,"wins":3},"stealth/ox-alpha":{"draws":47,"losses":61,"wins":50},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":15},"thinkingmachines/inkling":{"draws":16,"losses":12,"wins":36},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"draws":3,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":21,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":24,"wins":11},"x-ai/grok-4.7":{"draws":1,"losses":31,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":10,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":40},"z-ai/glm-5.3":{"draws":12,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":14},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":7,"wins":20},"claude-fable-5":{"draws":14,"losses":26,"wins":8},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":27,"losses":24,"wins":27},"claude-opus-4-8":{"draws":5,"losses":15,"wins":8},"claude-opus-5":{"draws":9,"losses":67,"wins":6},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":16,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":13,"wins":32},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":19,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":19,"wins":3},"elorian/glimpse":{"draws":4,"losses":5,"wins":7},"fireworks/ember-1":{"draws":19,"losses":16,"wins":13},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"gemini-4-argon":{"draws":2,"losses":16,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":20,"losses":18,"wins":22},"google/gemini-3.5-flash-lite":{"draws":32,"losses":8,"wins":44},"google/gemini-3.6-flash":{"draws":25,"losses":41,"wins":26},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":11},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":11,"wins":14},"gpt-5.4":{"draws":16,"losses":18,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":10,"wins":11},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":19,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":21,"losses":11,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":17,"losses":15,"wins":14},"gpt-6-astra":{"draws":1,"losses":44,"wins":3},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":45,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":4,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":17,"losses":0,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":11,"wins":24},"meta/muse-glimmer-30b":{"draws":18,"losses":6,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":22,"wins":13},"meta/muse-spark-1.3":{"draws":11,"losses":22,"wins":15},"meta/muse-spark-open":{"draws":11,"losses":3,"wins":6},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":9,"losses":4,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"nex-agi/nex-n2-pro":{"draws":10,"losses":0,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":8},"o3":{"draws":14,"losses":20,"wins":32},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":20,"losses":7,"wins":19},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":17,"losses":6,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":10,"wins":8},"stealth/ox-alpha":{"draws":41,"losses":71,"wins":46},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":19,"wins":10},"thinkingmachines/inkling":{"draws":24,"losses":12,"wins":28},"thinkingmachines/inkling-small":{"draws":21,"losses":3,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":19,"wins":15},"x-ai/grok-4.6":{"draws":15,"losses":22,"wins":11},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":29,"losses":8,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":3,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":41,"losses":20,"wins":35},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":22,"wins":15}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":59},"claude-fable-5":{"draws":11,"losses":22,"wins":51},"claude-fable-5-1":{"draws":6,"losses":68,"wins":22},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":51},"claude-opus-4-5":{"draws":27,"losses":7,"wins":102},"claude-opus-4-8":{"draws":13,"losses":11,"wins":52},"claude-opus-5":{"draws":18,"losses":60,"wins":54},"claude-opus-5-5":{"draws":8,"losses":59,"wins":25},"claude-sonnet-5":{"draws":13,"losses":9,"wins":62},"claude-sonnet-5-5":{"draws":7,"losses":33,"wins":44},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":28},"deepseek/deepseek-v4-flash":{"draws":15,"losses":1,"wins":108},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":12,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":16,"wins":56},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":15,"wins":34},"elorian/glimpse":{"draws":3,"losses":5,"wins":14},"fireworks/ember-1":{"draws":9,"losses":16,"wins":59},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":61},"gemini-4-argon":{"draws":9,"losses":21,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":42},"google/gemini-3.5-flash":{"draws":15,"losses":5,"wins":84},"google/gemini-3.5-flash-lite":{"draws":25,"losses":8,"wins":111},"google/gemini-3.6-flash":{"draws":18,"losses":25,"wins":117},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":56},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":35},"gpt-4.1":{"draws":2,"losses":2,"wins":24},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":5,"wins":63},"gpt-5.4":{"draws":10,"losses":15,"wins":55},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":41},"gpt-5.4-nano":{"draws":8,"losses":5,"wins":67},"gpt-5.5":{"draws":10,"losses":21,"wins":49},"gpt-5.6-luna":{"draws":9,"losses":12,"wins":63},"gpt-5.6-sol":{"draws":16,"losses":19,"wins":49},"gpt-5.6-terra":{"draws":12,"losses":9,"wins":59},"gpt-6-astra":{"draws":4,"losses":61,"wins":19},"gpt-6-luna":{"draws":16,"losses":8,"wins":60},"gpt-6-sol":{"draws":12,"losses":31,"wins":41},"gpt-6.1-sol":{"draws":6,"losses":50,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":40},"inception/mercury-3":{"draws":4,"losses":0,"wins":16},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":47},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":68},"meta/muse-glimmer-30b":{"draws":4,"losses":10,"wins":66},"meta/muse-spark-1.2":{"draws":12,"losses":13,"wins":59},"meta/muse-spark-1.3":{"draws":10,"losses":18,"wins":56},"meta/muse-spark-open":{"draws":8,"losses":7,"wins":35},"meta/muse-wonder":{"draws":9,"losses":32,"wins":43},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":40},"minimax/minimax-m3.1-flash":{"draws":4,"losses":3,"wins":33},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":40},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":22},"moonshotai/kimi-k3":{"draws":12,"losses":10,"wins":62},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":4,"wins":12},"o3":{"draws":9,"losses":9,"wins":90},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":66},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":74},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":37},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":12,"wins":55},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":40},"qwen/qwen3.8-flash":{"draws":8,"losses":3,"wins":45},"qwen/qwen3.8-max":{"draws":13,"losses":5,"wins":66},"qwen/qwen3.8-max-0902":{"draws":14,"losses":14,"wins":56},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":3,"wins":24},"stealth/ox-alpha":{"draws":41,"losses":32,"wins":211},"stealth/space-bunny-alpha":{"draws":14,"losses":4,"wins":50},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":51},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":35},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":62},"thinkingmachines/inkling":{"draws":20,"losses":3,"wins":93},"thinkingmachines/inkling-small":{"draws":16,"losses":3,"wins":65},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":4},"unbiased/pareto-26.10-preview":{"draws":2,"losses":18,"wins":8},"upstage/solar-mini4":{"draws":4,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":12,"losses":14,"wins":58},"x-ai/grok-4.6":{"draws":14,"losses":19,"wins":50},"x-ai/grok-4.7":{"draws":7,"losses":42,"wins":27},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":29,"losses":9,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":8,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":16,"wins":31},"z-ai/glm-5.2":{"draws":24,"losses":11,"wins":133},"z-ai/glm-5.3":{"draws":12,"losses":23,"wins":45},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":56},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":59}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":50},"claude-fable-5":{"draws":3,"losses":2,"wins":49},"claude-fable-5-1":{"draws":6,"losses":19,"wins":35},"claude-haiku-5-5":{"draws":2,"losses":0,"wins":50},"claude-opus-4-5":{"draws":4,"losses":1,"wins":83},"claude-opus-4-8":{"draws":2,"losses":2,"wins":46},"claude-opus-5":{"draws":3,"losses":19,"wins":72},"claude-opus-5-5":{"draws":5,"losses":18,"wins":21},"claude-sonnet-5":{"draws":0,"losses":1,"wins":53},"claude-sonnet-5-5":{"draws":5,"losses":8,"wins":41},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":80},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":51},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":0,"wins":22},"elorian/glimpse":{"draws":1,"losses":0,"wins":15},"fireworks/ember-1":{"draws":0,"losses":0,"wins":54},"gemini-3.1-pro-preview":{"draws":1,"losses":4,"wins":49},"gemini-4-argon":{"draws":1,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":35},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":67},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":94},"google/gemini-3.6-flash":{"draws":3,"losses":8,"wins":91},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":50},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":32},"gpt-4.1":{"draws":0,"losses":0,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":47},"gpt-5.4":{"draws":1,"losses":5,"wins":46},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":35},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":55},"gpt-5.5":{"draws":3,"losses":0,"wins":47},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":50},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":47},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":50},"gpt-6-astra":{"draws":4,"losses":25,"wins":25},"gpt-6-luna":{"draws":0,"losses":1,"wins":53},"gpt-6-sol":{"draws":5,"losses":12,"wins":37},"gpt-6.1-sol":{"draws":3,"losses":20,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":38},"inception/mercury-3":{"draws":0,"losses":0,"wins":16},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":40},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":58},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":48},"meta/muse-spark-1.2":{"draws":1,"losses":1,"wins":50},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":54},"meta/muse-spark-open":{"draws":0,"losses":0,"wins":24},"meta/muse-wonder":{"draws":2,"losses":7,"wins":45},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":30},"minimax/minimax-m3.1-flash":{"draws":2,"losses":0,"wins":26},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":51},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":49},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":15},"o3":{"draws":2,"losses":1,"wins":73},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":47},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":54},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":30},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":0,"wins":53},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":33},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":52},"qwen/qwen3.8-max-0902":{"draws":1,"losses":5,"wins":48},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":0,"wins":27},"stealth/ox-alpha":{"draws":5,"losses":2,"wins":167},"stealth/space-bunny-alpha":{"draws":0,"losses":1,"wins":41},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":38},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":28},"tencent/hy4-preview":{"draws":1,"losses":4,"wins":47},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":68},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":52},"unbiased/pareto-26.10":{"draws":1,"losses":2,"wins":7},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":49},"x-ai/grok-4.6":{"draws":1,"losses":1,"wins":52},"x-ai/grok-4.7":{"draws":2,"losses":7,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":34},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":107},"z-ai/glm-5.3":{"draws":2,"losses":5,"wins":45},"z-ai/glm-5.3-flash":{"draws":5,"losses":3,"wins":46},"z-ai/glm-5.3-flashx":{"draws":4,"losses":1,"wins":49}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":5,"wins":23},"claude-fable-5":{"draws":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":26,"losses":29,"wins":23},"claude-opus-4-8":{"draws":13,"losses":21,"wins":10},"claude-opus-5":{"draws":11,"losses":58,"wins":13},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":10,"losses":15,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":24,"losses":13,"wins":35},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":22,"wins":3},"elorian/glimpse":{"draws":5,"losses":3,"wins":2},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"gemini-4-argon":{"draws":3,"losses":21,"wins":2},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":19,"losses":24,"wins":17},"google/gemini-3.5-flash-lite":{"draws":28,"losses":22,"wins":34},"google/gemini-3.6-flash":{"draws":27,"losses":48,"wins":17},"google/gemini-3.8-flash":{"draws":14,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":10,"wins":20},"gpt-5.4":{"draws":13,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":16,"wins":20},"gpt-5.5":{"draws":21,"losses":19,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":13,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":23,"losses":14,"wins":9},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":14,"losses":17,"wins":17},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inception/mercury-3":{"draws":8,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":10,"wins":23},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":14,"losses":24,"wins":10},"meta/muse-spark-open":{"draws":4,"losses":14,"wins":4},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":13},"minimax/minimax-m3.1-flash":{"draws":6,"losses":5,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":11,"losses":2,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":6,"wins":2},"o3":{"draws":10,"losses":32,"wins":24},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":20,"losses":9,"wins":17},"qwen/qwen3.7-max":{"draws":12,"losses":5,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":18,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":22,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":5,"wins":8},"stealth/ox-alpha":{"draws":36,"losses":93,"wins":29},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":18,"losses":22,"wins":6},"thinkingmachines/inkling":{"draws":22,"losses":11,"wins":31},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":12},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":36,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":32,"losses":13,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":29,"wins":34},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":15,"losses":26,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":24},"claude-fable-5":{"draws":12,"losses":28,"wins":8},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":22,"losses":22,"wins":34},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":8,"losses":59,"wins":15},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":10,"wins":41},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":13,"wins":4},"elorian/glimpse":{"draws":8,"losses":6,"wins":4},"fireworks/ember-1":{"draws":12,"losses":21,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":21},"gemini-4-argon":{"draws":2,"losses":21,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":19,"wins":28},"google/gemini-3.5-flash-lite":{"draws":24,"losses":16,"wins":44},"google/gemini-3.6-flash":{"draws":21,"losses":40,"wins":31},"google/gemini-3.8-flash":{"draws":6,"losses":24,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":14,"losses":18,"wins":14},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":34},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":1,"losses":44,"wins":3},"gpt-6-luna":{"draws":13,"losses":16,"wins":19},"gpt-6-sol":{"draws":3,"losses":34,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inception/mercury-3":{"draws":2,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":12,"wins":31},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":14,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":16},"meta/muse-spark-open":{"draws":7,"losses":11,"wins":4},"meta/muse-wonder":{"draws":11,"losses":21,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":12},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":2},"o3":{"draws":7,"losses":15,"wins":44},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":22,"wins":12},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":9,"losses":17,"wins":22},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":7,"wins":13},"stealth/ox-alpha":{"draws":33,"losses":70,"wins":55},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":5,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.7":{"draws":8,"losses":26,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":29,"losses":23,"wins":44},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":16}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":13,"wins":12},"claude-fable-5":{"draws":6,"losses":28,"wins":2},"claude-fable-5-1":{"draws":0,"losses":41,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":20,"wins":7},"claude-opus-4-5":{"draws":6,"losses":44,"wins":8},"claude-opus-4-8":{"draws":7,"losses":23,"wins":2},"claude-opus-5":{"draws":6,"losses":48,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":5,"losses":23,"wins":8},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":12,"losses":20,"wins":20},"deepseek/deepseek-v4-pro":{"draws":5,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":11,"wins":0},"elorian/glimpse":{"draws":3,"losses":4,"wins":5},"fireworks/ember-1":{"draws":8,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":6,"losses":18,"wins":12},"gemini-4-argon":{"draws":0,"losses":16,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":29,"wins":9},"google/gemini-3.5-flash-lite":{"draws":22,"losses":23,"wins":21},"google/gemini-3.6-flash":{"draws":14,"losses":47,"wins":9},"google/gemini-3.8-flash":{"draws":4,"losses":26,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":5},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":22,"wins":6},"gpt-5.4":{"draws":5,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":20,"wins":11},"gpt-5.5":{"draws":8,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":17,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":29,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":6},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":8,"losses":21,"wins":7},"gpt-6-sol":{"draws":4,"losses":31,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":9,"wins":11},"inception/mercury-3":{"draws":2,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":9,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":3,"losses":22,"wins":9},"meta/muse-spark-1.3":{"draws":2,"losses":32,"wins":2},"meta/muse-spark-open":{"draws":5,"losses":13,"wins":4},"meta/muse-wonder":{"draws":3,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":1,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":5,"losses":8,"wins":5},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":5},"mistralai/mistral-medium-3-5":{"draws":5,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":21,"wins":8},"nex-agi/nex-n2-pro":{"draws":3,"losses":10,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":8,"wins":2},"o3":{"draws":5,"losses":36,"wins":13},"openai/gpt-oss-120b":{"draws":9,"losses":12,"wins":11},"poolside/laguna-s-2.1":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":29,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":16,"wins":6},"qwen/qwen3.8-flash":{"draws":3,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":5,"losses":27,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":27,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":8,"wins":3},"stealth/ox-alpha":{"draws":19,"losses":85,"wins":22},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":4},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":3},"thinkingmachines/inkling":{"draws":15,"losses":20,"wins":13},"thinkingmachines/inkling-small":{"draws":9,"losses":13,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":25,"wins":3},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":13,"losses":18,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":35,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":5,"losses":27,"wins":4}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":49,"wins":35},"claude-fable-5":{"draws":21,"losses":104,"wins":7},"claude-fable-5-1":{"draws":4,"losses":141,"wins":1},"claude-haiku-5-5":{"draws":33,"losses":75,"wins":20},"claude-opus-4-5":{"draws":64,"losses":116,"wins":36},"claude-opus-4-8":{"draws":30,"losses":78,"wins":16},"claude-opus-5":{"draws":19,"losses":193,"wins":10},"claude-opus-5-5":{"draws":6,"losses":135,"wins":3},"claude-sonnet-5":{"draws":39,"losses":71,"wins":22},"claude-sonnet-5-5":{"draws":27,"losses":87,"wins":18},"cohere/north-mini-code":{"draws":10,"losses":21,"wins":19},"deepseek/deepseek-v4-flash":{"draws":50,"losses":57,"wins":51},"deepseek/deepseek-v4-pro":{"draws":29,"losses":68,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":62,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":79,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":48,"wins":9},"elorian/glimpse":{"draws":9,"losses":21,"wins":8},"fireworks/ember-1":{"draws":40,"losses":74,"wins":18},"gemini-3.1-pro-preview":{"draws":37,"losses":65,"wins":30},"gemini-4-argon":{"draws":3,"losses":62,"wins":3},"google/gemini-3.1-flash-lite":{"draws":29,"losses":20,"wins":43},"google/gemini-3.5-flash":{"draws":37,"losses":98,"wins":31},"google/gemini-3.5-flash-lite":{"draws":65,"losses":84,"wins":81},"google/gemini-3.6-flash":{"draws":59,"losses":155,"wins":38},"google/gemini-3.8-flash":{"draws":22,"losses":97,"wins":13},"google/gemma-4-31b-it":{"draws":34,"losses":17,"wins":27},"gpt-4.1":{"draws":14,"losses":23,"wins":7},"gpt-4.1-nano":{"draws":10,"losses":3,"wins":3},"gpt-5":{"draws":37,"losses":54,"wins":25},"gpt-5.4":{"draws":32,"losses":77,"wins":17},"gpt-5.4-mini":{"draws":32,"losses":33,"wins":23},"gpt-5.4-nano":{"draws":28,"losses":61,"wins":51},"gpt-5.5":{"draws":43,"losses":66,"wins":11},"gpt-5.6-luna":{"draws":52,"losses":55,"wins":25},"gpt-5.6-sol":{"draws":16,"losses":110,"wins":6},"gpt-5.6-terra":{"draws":38,"losses":73,"wins":15},"gpt-6-astra":{"draws":4,"losses":124,"wins":4},"gpt-6-luna":{"draws":35,"losses":71,"wins":26},"gpt-6-sol":{"draws":18,"losses":105,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":122,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":38,"losses":22,"wins":34},"inception/mercury-3":{"draws":12,"losses":24,"wins":6},"inclusionai/ling-3.0-flash":{"draws":36,"losses":25,"wins":33},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":53,"wins":54},"meta/muse-glimmer-30b":{"draws":43,"losses":29,"wins":42},"meta/muse-spark-1.2":{"draws":32,"losses":76,"wins":18},"meta/muse-spark-1.3":{"draws":24,"losses":93,"wins":15},"meta/muse-spark-open":{"draws":11,"losses":42,"wins":9},"meta/muse-wonder":{"draws":23,"losses":93,"wins":16},"minimax/minimax-m3":{"draws":21,"losses":24,"wins":29},"minimax/minimax-m3.1-flash":{"draws":19,"losses":35,"wins":18},"mistralai/mistral-large-4-0":{"draws":28,"losses":43,"wins":11},"mistralai/mistral-medium-3-5":{"draws":30,"losses":20,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":39,"losses":67,"wins":20},"nex-agi/nex-n2-pro":{"draws":16,"losses":24,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":38,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":14,"wins":9},"o3":{"draws":22,"losses":125,"wins":43},"openai/gpt-oss-120b":{"draws":39,"losses":38,"wins":39},"poolside/laguna-s-2.1":{"draws":42,"losses":46,"wins":40},"qwen/qwen3.7-max":{"draws":28,"losses":29,"wins":23},"qwen/qwen3.7-plus":{"draws":19,"losses":26,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":75,"wins":17},"qwen/qwen3.8-27b":{"draws":22,"losses":52,"wins":20},"qwen/qwen3.8-flash":{"draws":27,"losses":40,"wins":21},"qwen/qwen3.8-max":{"draws":42,"losses":69,"wins":21},"qwen/qwen3.8-max-0902":{"draws":38,"losses":78,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":33,"wins":10},"stealth/ox-alpha":{"draws":101,"losses":250,"wins":65},"stealth/space-bunny-alpha":{"draws":34,"losses":52,"wins":18},"stepfun/step-3.7-flash":{"draws":21,"losses":34,"wins":41},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":27,"losses":26,"wins":19},"tencent/hy4-preview":{"draws":33,"losses":75,"wins":18},"thinkingmachines/inkling":{"draws":50,"losses":67,"wins":57},"thinkingmachines/inkling-small":{"draws":50,"losses":33,"wins":49},"unbiased/pareto-26.10":{"draws":3,"losses":33,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":44,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":10,"wins":18},"x-ai/grok-4.5":{"draws":21,"losses":93,"wins":18},"x-ai/grok-4.6":{"draws":32,"losses":90,"wins":10},"x-ai/grok-4.7":{"draws":12,"losses":98,"wins":8},"x-ai/grok-build-0.1":{"draws":16,"losses":11,"wins":17},"xiaomi/mimo-v2.5":{"draws":64,"losses":72,"wins":72},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":32,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":56,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":63,"wins":13},"z-ai/glm-5.2":{"draws":87,"losses":114,"wins":63},"z-ai/glm-5.3":{"draws":27,"losses":91,"wins":8},"z-ai/glm-5.3-flash":{"draws":27,"losses":79,"wins":26},"z-ai/glm-5.3-flashx":{"draws":34,"losses":78,"wins":20}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":27},"claude-fable-5":{"draws":8,"losses":27,"wins":13},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":18},"claude-opus-4-5":{"draws":20,"losses":20,"wins":38},"claude-opus-4-8":{"draws":10,"losses":18,"wins":16},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":14,"losses":13,"wins":21},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":14},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":18,"wins":40},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":22,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":24,"wins":4},"elorian/glimpse":{"draws":4,"losses":7,"wins":5},"fireworks/ember-1":{"draws":12,"losses":19,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"gemini-4-argon":{"draws":2,"losses":17,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":23},"google/gemini-3.5-flash-lite":{"draws":14,"losses":22,"wins":48},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":42},"google/gemini-3.8-flash":{"draws":6,"losses":27,"wins":15},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":24},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":28},"gpt-5.5":{"draws":8,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":13,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":15},"gpt-5.6-terra":{"draws":10,"losses":14,"wins":22},"gpt-6-astra":{"draws":4,"losses":37,"wins":7},"gpt-6-luna":{"draws":10,"losses":20,"wins":18},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":3,"losses":8,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":4,"wins":38},"meta/muse-glimmer-30b":{"draws":10,"losses":6,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":18},"meta/muse-spark-open":{"draws":9,"losses":10,"wins":7},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":18,"wins":17},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":5,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":5},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":8,"losses":11,"wins":27},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":20,"wins":16},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":36,"losses":65,"wins":57},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":7,"wins":38},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":28},"unbiased/pareto-26.10":{"draws":0,"losses":7,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":23,"wins":15},"x-ai/grok-4.6":{"draws":7,"losses":26,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":22,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":8,"losses":23,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":17}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":13,"wins":18},"claude-fable-5":{"draws":5,"losses":33,"wins":10},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":24,"wins":12},"claude-opus-4-5":{"draws":24,"losses":29,"wins":25},"claude-opus-4-8":{"draws":12,"losses":16,"wins":16},"claude-opus-5":{"draws":9,"losses":63,"wins":10},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":20,"losses":19,"wins":33},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":12,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":7},"elorian/glimpse":{"draws":2,"losses":6,"wins":2},"fireworks/ember-1":{"draws":13,"losses":24,"wins":11},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":0,"losses":22,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":27,"wins":16},"google/gemini-3.5-flash-lite":{"draws":25,"losses":19,"wins":40},"google/gemini-3.6-flash":{"draws":22,"losses":46,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":11},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":17,"wins":14},"gpt-5.4":{"draws":9,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":11,"losses":14,"wins":23},"gpt-5.5":{"draws":13,"losses":15,"wins":16},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":33,"wins":9},"gpt-5.6-terra":{"draws":13,"losses":20,"wins":13},"gpt-6-astra":{"draws":1,"losses":47,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":15},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":17},"inception/mercury-3":{"draws":9,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":15,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":16,"losses":13,"wins":23},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":8,"losses":26,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":24,"wins":13},"meta/muse-spark-open":{"draws":3,"losses":12,"wins":3},"meta/muse-wonder":{"draws":13,"losses":27,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":5,"losses":9,"wins":14},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":4,"wins":5},"o3":{"draws":11,"losses":23,"wins":32},"openai/gpt-oss-120b":{"draws":12,"losses":11,"wins":19},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":12,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":20,"losses":19,"wins":9},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":0,"wins":5},"stealth/ox-alpha":{"draws":42,"losses":66,"wins":50},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":18},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":9,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":11,"losses":26,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":26,"losses":13,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":34,"losses":31,"wins":31},"z-ai/glm-5.3":{"draws":12,"losses":25,"wins":9},"z-ai/glm-5.3-flash":{"draws":5,"losses":29,"wins":14},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":6,"wins":22},"claude-fable-5":{"draws":12,"losses":25,"wins":11},"claude-fable-5-1":{"draws":8,"losses":41,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":18,"wins":13},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":11,"losses":11,"wins":22},"claude-opus-5":{"draws":17,"losses":52,"wins":13},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":11,"losses":15,"wins":22},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":28,"losses":5,"wins":39},"deepseek/deepseek-v4-pro":{"draws":11,"losses":14,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":11,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":13,"wins":4},"elorian/glimpse":{"draws":4,"losses":8,"wins":2},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":16,"losses":12,"wins":20},"gemini-4-argon":{"draws":2,"losses":12,"wins":2},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":18},"google/gemini-3.5-flash":{"draws":22,"losses":15,"wins":23},"google/gemini-3.5-flash-lite":{"draws":34,"losses":7,"wins":43},"google/gemini-3.6-flash":{"draws":29,"losses":33,"wins":30},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":14,"losses":3,"wins":11},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":16,"losses":9,"wins":17},"gpt-5.4":{"draws":15,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":10,"wins":20},"gpt-5.5":{"draws":14,"losses":17,"wins":13},"gpt-5.6-luna":{"draws":22,"losses":6,"wins":20},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":6,"losses":39,"wins":3},"gpt-6-luna":{"draws":16,"losses":10,"wins":22},"gpt-6-sol":{"draws":9,"losses":27,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inception/mercury-3":{"draws":7,"losses":3,"wins":12},"inclusionai/ling-3.0-flash":{"draws":19,"losses":3,"wins":12},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":28},"meta/muse-glimmer-30b":{"draws":18,"losses":4,"wins":20},"meta/muse-spark-1.2":{"draws":15,"losses":13,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":18,"wins":18},"meta/muse-spark-open":{"draws":2,"losses":5,"wins":5},"meta/muse-wonder":{"draws":16,"losses":19,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"minimax/minimax-m3.1-flash":{"draws":6,"losses":5,"wins":17},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":12,"wins":18},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":1,"wins":9},"o3":{"draws":15,"losses":16,"wins":35},"openai/gpt-oss-120b":{"draws":16,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":22,"losses":5,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":1,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":20,"losses":11,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":5,"wins":11},"stealth/ox-alpha":{"draws":37,"losses":58,"wins":63},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":14},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":7,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":6,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":11,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":40,"losses":17,"wins":39},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":17,"wins":21},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":16}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":6,"wins":20},"claude-fable-5":{"draws":7,"losses":17,"wins":12},"claude-fable-5-1":{"draws":1,"losses":24,"wins":5},"claude-haiku-5-5":{"draws":3,"losses":7,"wins":8},"claude-opus-4-5":{"draws":7,"losses":8,"wins":29},"claude-opus-4-8":{"draws":5,"losses":8,"wins":11},"claude-opus-5":{"draws":10,"losses":35,"wins":9},"claude-opus-5-5":{"draws":0,"losses":13,"wins":3},"claude-sonnet-5":{"draws":7,"losses":9,"wins":16},"claude-sonnet-5-5":{"draws":0,"losses":10,"wins":14},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":24},"deepseek/deepseek-v4-pro":{"draws":6,"losses":1,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":5,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":10,"wins":14},"elorian/glimpse":{"draws":5,"losses":7,"wins":14},"fireworks/ember-1":{"draws":5,"losses":4,"wins":17},"gemini-3.1-pro-preview":{"draws":6,"losses":10,"wins":10},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":8,"wins":16},"google/gemini-3.5-flash-lite":{"draws":6,"losses":7,"wins":37},"google/gemini-3.6-flash":{"draws":9,"losses":15,"wins":20},"google/gemini-3.8-flash":{"draws":2,"losses":8,"wins":16},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":9},"gpt-4.1":{"draws":4,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":1,"wins":19},"gpt-5.4":{"draws":6,"losses":5,"wins":11},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":13},"gpt-5.5":{"draws":10,"losses":7,"wins":13},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":11,"wins":7},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":14},"gpt-6-astra":{"draws":1,"losses":21,"wins":2},"gpt-6-luna":{"draws":3,"losses":5,"wins":14},"gpt-6-sol":{"draws":2,"losses":17,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":14,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":3},"inception/mercury-3":{"draws":3,"losses":5,"wins":22},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":13},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":20},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":6,"wins":9},"meta/muse-spark-1.3":{"draws":4,"losses":11,"wins":15},"meta/muse-spark-open":{"draws":8,"losses":14,"wins":24},"meta/muse-wonder":{"draws":5,"losses":8,"wins":9},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":8},"minimax/minimax-m3.1-flash":{"draws":5,"losses":7,"wins":28},"mistralai/mistral-large-4-0":{"draws":1,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":14},"o3":{"draws":3,"losses":5,"wins":22},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":15},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":22},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":10,"wins":12},"qwen/qwen3.8-27b":{"draws":1,"losses":5,"wins":8},"qwen/qwen3.8-flash":{"draws":2,"losses":8,"wins":16},"qwen/qwen3.8-max":{"draws":5,"losses":8,"wins":19},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":9,"wins":27},"stealth/ox-alpha":{"draws":14,"losses":37,"wins":49},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":14},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":14},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":15},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":27},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":26},"unbiased/pareto-26.10":{"draws":3,"losses":12,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":11,"wins":13},"x-ai/grok-4.6":{"draws":6,"losses":8,"wins":10},"x-ai/grok-4.7":{"draws":2,"losses":11,"wins":7},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":7},"z-ai/glm-5.2":{"draws":5,"losses":4,"wins":39},"z-ai/glm-5.3":{"draws":1,"losses":14,"wins":9},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":17},"z-ai/glm-5.3-flashx":{"draws":5,"losses":3,"wins":12}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":5,"wins":14},"claude-fable-5":{"draws":4,"losses":5,"wins":13},"claude-fable-5-1":{"draws":3,"losses":17,"wins":2},"claude-haiku-5-5":{"draws":5,"losses":7,"wins":14},"claude-opus-4-5":{"draws":10,"losses":2,"wins":24},"claude-opus-4-8":{"draws":5,"losses":4,"wins":19},"claude-opus-5":{"draws":1,"losses":24,"wins":9},"claude-opus-5-5":{"draws":2,"losses":21,"wins":1},"claude-sonnet-5":{"draws":7,"losses":3,"wins":8},"claude-sonnet-5-5":{"draws":7,"losses":7,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":22},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":5,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":16,"wins":17},"elorian/glimpse":{"draws":1,"losses":2,"wins":5},"fireworks/ember-1":{"draws":2,"losses":4,"wins":8},"gemini-3.1-pro-preview":{"draws":8,"losses":4,"wins":14},"gemini-4-argon":{"draws":7,"losses":30,"wins":11},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":12},"google/gemini-3.5-flash-lite":{"draws":8,"losses":2,"wins":24},"google/gemini-3.6-flash":{"draws":8,"losses":10,"wins":20},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":14},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":1,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":3,"wins":16},"gpt-5.4":{"draws":6,"losses":8,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":7,"losses":2,"wins":13},"gpt-5.5":{"draws":5,"losses":8,"wins":11},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":11},"gpt-5.6-terra":{"draws":5,"losses":0,"wins":11},"gpt-6-astra":{"draws":0,"losses":17,"wins":3},"gpt-6-luna":{"draws":7,"losses":4,"wins":13},"gpt-6-sol":{"draws":5,"losses":7,"wins":10},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":10},"inception/mercury-3":{"draws":6,"losses":5,"wins":19},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":9},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":8},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":10},"meta/muse-spark-1.2":{"draws":5,"losses":3,"wins":12},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":8},"meta/muse-spark-open":{"draws":9,"losses":6,"wins":29},"meta/muse-wonder":{"draws":9,"losses":9,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":9},"minimax/minimax-m3.1-flash":{"draws":13,"losses":4,"wins":23},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":4,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":1,"wins":13},"o3":{"draws":3,"losses":3,"wins":22},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":2,"wins":15},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":11},"qwen/qwen3.8-flash":{"draws":4,"losses":3,"wins":9},"qwen/qwen3.8-max":{"draws":6,"losses":4,"wins":10},"qwen/qwen3.8-max-0902":{"draws":12,"losses":3,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":5,"wins":27},"stealth/ox-alpha":{"draws":24,"losses":26,"wins":28},"stealth/space-bunny-alpha":{"draws":2,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":6,"losses":5,"wins":13},"thinkingmachines/inkling":{"draws":18,"losses":1,"wins":19},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":16},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":13},"x-ai/grok-4.6":{"draws":8,"losses":4,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":7,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":13,"losses":0,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":3,"wins":11},"z-ai/glm-5.2":{"draws":17,"losses":6,"wins":29},"z-ai/glm-5.3":{"draws":6,"losses":8,"wins":6},"z-ai/glm-5.3-flash":{"draws":5,"losses":7,"wins":14},"z-ai/glm-5.3-flashx":{"draws":5,"losses":6,"wins":7}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":5,"wins":25},"claude-fable-5":{"draws":12,"losses":31,"wins":5},"claude-fable-5-1":{"draws":0,"losses":52,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":29,"losses":21,"wins":28},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":24,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":15,"wins":5},"elorian/glimpse":{"draws":0,"losses":1,"wins":3},"fireworks/ember-1":{"draws":10,"losses":7,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"gemini-4-argon":{"draws":0,"losses":12,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":24},"google/gemini-3.5-flash-lite":{"draws":34,"losses":9,"wins":41},"google/gemini-3.6-flash":{"draws":30,"losses":27,"wins":35},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":8,"wins":22},"gpt-5.4":{"draws":14,"losses":20,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":15,"losses":9,"wins":24},"gpt-5.5":{"draws":19,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":26,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":11,"wins":22},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inception/mercury-3":{"draws":6,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":6,"wins":33},"meta/muse-glimmer-30b":{"draws":17,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":21,"losses":16,"wins":11},"meta/muse-spark-open":{"draws":5,"losses":12,"wins":7},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":4,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":12,"wins":17},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":5,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":0,"wins":5},"o3":{"draws":13,"losses":16,"wins":37},"openai/gpt-oss-120b":{"draws":16,"losses":3,"wins":23},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":13,"losses":8,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":12,"wins":21},"qwen/qwen3.8-max-0902":{"draws":19,"losses":19,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":18,"wins":8},"stealth/ox-alpha":{"draws":48,"losses":51,"wins":59},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":24,"losses":3,"wins":37},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":20,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":7,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":19,"wins":43},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":9},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":18,"wins":18}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":13,"wins":15},"claude-fable-5":{"draws":13,"losses":25,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":26,"losses":34,"wins":18},"claude-opus-4-8":{"draws":16,"losses":22,"wins":6},"claude-opus-5":{"draws":10,"losses":65,"wins":7},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":19,"losses":15,"wins":14},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":11},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":28,"losses":17,"wins":27},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":23,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":16,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":16,"wins":4},"elorian/glimpse":{"draws":4,"losses":5,"wins":1},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":11,"losses":11,"wins":10},"gemini-4-argon":{"draws":1,"losses":13,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":16,"losses":30,"wins":14},"google/gemini-3.5-flash-lite":{"draws":35,"losses":24,"wins":25},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":5,"wins":9},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":12,"wins":13},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":19},"gpt-5.5":{"draws":15,"losses":20,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":15,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":18,"losses":16,"wins":14},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":5,"wins":10},"inception/mercury-3":{"draws":7,"losses":10,"wins":3},"inclusionai/ling-3.0-flash":{"draws":18,"losses":2,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":23},"meta/muse-glimmer-30b":{"draws":20,"losses":3,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":12},"meta/muse-spark-open":{"draws":5,"losses":9,"wins":4},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":10},"minimax/minimax-m3.1-flash":{"draws":10,"losses":8,"wins":10},"mistralai/mistral-large-4-0":{"draws":7,"losses":14,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":24,"wins":10},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":4},"o3":{"draws":17,"losses":28,"wins":21},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":17},"poolside/laguna-s-2.1":{"draws":20,"losses":11,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":15,"losses":21,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":8,"wins":8},"stealth/ox-alpha":{"draws":45,"losses":72,"wins":41},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":22},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":9,"losses":25,"wins":14},"x-ai/grok-4.6":{"draws":14,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":35,"wins":26},"z-ai/glm-5.3":{"draws":9,"losses":30,"wins":7},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":1,"wins":23},"claude-fable-5":{"draws":2,"losses":6,"wins":16},"claude-fable-5-1":{"draws":2,"losses":25,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":7,"wins":8},"claude-opus-4-5":{"draws":4,"losses":6,"wins":36},"claude-opus-4-8":{"draws":2,"losses":2,"wins":14},"claude-opus-5":{"draws":6,"losses":15,"wins":13},"claude-opus-5-5":{"draws":1,"losses":15,"wins":6},"claude-sonnet-5":{"draws":3,"losses":1,"wins":24},"claude-sonnet-5-5":{"draws":3,"losses":9,"wins":14},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":27},"deepseek/deepseek-v4-pro":{"draws":5,"losses":3,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":3,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":8,"wins":27},"elorian/glimpse":{"draws":6,"losses":3,"wins":17},"fireworks/ember-1":{"draws":5,"losses":0,"wins":13},"gemini-3.1-pro-preview":{"draws":2,"losses":2,"wins":14},"gemini-4-argon":{"draws":7,"losses":16,"wins":9},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":36},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":33},"google/gemini-3.6-flash":{"draws":8,"losses":7,"wins":33},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":20},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":16},"gpt-4.1":{"draws":1,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":0,"wins":14},"gpt-5.4":{"draws":0,"losses":8,"wins":14},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":11},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":26},"gpt-5.5":{"draws":3,"losses":3,"wins":14},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":13},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":20},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":19},"gpt-6-astra":{"draws":1,"losses":23,"wins":4},"gpt-6-luna":{"draws":4,"losses":3,"wins":21},"gpt-6-sol":{"draws":3,"losses":10,"wins":9},"gpt-6.1-sol":{"draws":0,"losses":15,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":8},"inception/mercury-3":{"draws":6,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":12},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":25},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":21},"meta/muse-spark-1.2":{"draws":6,"losses":3,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":4,"wins":13},"meta/muse-spark-open":{"draws":4,"losses":10,"wins":32},"meta/muse-wonder":{"draws":2,"losses":2,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":14},"minimax/minimax-m3.1-flash":{"draws":8,"losses":4,"wins":28},"mistralai/mistral-large-4-0":{"draws":0,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":19},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":18},"o3":{"draws":0,"losses":4,"wins":32},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":10},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":4,"wins":15},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":12},"qwen/qwen3.8-flash":{"draws":3,"losses":6,"wins":9},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":8},"qwen/qwen3.8-max-0902":{"draws":1,"losses":3,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":6,"wins":34},"stealth/ox-alpha":{"draws":12,"losses":12,"wins":54},"stealth/space-bunny-alpha":{"draws":3,"losses":1,"wins":12},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":12},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":15},"tencent/hy4-preview":{"draws":5,"losses":1,"wins":14},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":27},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":4},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":5,"losses":4,"wins":11},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":8,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":10},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":36},"z-ai/glm-5.3":{"draws":3,"losses":10,"wins":9},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":5,"wins":19}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":8},"claude-fable-5":{"draws":4,"losses":30,"wins":2},"claude-fable-5-1":{"draws":1,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":4},"claude-opus-4-5":{"draws":14,"losses":44,"wins":2},"claude-opus-4-8":{"draws":11,"losses":23,"wins":2},"claude-opus-5":{"draws":7,"losses":46,"wins":5},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":2},"claude-sonnet-5-5":{"draws":8,"losses":22,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":18,"losses":27,"wins":9},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":14,"wins":1},"elorian/glimpse":{"draws":6,"losses":7,"wins":1},"fireworks/ember-1":{"draws":7,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":7,"losses":19,"wins":10},"gemini-4-argon":{"draws":1,"losses":11,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":8,"wins":8},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":9},"google/gemini-3.5-flash-lite":{"draws":18,"losses":28,"wins":20},"google/gemini-3.6-flash":{"draws":16,"losses":46,"wins":8},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":7},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":20,"wins":2},"gpt-5.4":{"draws":7,"losses":26,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":3},"gpt-5.4-nano":{"draws":11,"losses":20,"wins":9},"gpt-5.5":{"draws":11,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":33,"wins":1},"gpt-5.6-terra":{"draws":12,"losses":19,"wins":3},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":11,"losses":22,"wins":3},"gpt-6-sol":{"draws":6,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":9,"wins":5},"inception/mercury-3":{"draws":0,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":20,"wins":13},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":22,"wins":5},"meta/muse-spark-1.3":{"draws":5,"losses":30,"wins":1},"meta/muse-spark-open":{"draws":2,"losses":10,"wins":0},"meta/muse-wonder":{"draws":5,"losses":30,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":6},"minimax/minimax-m3.1-flash":{"draws":4,"losses":11,"wins":3},"mistralai/mistral-large-4-0":{"draws":7,"losses":15,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":9,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":13,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":0},"o3":{"draws":11,"losses":45,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":17,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":16,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":27,"wins":1},"qwen/qwen3.8-27b":{"draws":5,"losses":17,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":23,"wins":0},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":13,"wins":0},"stealth/ox-alpha":{"draws":19,"losses":70,"wins":13},"stealth/space-bunny-alpha":{"draws":7,"losses":18,"wins":5},"stepfun/step-3.7-flash":{"draws":6,"losses":18,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":12,"losses":22,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":23,"wins":13},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":27,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":22,"losses":23,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":17,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":14,"losses":47,"wins":11},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":24,"wins":4},"z-ai/glm-5.3-flashx":{"draws":10,"losses":23,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":26},"claude-fable-5":{"draws":11,"losses":25,"wins":12},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":19},"claude-opus-4-5":{"draws":22,"losses":16,"wins":40},"claude-opus-4-8":{"draws":8,"losses":14,"wins":22},"claude-opus-5":{"draws":8,"losses":65,"wins":9},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":9,"losses":11,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":23,"losses":7,"wins":42},"deepseek/deepseek-v4-pro":{"draws":11,"losses":7,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":8,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":11,"wins":6},"elorian/glimpse":{"draws":3,"losses":3,"wins":8},"fireworks/ember-1":{"draws":11,"losses":15,"wins":22},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":24},"gemini-4-argon":{"draws":3,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":9,"losses":14,"wins":21},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":62},"google/gemini-3.6-flash":{"draws":19,"losses":33,"wins":40},"google/gemini-3.8-flash":{"draws":9,"losses":23,"wins":16},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":10,"wins":23},"gpt-5.4":{"draws":8,"losses":22,"wins":16},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":8,"wins":28},"gpt-5.5":{"draws":11,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":17,"losses":8,"wins":23},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":14},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":18},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":14,"losses":13,"wins":21},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inception/mercury-3":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":10,"wins":32},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":9,"losses":24,"wins":15},"meta/muse-spark-open":{"draws":3,"losses":6,"wins":7},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"minimax/minimax-m3.1-flash":{"draws":8,"losses":1,"wins":7},"mistralai/mistral-large-4-0":{"draws":8,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":18},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":4},"o3":{"draws":7,"losses":16,"wins":43},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":10,"losses":8,"wins":14},"qwen/qwen3.8-max":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":14,"losses":18,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":10,"wins":13},"stealth/ox-alpha":{"draws":32,"losses":49,"wins":77},"stealth/space-bunny-alpha":{"draws":12,"losses":3,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":17},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":28},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":17,"wins":22},"x-ai/grok-4.6":{"draws":15,"losses":24,"wins":9},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":11,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":25,"losses":19,"wins":52},"z-ai/glm-5.3":{"draws":10,"losses":19,"wins":17},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":21},"z-ai/glm-5.3-flashx":{"draws":20,"losses":14,"wins":14}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":34,"wins":18},"claude-fable-5":{"draws":16,"losses":63,"wins":5},"claude-fable-5-1":{"draws":9,"losses":84,"wins":1},"claude-haiku-5-5":{"draws":20,"losses":48,"wins":12},"claude-opus-4-5":{"draws":49,"losses":75,"wins":12},"claude-opus-4-8":{"draws":23,"losses":52,"wins":1},"claude-opus-5":{"draws":23,"losses":113,"wins":8},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":26,"losses":48,"wins":10},"claude-sonnet-5-5":{"draws":15,"losses":57,"wins":12},"cohere/north-mini-code":{"draws":11,"losses":15,"wins":6},"deepseek/deepseek-v4-flash":{"draws":41,"losses":52,"wins":31},"deepseek/deepseek-v4-pro":{"draws":21,"losses":37,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":44,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":46,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":44,"wins":3},"elorian/glimpse":{"draws":3,"losses":12,"wins":3},"fireworks/ember-1":{"draws":34,"losses":42,"wins":8},"gemini-3.1-pro-preview":{"draws":33,"losses":37,"wins":14},"gemini-4-argon":{"draws":4,"losses":36,"wins":0},"google/gemini-3.1-flash-lite":{"draws":19,"losses":13,"wins":24},"google/gemini-3.5-flash":{"draws":23,"losses":60,"wins":23},"google/gemini-3.5-flash-lite":{"draws":41,"losses":45,"wins":36},"google/gemini-3.6-flash":{"draws":48,"losses":95,"wins":19},"google/gemini-3.8-flash":{"draws":17,"losses":63,"wins":4},"google/gemma-4-31b-it":{"draws":20,"losses":14,"wins":14},"gpt-4.1":{"draws":11,"losses":14,"wins":3},"gpt-4.1-nano":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":23,"losses":34,"wins":17},"gpt-5.4":{"draws":22,"losses":51,"wins":9},"gpt-5.4-mini":{"draws":21,"losses":24,"wins":11},"gpt-5.4-nano":{"draws":20,"losses":34,"wins":30},"gpt-5.5":{"draws":32,"losses":39,"wins":7},"gpt-5.6-luna":{"draws":29,"losses":41,"wins":14},"gpt-5.6-sol":{"draws":12,"losses":68,"wins":4},"gpt-5.6-terra":{"draws":26,"losses":48,"wins":6},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":26,"losses":39,"wins":19},"gpt-6-sol":{"draws":14,"losses":61,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":78,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":20,"wins":16},"inception/mercury-3":{"draws":8,"losses":13,"wins":3},"inclusionai/ling-3.0-flash":{"draws":21,"losses":20,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":37,"wins":27},"meta/muse-glimmer-30b":{"draws":31,"losses":20,"wins":23},"meta/muse-spark-1.2":{"draws":21,"losses":50,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":62,"wins":7},"meta/muse-spark-open":{"draws":6,"losses":33,"wins":1},"meta/muse-wonder":{"draws":15,"losses":63,"wins":6},"minimax/minimax-m3":{"draws":11,"losses":15,"wins":18},"minimax/minimax-m3.1-flash":{"draws":13,"losses":18,"wins":9},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":20,"losses":12,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":31,"losses":41,"wins":8},"nex-agi/nex-n2-pro":{"draws":11,"losses":15,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":29,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":17,"wins":1},"o3":{"draws":18,"losses":86,"wins":14},"openai/gpt-oss-120b":{"draws":24,"losses":30,"wins":18},"poolside/laguna-s-2.1":{"draws":26,"losses":41,"wins":15},"qwen/qwen3.7-max":{"draws":15,"losses":24,"wins":9},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":50,"wins":6},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":10},"qwen/qwen3.8-flash":{"draws":22,"losses":30,"wins":4},"qwen/qwen3.8-max":{"draws":28,"losses":46,"wins":10},"qwen/qwen3.8-max-0902":{"draws":25,"losses":53,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":21,"wins":4},"stealth/ox-alpha":{"draws":66,"losses":178,"wins":38},"stealth/space-bunny-alpha":{"draws":20,"losses":35,"wins":11},"stepfun/step-3.7-flash":{"draws":17,"losses":30,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":22,"wins":8},"tencent/hy4-preview":{"draws":24,"losses":46,"wins":12},"thinkingmachines/inkling":{"draws":31,"losses":49,"wins":34},"thinkingmachines/inkling-small":{"draws":26,"losses":24,"wins":34},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":8,"losses":12,"wins":2},"x-ai/grok-4.5":{"draws":21,"losses":55,"wins":8},"x-ai/grok-4.6":{"draws":23,"losses":57,"wins":4},"x-ai/grok-4.7":{"draws":7,"losses":58,"wins":7},"x-ai/grok-build-0.1":{"draws":13,"losses":12,"wins":3},"xiaomi/mimo-v2.5":{"draws":37,"losses":56,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":19,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":37,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":44,"wins":6},"z-ai/glm-5.2":{"draws":59,"losses":76,"wins":33},"z-ai/glm-5.3":{"draws":18,"losses":59,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":50,"wins":15},"z-ai/glm-5.3-flashx":{"draws":21,"losses":53,"wins":10}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":13,"wins":47},"claude-fable-5":{"draws":13,"losses":41,"wins":30},"claude-fable-5-1":{"draws":8,"losses":80,"wins":8},"claude-haiku-5-5":{"draws":15,"losses":29,"wins":36},"claude-opus-4-5":{"draws":40,"losses":27,"wins":69},"claude-opus-4-8":{"draws":16,"losses":23,"wins":37},"claude-opus-5":{"draws":16,"losses":91,"wins":33},"claude-opus-5-5":{"draws":6,"losses":70,"wins":12},"claude-sonnet-5":{"draws":20,"losses":24,"wins":40},"claude-sonnet-5-5":{"draws":13,"losses":32,"wins":39},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":25},"deepseek/deepseek-v4-flash":{"draws":26,"losses":14,"wins":84},"deepseek/deepseek-v4-pro":{"draws":18,"losses":25,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":19,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":24,"wins":40},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":16,"wins":17},"elorian/glimpse":{"draws":5,"losses":8,"wins":15},"fireworks/ember-1":{"draws":21,"losses":31,"wins":32},"gemini-3.1-pro-preview":{"draws":15,"losses":27,"wins":42},"gemini-4-argon":{"draws":3,"losses":28,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":47},"google/gemini-3.5-flash":{"draws":21,"losses":32,"wins":53},"google/gemini-3.5-flash-lite":{"draws":41,"losses":24,"wins":85},"google/gemini-3.6-flash":{"draws":26,"losses":47,"wins":63},"google/gemini-3.8-flash":{"draws":17,"losses":33,"wins":34},"google/gemma-4-31b-it":{"draws":13,"losses":7,"wins":28},"gpt-4.1":{"draws":7,"losses":4,"wins":17},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":15,"losses":15,"wins":44},"gpt-5.4":{"draws":17,"losses":34,"wins":31},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":31},"gpt-5.4-nano":{"draws":13,"losses":10,"wins":59},"gpt-5.5":{"draws":17,"losses":31,"wins":30},"gpt-5.6-luna":{"draws":22,"losses":14,"wins":48},"gpt-5.6-sol":{"draws":11,"losses":46,"wins":27},"gpt-5.6-terra":{"draws":23,"losses":16,"wins":41},"gpt-6-astra":{"draws":7,"losses":72,"wins":5},"gpt-6-luna":{"draws":21,"losses":22,"wins":41},"gpt-6-sol":{"draws":8,"losses":51,"wins":25},"gpt-6.1-sol":{"draws":4,"losses":66,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":36},"inception/mercury-3":{"draws":11,"losses":5,"wins":14},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":41},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":9,"wins":65},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":47},"meta/muse-spark-1.2":{"draws":15,"losses":27,"wins":38},"meta/muse-spark-1.3":{"draws":7,"losses":42,"wins":35},"meta/muse-spark-open":{"draws":5,"losses":15,"wins":18},"meta/muse-wonder":{"draws":13,"losses":43,"wins":28},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":32},"minimax/minimax-m3.1-flash":{"draws":8,"losses":6,"wins":30},"mistralai/mistral-large-4-0":{"draws":10,"losses":19,"wins":23},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":2,"wins":11},"moonshotai/kimi-k3":{"draws":19,"losses":27,"wins":34},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":1,"wins":14},"o3":{"draws":14,"losses":25,"wins":81},"openai/gpt-oss-120b":{"draws":21,"losses":6,"wins":45},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":48},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":29},"qwen/qwen3.7-plus":{"draws":11,"losses":3,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":25,"wins":38},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":34},"qwen/qwen3.8-flash":{"draws":15,"losses":14,"wins":27},"qwen/qwen3.8-max":{"draws":20,"losses":27,"wins":37},"qwen/qwen3.8-max-0902":{"draws":16,"losses":30,"wins":38},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":14,"wins":13},"stealth/ox-alpha":{"draws":56,"losses":102,"wins":126},"stealth/space-bunny-alpha":{"draws":19,"losses":10,"wins":39},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":43},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":13,"losses":9,"wins":22},"tencent/hy4-preview":{"draws":17,"losses":29,"wins":36},"thinkingmachines/inkling":{"draws":27,"losses":16,"wins":73},"thinkingmachines/inkling-small":{"draws":19,"losses":11,"wins":54},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":2},"unbiased/pareto-26.10-preview":{"draws":3,"losses":22,"wins":3},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":21},"x-ai/grok-4.5":{"draws":18,"losses":31,"wins":35},"x-ai/grok-4.6":{"draws":21,"losses":35,"wins":28},"x-ai/grok-4.7":{"draws":4,"losses":47,"wins":21},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":20},"xiaomi/mimo-v2.5":{"draws":35,"losses":10,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":18,"wins":25},"z-ai/glm-5.2":{"draws":38,"losses":47,"wins":83},"z-ai/glm-5.3":{"draws":13,"losses":46,"wins":21},"z-ai/glm-5.3-flash":{"draws":7,"losses":44,"wins":33},"z-ai/glm-5.3-flashx":{"draws":14,"losses":31,"wins":39}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":9,"losses":14,"wins":25},"claude-fable-5-1":{"draws":1,"losses":47,"wins":6},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":31,"losses":9,"wins":38},"claude-opus-4-8":{"draws":12,"losses":12,"wins":20},"claude-opus-5":{"draws":11,"losses":50,"wins":21},"claude-opus-5-5":{"draws":7,"losses":42,"wins":3},"claude-sonnet-5":{"draws":15,"losses":10,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":16,"losses":8,"wins":48},"deepseek/deepseek-v4-pro":{"draws":13,"losses":12,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":12,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":14,"wins":11},"elorian/glimpse":{"draws":2,"losses":5,"wins":9},"fireworks/ember-1":{"draws":17,"losses":13,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":9,"wins":25},"gemini-4-argon":{"draws":2,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":16,"losses":14,"wins":30},"google/gemini-3.5-flash-lite":{"draws":23,"losses":3,"wins":58},"google/gemini-3.6-flash":{"draws":26,"losses":24,"wins":42},"google/gemini-3.8-flash":{"draws":9,"losses":10,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":12,"wins":19},"gpt-5.4":{"draws":12,"losses":17,"wins":17},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":13,"losses":8,"wins":27},"gpt-5.5":{"draws":23,"losses":12,"wins":9},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":30},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":15},"gpt-5.6-terra":{"draws":14,"losses":10,"wins":22},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":14,"losses":12,"wins":22},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":0,"wins":20},"inception/mercury-3":{"draws":6,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":12,"losses":0,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":4,"wins":33},"meta/muse-glimmer-30b":{"draws":17,"losses":3,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":11},"meta/muse-spark-1.3":{"draws":15,"losses":14,"wins":19},"meta/muse-spark-open":{"draws":5,"losses":10,"wins":9},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":18},"minimax/minimax-m3.1-flash":{"draws":4,"losses":6,"wins":18},"mistralai/mistral-large-4-0":{"draws":11,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":11,"losses":0,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":10,"wins":21},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":0,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":6,"wins":9},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":17,"losses":6,"wins":23},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":12,"wins":21},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":22},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":13,"wins":21},"qwen/qwen3.8-max-0902":{"draws":18,"losses":11,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":1,"wins":8},"stealth/ox-alpha":{"draws":41,"losses":40,"wins":77},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":14,"losses":14,"wins":18},"thinkingmachines/inkling":{"draws":23,"losses":4,"wins":37},"thinkingmachines/inkling-small":{"draws":17,"losses":2,"wins":29},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":21,"wins":16},"x-ai/grok-4.6":{"draws":21,"losses":16,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":25,"losses":3,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":32,"losses":15,"wins":49},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":19,"wins":22},"z-ai/glm-5.3-flashx":{"draws":12,"losses":14,"wins":22}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":13,"wins":17},"claude-fable-5":{"draws":11,"losses":30,"wins":7},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":28,"wins":6},"claude-opus-4-5":{"draws":28,"losses":37,"wins":13},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":13,"losses":62,"wins":7},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":13,"losses":25,"wins":10},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":34,"losses":24,"wins":14},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":3},"elorian/glimpse":{"draws":5,"losses":5,"wins":2},"fireworks/ember-1":{"draws":19,"losses":21,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":20,"wins":11},"gemini-4-argon":{"draws":1,"losses":23,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":15},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":29,"losses":31,"wins":24},"google/gemini-3.6-flash":{"draws":28,"losses":49,"wins":15},"google/gemini-3.8-flash":{"draws":10,"losses":31,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":6},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":17,"wins":8},"gpt-5.4":{"draws":17,"losses":22,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":17,"losses":20,"wins":11},"gpt-5.5":{"draws":19,"losses":20,"wins":5},"gpt-5.6-luna":{"draws":20,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":38,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":5,"losses":41,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":9,"wins":10},"inception/mercury-3":{"draws":9,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":15,"wins":16},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":18,"wins":4},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":8},"minimax/minimax-m3.1-flash":{"draws":4,"losses":7,"wins":5},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":12},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":8,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":9,"wins":2},"o3":{"draws":15,"losses":34,"wins":17},"openai/gpt-oss-120b":{"draws":17,"losses":17,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":14,"wins":14},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":16,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":21,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":13,"wins":2},"stealth/ox-alpha":{"draws":32,"losses":91,"wins":35},"stealth/space-bunny-alpha":{"draws":14,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":9},"thinkingmachines/inkling":{"draws":25,"losses":17,"wins":22},"thinkingmachines/inkling-small":{"draws":19,"losses":13,"wins":16},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":29,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":34,"losses":19,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":31,"wins":22},"z-ai/glm-5.3":{"draws":13,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":15,"losses":24,"wins":9}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":15,"wins":16},"claude-fable-5":{"draws":7,"losses":27,"wins":8},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":15,"losses":31,"wins":22},"claude-opus-4-8":{"draws":8,"losses":21,"wins":9},"claude-opus-5":{"draws":8,"losses":57,"wins":5},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":13,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":26,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":15,"losses":17,"wins":30},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":21,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":16,"wins":4},"elorian/glimpse":{"draws":6,"losses":5,"wins":3},"fireworks/ember-1":{"draws":11,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":12},"gemini-4-argon":{"draws":3,"losses":16,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":14},"google/gemini-3.5-flash-lite":{"draws":19,"losses":26,"wins":31},"google/gemini-3.6-flash":{"draws":10,"losses":45,"wins":27},"google/gemini-3.8-flash":{"draws":7,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":11},"gpt-4.1":{"draws":3,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":6},"gpt-5.4":{"draws":9,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":21,"wins":15},"gpt-5.5":{"draws":12,"losses":15,"wins":13},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":3,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":11},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":10,"losses":19,"wins":13},"gpt-6-sol":{"draws":2,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":15},"inception/mercury-3":{"draws":0,"losses":11,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":10,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":26},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":13},"meta/muse-spark-1.2":{"draws":6,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":26,"wins":9},"meta/muse-spark-open":{"draws":2,"losses":7,"wins":3},"meta/muse-wonder":{"draws":7,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":10},"minimax/minimax-m3.1-flash":{"draws":7,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":8,"losses":15,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":13,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":5,"wins":4},"o3":{"draws":9,"losses":24,"wins":31},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":12,"losses":12,"wins":16},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.8-max":{"draws":7,"losses":27,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":9,"wins":4},"stealth/ox-alpha":{"draws":35,"losses":61,"wins":46},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":13,"losses":14,"wins":31},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":20},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":26,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":20,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":29,"losses":28,"wins":27},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":8},"z-ai/glm-5.3-flash":{"draws":7,"losses":28,"wins":7},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":9,"wins":24},"claude-fable-5":{"draws":13,"losses":22,"wins":13},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":15},"claude-opus-4-5":{"draws":28,"losses":11,"wins":39},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":6,"losses":63,"wins":13},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":19,"losses":9,"wins":20},"claude-sonnet-5-5":{"draws":17,"losses":20,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":7,"wins":8},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":8,"wins":6},"elorian/glimpse":{"draws":4,"losses":5,"wins":7},"fireworks/ember-1":{"draws":16,"losses":14,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"gemini-4-argon":{"draws":2,"losses":10,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":19,"wins":27},"google/gemini-3.5-flash-lite":{"draws":24,"losses":14,"wins":46},"google/gemini-3.6-flash":{"draws":25,"losses":35,"wins":32},"google/gemini-3.8-flash":{"draws":15,"losses":16,"wins":17},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":12,"wins":19},"gpt-5.4":{"draws":8,"losses":10,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":27},"gpt-5.5":{"draws":16,"losses":16,"wins":12},"gpt-5.6-luna":{"draws":19,"losses":6,"wins":23},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":14},"gpt-5.6-terra":{"draws":17,"losses":10,"wins":19},"gpt-6-astra":{"draws":3,"losses":38,"wins":7},"gpt-6-luna":{"draws":15,"losses":12,"wins":21},"gpt-6-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":1,"wins":15},"inception/mercury-3":{"draws":4,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":13,"losses":6,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":30},"meta/muse-glimmer-30b":{"draws":16,"losses":3,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":14,"wins":20},"meta/muse-spark-1.3":{"draws":15,"losses":18,"wins":15},"meta/muse-spark-open":{"draws":4,"losses":12,"wins":6},"meta/muse-wonder":{"draws":15,"losses":20,"wins":13},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":7,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":12,"losses":5,"wins":13},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":23},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":4},"o3":{"draws":10,"losses":12,"wins":44},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":15,"losses":5,"wins":26},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":21,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max-0902":{"draws":16,"losses":15,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":4,"wins":7},"stealth/ox-alpha":{"draws":52,"losses":47,"wins":59},"stealth/space-bunny-alpha":{"draws":15,"losses":6,"wins":17},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":3,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":16,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":19,"losses":3,"wins":26},"unbiased/pareto-26.10":{"draws":3,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":16,"wins":19},"x-ai/grok-4.6":{"draws":19,"losses":14,"wins":15},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":26,"losses":7,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":8,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":35,"losses":19,"wins":42},"z-ai/glm-5.3":{"draws":11,"losses":24,"wins":11},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":18},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":10,"wins":20},"claude-fable-5":{"draws":12,"losses":26,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":21,"losses":29,"wins":28},"claude-opus-4-8":{"draws":12,"losses":14,"wins":18},"claude-opus-5":{"draws":11,"losses":62,"wins":9},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":17,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":24,"losses":11,"wins":37},"deepseek/deepseek-v4-pro":{"draws":16,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":18,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":18,"wins":4},"elorian/glimpse":{"draws":2,"losses":2,"wins":6},"fireworks/ember-1":{"draws":14,"losses":22,"wins":12},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":18},"gemini-4-argon":{"draws":4,"losses":24,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":18,"losses":18,"wins":24},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":42},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":25},"google/gemini-3.8-flash":{"draws":8,"losses":28,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":9,"wins":24},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":22,"losses":14,"wins":8},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":11},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":17,"wins":10},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":16},"inception/mercury-3":{"draws":3,"losses":13,"wins":2},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":7,"wins":28},"meta/muse-glimmer-30b":{"draws":19,"losses":0,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":9,"losses":29,"wins":10},"meta/muse-spark-open":{"draws":6,"losses":3,"wins":1},"meta/muse-wonder":{"draws":10,"losses":30,"wins":8},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":11,"losses":11,"wins":8},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":13,"wins":19},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":9,"wins":3},"o3":{"draws":10,"losses":28,"wins":28},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":15,"losses":21,"wins":12},"qwen/qwen3.8-max-0902":{"draws":14,"losses":21,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":11,"wins":4},"stealth/ox-alpha":{"draws":35,"losses":75,"wins":48},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":20,"wins":11},"thinkingmachines/inkling":{"draws":23,"losses":11,"wins":30},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":24,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":7,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":13,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":37,"losses":29,"wins":30},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":26,"wins":26},"claude-fable-5":{"draws":8,"losses":54,"wins":10},"claude-fable-5-1":{"draws":0,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":38,"wins":24},"claude-opus-4-5":{"draws":32,"losses":47,"wins":41},"claude-opus-4-8":{"draws":11,"losses":42,"wins":19},"claude-opus-5":{"draws":10,"losses":92,"wins":14},"claude-opus-5-5":{"draws":2,"losses":76,"wins":2},"claude-sonnet-5":{"draws":10,"losses":38,"wins":24},"claude-sonnet-5-5":{"draws":8,"losses":52,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":20},"deepseek/deepseek-v4-flash":{"draws":23,"losses":38,"wins":51},"deepseek/deepseek-v4-pro":{"draws":7,"losses":37,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":31,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":37,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":27,"wins":13},"elorian/glimpse":{"draws":0,"losses":1,"wins":9},"fireworks/ember-1":{"draws":16,"losses":35,"wins":21},"gemini-3.1-pro-preview":{"draws":14,"losses":33,"wins":25},"gemini-4-argon":{"draws":1,"losses":27,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":9,"wins":37},"google/gemini-3.5-flash":{"draws":14,"losses":48,"wins":32},"google/gemini-3.5-flash-lite":{"draws":18,"losses":57,"wins":53},"google/gemini-3.6-flash":{"draws":22,"losses":83,"wins":33},"google/gemini-3.8-flash":{"draws":11,"losses":46,"wins":15},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":26},"gpt-4.1":{"draws":3,"losses":11,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":28,"wins":27},"gpt-5.4":{"draws":9,"losses":42,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":25},"gpt-5.4-nano":{"draws":6,"losses":26,"wins":28},"gpt-5.5":{"draws":15,"losses":32,"wins":19},"gpt-5.6-luna":{"draws":13,"losses":30,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":56,"wins":10},"gpt-5.6-terra":{"draws":9,"losses":35,"wins":24},"gpt-6-astra":{"draws":0,"losses":70,"wins":2},"gpt-6-luna":{"draws":14,"losses":30,"wins":28},"gpt-6-sol":{"draws":12,"losses":56,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":67,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":33},"inception/mercury-3":{"draws":8,"losses":12,"wins":6},"inclusionai/ling-3.0-flash":{"draws":13,"losses":18,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":23,"wins":50},"meta/muse-glimmer-30b":{"draws":13,"losses":23,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":32,"wins":26},"meta/muse-spark-1.3":{"draws":14,"losses":38,"wins":20},"meta/muse-spark-open":{"draws":2,"losses":26,"wins":8},"meta/muse-wonder":{"draws":7,"losses":55,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":15,"wins":19},"minimax/minimax-m3.1-flash":{"draws":8,"losses":14,"wins":22},"mistralai/mistral-large-4-0":{"draws":8,"losses":23,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":8},"moonshotai/kimi-k3":{"draws":16,"losses":31,"wins":21},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":25,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":10,"wins":8},"o3":{"draws":8,"losses":45,"wins":65},"openai/gpt-oss-120b":{"draws":11,"losses":23,"wins":28},"poolside/laguna-s-2.1":{"draws":10,"losses":28,"wins":30},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":20},"qwen/qwen3.7-plus":{"draws":9,"losses":14,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":39,"wins":15},"qwen/qwen3.8-27b":{"draws":7,"losses":24,"wins":21},"qwen/qwen3.8-flash":{"draws":11,"losses":21,"wins":16},"qwen/qwen3.8-max":{"draws":18,"losses":37,"wins":17},"qwen/qwen3.8-max-0902":{"draws":15,"losses":37,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":19,"wins":11},"stealth/ox-alpha":{"draws":34,"losses":100,"wins":68},"stealth/space-bunny-alpha":{"draws":13,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":34},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":16},"tencent/hy4-preview":{"draws":9,"losses":41,"wins":20},"thinkingmachines/inkling":{"draws":17,"losses":29,"wins":48},"thinkingmachines/inkling-small":{"draws":23,"losses":18,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":7,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":14,"losses":37,"wins":21},"x-ai/grok-4.6":{"draws":9,"losses":51,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":51,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":13},"xiaomi/mimo-v2.5":{"draws":25,"losses":35,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":17,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":25,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":31,"wins":11},"z-ai/glm-5.2":{"draws":29,"losses":55,"wins":60},"z-ai/glm-5.3":{"draws":7,"losses":47,"wins":14},"z-ai/glm-5.3-flash":{"draws":10,"losses":39,"wins":23},"z-ai/glm-5.3-flashx":{"draws":12,"losses":40,"wins":20}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":9,"wins":16},"claude-fable-5":{"draws":11,"losses":24,"wins":13},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":20,"losses":19,"wins":7},"claude-opus-4-5":{"draws":37,"losses":17,"wins":24},"claude-opus-4-8":{"draws":13,"losses":12,"wins":19},"claude-opus-5":{"draws":12,"losses":57,"wins":13},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":20,"losses":8,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":26,"losses":11,"wins":35},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":10,"wins":7},"elorian/glimpse":{"draws":1,"losses":6,"wins":7},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"gemini-4-argon":{"draws":1,"losses":22,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":18,"losses":17,"wins":25},"google/gemini-3.5-flash-lite":{"draws":34,"losses":15,"wins":35},"google/gemini-3.6-flash":{"draws":26,"losses":34,"wins":32},"google/gemini-3.8-flash":{"draws":15,"losses":20,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":10,"wins":18},"gpt-5.4":{"draws":14,"losses":17,"wins":15},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":18,"wins":17},"gpt-5.5":{"draws":11,"losses":8,"wins":9},"gpt-5.6-luna":{"draws":19,"losses":7,"wins":22},"gpt-5.6-sol":{"draws":11,"losses":21,"wins":16},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":18},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":21,"losses":9,"wins":18},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":14},"inception/mercury-3":{"draws":9,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":18,"losses":10,"wins":24},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":17,"wins":19},"meta/muse-spark-open":{"draws":9,"losses":9,"wins":6},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":15},"minimax/minimax-m3.1-flash":{"draws":7,"losses":5,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":4,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":4,"wins":5},"o3":{"draws":14,"losses":19,"wins":33},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":13,"losses":9,"wins":12},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max-0902":{"draws":19,"losses":14,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":4,"wins":13},"stealth/ox-alpha":{"draws":45,"losses":66,"wins":47},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":13},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":15,"wins":29},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":20},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":5,"wins":6},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":14,"losses":21,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":9,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":30,"losses":12,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":7,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":40,"losses":18,"wins":38},"z-ai/glm-5.3":{"draws":15,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":14,"losses":20,"wins":14}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":14,"wins":15},"claude-fable-5":{"draws":12,"losses":33,"wins":3},"claude-fable-5-1":{"draws":5,"losses":49,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":28,"losses":29,"wins":21},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":9,"losses":62,"wins":11},"claude-opus-5-5":{"draws":6,"losses":46,"wins":0},"claude-sonnet-5":{"draws":19,"losses":18,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":29},"deepseek/deepseek-v4-pro":{"draws":16,"losses":17,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":15,"wins":0},"elorian/glimpse":{"draws":4,"losses":9,"wins":5},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":16,"losses":17,"wins":15},"gemini-4-argon":{"draws":3,"losses":14,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":18,"losses":28,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":18,"wins":36},"google/gemini-3.6-flash":{"draws":30,"losses":44,"wins":18},"google/gemini-3.8-flash":{"draws":12,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":17,"wins":10},"gpt-5.4":{"draws":14,"losses":24,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":22},"gpt-5.5":{"draws":18,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":14,"losses":8,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":15},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":18,"losses":18,"wins":12},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":3,"wins":12},"inception/mercury-3":{"draws":5,"losses":9,"wins":8},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":11,"wins":24},"meta/muse-glimmer-30b":{"draws":19,"losses":6,"wins":17},"meta/muse-spark-1.2":{"draws":13,"losses":21,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":26,"wins":10},"meta/muse-spark-open":{"draws":6,"losses":11,"wins":3},"meta/muse-wonder":{"draws":9,"losses":34,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":3,"wins":13},"minimax/minimax-m3.1-flash":{"draws":7,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":2},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":3},"o3":{"draws":15,"losses":22,"wins":29},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":18},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":24,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":9,"losses":11,"wins":12},"qwen/qwen3.8-max":{"draws":18,"losses":21,"wins":9},"qwen/qwen3.8-max-0902":{"draws":19,"losses":21,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":12,"wins":6},"stealth/ox-alpha":{"draws":53,"losses":71,"wins":34},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":27,"wins":6},"thinkingmachines/inkling":{"draws":20,"losses":13,"wins":31},"thinkingmachines/inkling-small":{"draws":21,"losses":8,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":26,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":28,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":9,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":21,"wins":6},"z-ai/glm-5.2":{"draws":33,"losses":34,"wins":29},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":22,"wins":10}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":30},"claude-fable-5":{"draws":6,"losses":24,"wins":18},"claude-fable-5-1":{"draws":5,"losses":48,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":17,"losses":14,"wins":47},"claude-opus-4-8":{"draws":3,"losses":17,"wins":24},"claude-opus-5":{"draws":12,"losses":53,"wins":17},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":7,"wins":10},"elorian/glimpse":{"draws":0,"losses":3,"wins":5},"fireworks/ember-1":{"draws":7,"losses":12,"wins":29},"gemini-3.1-pro-preview":{"draws":3,"losses":16,"wins":29},"gemini-4-argon":{"draws":3,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":15,"wins":39},"google/gemini-3.5-flash-lite":{"draws":11,"losses":10,"wins":63},"google/gemini-3.6-flash":{"draws":11,"losses":28,"wins":53},"google/gemini-3.8-flash":{"draws":5,"losses":20,"wins":23},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":10,"losses":14,"wins":22},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":25},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":4,"losses":9,"wins":35},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":7,"wins":27},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":3,"losses":1,"wins":12},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":35},"meta/muse-spark-1.2":{"draws":4,"losses":16,"wins":26},"meta/muse-spark-1.3":{"draws":9,"losses":16,"wins":23},"meta/muse-spark-open":{"draws":3,"losses":11,"wins":18},"meta/muse-wonder":{"draws":10,"losses":22,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"minimax/minimax-m3.1-flash":{"draws":3,"losses":4,"wins":21},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":1,"losses":3,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":11,"losses":11,"wins":24},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":10},"o3":{"draws":7,"losses":10,"wins":49},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":37},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":29},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":22},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":20},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":24},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":10},"stealth/ox-alpha":{"draws":25,"losses":38,"wins":95},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":15,"wins":25},"thinkingmachines/inkling":{"draws":8,"losses":8,"wins":48},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":7,"losses":16,"wins":25},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":18},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":7,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":11,"losses":15,"wins":70},"z-ai/glm-5.3":{"draws":10,"losses":15,"wins":21},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":21},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":26}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":11,"wins":21},"claude-fable-5":{"draws":12,"losses":28,"wins":8},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":24,"losses":24,"wins":30},"claude-opus-4-8":{"draws":10,"losses":21,"wins":13},"claude-opus-5":{"draws":8,"losses":69,"wins":5},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":15,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":24,"losses":11,"wins":37},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":14,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":13,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":9,"wins":10},"elorian/glimpse":{"draws":6,"losses":7,"wins":5},"fireworks/ember-1":{"draws":13,"losses":20,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":16,"wins":18},"gemini-4-argon":{"draws":3,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":19,"wins":29},"google/gemini-3.5-flash-lite":{"draws":23,"losses":15,"wins":46},"google/gemini-3.6-flash":{"draws":22,"losses":42,"wins":28},"google/gemini-3.8-flash":{"draws":14,"losses":16,"wins":18},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":9,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":10,"wins":25},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":15,"wins":24},"gpt-5.5":{"draws":14,"losses":18,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":15,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":10},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":6,"losses":37,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":43,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inception/mercury-3":{"draws":5,"losses":3,"wins":6},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":11,"wins":29},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":17,"wins":17},"meta/muse-spark-1.3":{"draws":8,"losses":25,"wins":15},"meta/muse-spark-open":{"draws":6,"losses":6,"wins":8},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":16},"minimax/minimax-m3.1-flash":{"draws":8,"losses":10,"wins":10},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":22,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":7,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":7,"wins":3},"o3":{"draws":12,"losses":24,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":10,"losses":9,"wins":15},"qwen/qwen3.8-flash":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":19,"losses":16,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":3,"wins":6},"stealth/ox-alpha":{"draws":43,"losses":66,"wins":49},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":20,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":14,"losses":9,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":28,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":23,"losses":4,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":38},"z-ai/glm-5.3":{"draws":10,"losses":30,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":22,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":19,"wins":17}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":41},"claude-fable-5":{"draws":3,"losses":7,"wins":38},"claude-fable-5-1":{"draws":6,"losses":19,"wins":29},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":41},"claude-opus-4-5":{"draws":6,"losses":2,"wins":70},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":9,"losses":24,"wins":49},"claude-opus-5-5":{"draws":4,"losses":24,"wins":24},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":6,"losses":9,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":3,"wins":41},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":1,"wins":27},"elorian/glimpse":{"draws":0,"losses":0,"wins":10},"fireworks/ember-1":{"draws":1,"losses":3,"wins":44},"gemini-3.1-pro-preview":{"draws":5,"losses":2,"wins":41},"gemini-4-argon":{"draws":1,"losses":5,"wins":14},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":53},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":82},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":80},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":42},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":1,"wins":37},"gpt-5.4":{"draws":1,"losses":6,"wins":39},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":47},"gpt-5.5":{"draws":1,"losses":3,"wins":40},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":42},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":37},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":42},"gpt-6-astra":{"draws":4,"losses":21,"wins":7},"gpt-6-luna":{"draws":4,"losses":5,"wins":39},"gpt-6-sol":{"draws":6,"losses":7,"wins":35},"gpt-6.1-sol":{"draws":7,"losses":19,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":1,"losses":0,"wins":17},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":49},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":39},"meta/muse-spark-1.2":{"draws":3,"losses":1,"wins":42},"meta/muse-spark-1.3":{"draws":7,"losses":4,"wins":37},"meta/muse-spark-open":{"draws":1,"losses":1,"wins":20},"meta/muse-wonder":{"draws":3,"losses":6,"wins":39},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":39},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":16},"o3":{"draws":3,"losses":1,"wins":62},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":45},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":33},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":28},"qwen/qwen3.8-max":{"draws":5,"losses":0,"wins":43},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":24},"stealth/ox-alpha":{"draws":11,"losses":8,"wins":139},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":2,"losses":1,"wins":43},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":60},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"draws":1,"losses":3,"wins":2},"unbiased/pareto-26.10-preview":{"draws":3,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":5,"wins":40},"x-ai/grok-4.6":{"draws":4,"losses":6,"wins":38},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":29},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":71},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":5,"losses":3,"wins":38},"z-ai/glm-5.3-flash":{"draws":2,"losses":2,"wins":44},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":41}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":23,"wins":9},"claude-opus-4-5":{"draws":31,"losses":33,"wins":14},"claude-opus-4-8":{"draws":11,"losses":22,"wins":11},"claude-opus-5":{"draws":19,"losses":57,"wins":6},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":14,"losses":22,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":32,"losses":13,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":17,"wins":3},"elorian/glimpse":{"draws":3,"losses":4,"wins":5},"fireworks/ember-1":{"draws":17,"losses":21,"wins":10},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"gemini-4-argon":{"draws":0,"losses":27,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":18,"losses":26,"wins":16},"google/gemini-3.5-flash-lite":{"draws":27,"losses":26,"wins":31},"google/gemini-3.6-flash":{"draws":28,"losses":51,"wins":13},"google/gemini-3.8-flash":{"draws":19,"losses":22,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":17,"losses":15,"wins":10},"gpt-5.4":{"draws":15,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":14,"wins":20},"gpt-5.5":{"draws":22,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":18},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":9,"losses":13,"wins":10},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":5,"wins":11},"inception/mercury-3":{"draws":4,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":13,"wins":26},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":17},"meta/muse-spark-1.2":{"draws":15,"losses":22,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":11},"meta/muse-spark-open":{"draws":8,"losses":11,"wins":5},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":3,"losses":13,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":16,"wins":10},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":3},"o3":{"draws":15,"losses":20,"wins":31},"openai/gpt-oss-120b":{"draws":14,"losses":12,"wins":16},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":11,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":11,"wins":6},"stealth/ox-alpha":{"draws":38,"losses":76,"wins":44},"stealth/space-bunny-alpha":{"draws":15,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":31,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":27,"wins":7},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":34},"claude-fable-5":{"draws":8,"losses":11,"wins":29},"claude-fable-5-1":{"draws":8,"losses":36,"wins":10},"claude-haiku-5-5":{"draws":13,"losses":5,"wins":28},"claude-opus-4-5":{"draws":18,"losses":4,"wins":56},"claude-opus-4-8":{"draws":10,"losses":7,"wins":27},"claude-opus-5":{"draws":10,"losses":36,"wins":36},"claude-opus-5-5":{"draws":7,"losses":33,"wins":12},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":4,"losses":17,"wins":27},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":3,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":5,"wins":22},"elorian/glimpse":{"draws":1,"losses":3,"wins":6},"fireworks/ember-1":{"draws":7,"losses":5,"wins":36},"gemini-3.1-pro-preview":{"draws":3,"losses":6,"wins":39},"gemini-4-argon":{"draws":3,"losses":10,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":11,"losses":3,"wins":46},"google/gemini-3.5-flash-lite":{"draws":23,"losses":4,"wins":57},"google/gemini-3.6-flash":{"draws":12,"losses":17,"wins":63},"google/gemini-3.8-flash":{"draws":9,"losses":7,"wins":32},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":32},"gpt-5.5":{"draws":7,"losses":9,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":34},"gpt-5.6-sol":{"draws":5,"losses":16,"wins":27},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":32},"gpt-6-astra":{"draws":8,"losses":30,"wins":10},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":6,"losses":13,"wins":13},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inception/mercury-3":{"draws":1,"losses":3,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":45},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":6,"losses":9,"wins":31},"meta/muse-spark-1.3":{"draws":11,"losses":6,"wins":31},"meta/muse-spark-open":{"draws":3,"losses":2,"wins":21},"meta/muse-wonder":{"draws":4,"losses":16,"wins":28},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":8,"losses":7,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":7},"o3":{"draws":6,"losses":4,"wins":56},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":35},"poolside/laguna-s-2.1":{"draws":11,"losses":2,"wins":33},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":19},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":9,"wins":34},"qwen/qwen3.8-27b":{"draws":9,"losses":4,"wins":21},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-max":{"draws":5,"losses":8,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":8,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":4,"wins":15},"stealth/ox-alpha":{"draws":23,"losses":20,"wins":115},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":6,"wins":33},"thinkingmachines/inkling":{"draws":9,"losses":4,"wins":51},"thinkingmachines/inkling-small":{"draws":7,"losses":1,"wins":40},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":33},"x-ai/grok-4.6":{"draws":7,"losses":9,"wins":32},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":15},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":16,"losses":6,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":14,"wins":25},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":32},"z-ai/glm-5.3-flashx":{"draws":7,"losses":10,"wins":31}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":38},"claude-fable-5":{"draws":4,"losses":9,"wins":35},"claude-fable-5-1":{"draws":3,"losses":21,"wins":30},"claude-haiku-5-5":{"draws":5,"losses":4,"wins":37},"claude-opus-4-5":{"draws":2,"losses":5,"wins":71},"claude-opus-4-8":{"draws":2,"losses":5,"wins":37},"claude-opus-5":{"draws":12,"losses":26,"wins":44},"claude-opus-5-5":{"draws":3,"losses":28,"wins":21},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":1,"losses":12,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":5,"wins":15},"elorian/glimpse":{"draws":1,"losses":2,"wins":13},"fireworks/ember-1":{"draws":0,"losses":8,"wins":40},"gemini-3.1-pro-preview":{"draws":4,"losses":3,"wins":41},"gemini-4-argon":{"draws":1,"losses":7,"wins":14},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":51},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":7,"wins":79},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":38},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":2,"losses":4,"wins":40},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":45},"gpt-5.5":{"draws":1,"losses":6,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":41},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":41},"gpt-6-astra":{"draws":5,"losses":26,"wins":17},"gpt-6-luna":{"draws":1,"losses":1,"wins":46},"gpt-6-sol":{"draws":5,"losses":10,"wins":33},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inception/mercury-3":{"draws":0,"losses":1,"wins":11},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":5,"losses":5,"wins":38},"meta/muse-spark-open":{"draws":0,"losses":2,"wins":14},"meta/muse-wonder":{"draws":7,"losses":11,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":1,"losses":0,"wins":21},"mistralai/mistral-large-4-0":{"draws":3,"losses":4,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":38},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":12},"o3":{"draws":1,"losses":0,"wins":65},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":41},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":24},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":38},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":3,"wins":29},"qwen/qwen3.8-max":{"draws":5,"losses":4,"wins":39},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":45},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":2,"wins":26},"stealth/ox-alpha":{"draws":14,"losses":8,"wins":136},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":44},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":61},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10":{"draws":2,"losses":4,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":42},"x-ai/grok-4.6":{"draws":3,"losses":5,"wins":40},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":21},"z-ai/glm-5.2":{"draws":11,"losses":5,"wins":80},"z-ai/glm-5.3":{"draws":8,"losses":7,"wins":31},"z-ai/glm-5.3-flash":{"draws":5,"losses":5,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":38}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"elorian/glimpse":{"draws":2,"losses":0,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":1,"losses":3,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inception/mercury-3":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":1},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":2},"meta/muse-spark-open":{"draws":1,"losses":1,"wins":0},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":9,"losses":8,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":1,"losses":1,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":0},"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":12,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":7},"claude-fable-5":{"draws":8,"losses":28,"wins":0},"claude-fable-5-1":{"draws":4,"losses":36,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":25,"wins":1},"claude-opus-4-5":{"draws":21,"losses":38,"wins":1},"claude-opus-4-8":{"draws":11,"losses":24,"wins":1},"claude-opus-5":{"draws":7,"losses":49,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":25,"losses":21,"wins":8},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":9,"wins":1},"elorian/glimpse":{"draws":1,"losses":6,"wins":1},"fireworks/ember-1":{"draws":16,"losses":20,"wins":0},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":4},"gemini-4-argon":{"draws":0,"losses":12,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":15,"losses":26,"wins":5},"google/gemini-3.5-flash-lite":{"draws":27,"losses":29,"wins":8},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":2},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":2},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":16,"wins":2},"gpt-5.4":{"draws":14,"losses":20,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":3},"gpt-5.5":{"draws":14,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":5},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":0},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":5,"losses":30,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":6},"inception/mercury-3":{"draws":4,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":16,"wins":11},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":25,"wins":1},"meta/muse-spark-open":{"draws":4,"losses":12,"wins":2},"meta/muse-wonder":{"draws":10,"losses":25,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":2},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":1},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":0},"o3":{"draws":15,"losses":34,"wins":3},"openai/gpt-oss-120b":{"draws":15,"losses":14,"wins":3},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":1},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":2},"qwen/qwen3.8-max-0902":{"draws":15,"losses":16,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":14,"wins":0},"stealth/ox-alpha":{"draws":33,"losses":65,"wins":4},"stealth/space-bunny-alpha":{"draws":13,"losses":13,"wins":4},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":3},"thinkingmachines/inkling":{"draws":18,"losses":19,"wins":7},"thinkingmachines/inkling-small":{"draws":17,"losses":12,"wins":7},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":29,"losses":25,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":41,"wins":4},"z-ai/glm-5.3":{"draws":12,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":2}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":1},"claude-fable-5":{"draws":0,"losses":3,"wins":1},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-haiku-5-5":{"draws":2,"losses":5,"wins":3},"claude-opus-4-5":{"draws":4,"losses":1,"wins":7},"claude-opus-4-8":{"draws":3,"losses":3,"wins":2},"claude-opus-5":{"draws":1,"losses":8,"wins":1},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":5,"losses":2,"wins":5},"claude-sonnet-5-5":{"draws":0,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":8,"wins":5},"elorian/glimpse":{"draws":2,"losses":3,"wins":3},"fireworks/ember-1":{"draws":4,"losses":2,"wins":6},"gemini-3.1-pro-preview":{"draws":0,"losses":0,"wins":6},"gemini-4-argon":{"draws":1,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":5},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":0,"wins":4},"gpt-5.4":{"draws":2,"losses":3,"wins":9},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":4},"gpt-5.5":{"draws":0,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":7},"gpt-6-astra":{"draws":2,"losses":12,"wins":0},"gpt-6-luna":{"draws":0,"losses":1,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inception/mercury-3":{"draws":3,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":6},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":3,"losses":3,"wins":4},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":6},"meta/muse-spark-open":{"draws":1,"losses":9,"wins":6},"meta/muse-wonder":{"draws":4,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":5},"minimax/minimax-m3.1-flash":{"draws":2,"losses":1,"wins":9},"mistralai/mistral-large-4-0":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":5},"o3":{"draws":1,"losses":2,"wins":7},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"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":2,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-max-0902":{"draws":4,"losses":0,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":6,"losses":10,"wins":10},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":1,"losses":6,"wins":3},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":6},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":3},"unbiased/pareto-26.10":{"draws":0,"losses":3,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":5,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":1},"x-ai/grok-4.6":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":8,"losses":2,"wins":6},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":0}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":6},"claude-fable-5":{"draws":4,"losses":31,"wins":1},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":1},"claude-opus-4-5":{"draws":24,"losses":24,"wins":12},"claude-opus-4-8":{"draws":10,"losses":26,"wins":0},"claude-opus-5":{"draws":9,"losses":43,"wins":2},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":4},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":20,"wins":18},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":12,"wins":1},"elorian/glimpse":{"draws":6,"losses":4,"wins":4},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":5},"gemini-4-argon":{"draws":1,"losses":16,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":11,"losses":28,"wins":7},"google/gemini-3.5-flash-lite":{"draws":17,"losses":32,"wins":13},"google/gemini-3.6-flash":{"draws":22,"losses":40,"wins":8},"google/gemini-3.8-flash":{"draws":9,"losses":26,"wins":1},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":8},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":16,"wins":4},"gpt-5.4":{"draws":7,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":14},"gpt-5.5":{"draws":10,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":23,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":9,"losses":21,"wins":6},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":11},"inception/mercury-3":{"draws":6,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":7,"wins":5},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":10,"wins":6},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":6},"meta/muse-spark-1.3":{"draws":1,"losses":30,"wins":5},"meta/muse-spark-open":{"draws":3,"losses":10,"wins":1},"meta/muse-wonder":{"draws":9,"losses":27,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":14,"wins":1},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":2},"o3":{"draws":4,"losses":37,"wins":11},"openai/gpt-oss-120b":{"draws":9,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":7,"losses":15,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":21,"losses":66,"wins":15},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":16,"wins":7},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":10},"thinkingmachines/inkling-small":{"draws":13,"losses":15,"wins":8},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":9,"losses":24,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":26,"losses":20,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":35,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":2},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":29,"wins":19},"claude-fable-5":{"draws":10,"losses":51,"wins":11},"claude-fable-5-1":{"draws":5,"losses":73,"wins":3},"claude-haiku-5-5":{"draws":15,"losses":44,"wins":11},"claude-opus-4-5":{"draws":29,"losses":71,"wins":18},"claude-opus-4-8":{"draws":17,"losses":40,"wins":11},"claude-opus-5":{"draws":12,"losses":91,"wins":13},"claude-opus-5-5":{"draws":5,"losses":71,"wins":4},"claude-sonnet-5":{"draws":17,"losses":43,"wins":12},"claude-sonnet-5-5":{"draws":8,"losses":47,"wins":17},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":33,"losses":41,"wins":32},"deepseek/deepseek-v4-pro":{"draws":14,"losses":38,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":34,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":41,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":25,"wins":10},"elorian/glimpse":{"draws":5,"losses":5,"wins":4},"fireworks/ember-1":{"draws":15,"losses":41,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":35,"wins":24},"gemini-4-argon":{"draws":2,"losses":29,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":13,"wins":31},"google/gemini-3.5-flash":{"draws":18,"losses":56,"wins":18},"google/gemini-3.5-flash-lite":{"draws":28,"losses":52,"wins":50},"google/gemini-3.6-flash":{"draws":30,"losses":87,"wins":21},"google/gemini-3.8-flash":{"draws":15,"losses":45,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":15,"wins":18},"gpt-4.1":{"draws":10,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":19,"losses":32,"wins":11},"gpt-5.4":{"draws":13,"losses":42,"wins":15},"gpt-5.4-mini":{"draws":14,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":39,"wins":22},"gpt-5.5":{"draws":11,"losses":41,"wins":14},"gpt-5.6-luna":{"draws":22,"losses":29,"wins":21},"gpt-5.6-sol":{"draws":11,"losses":53,"wins":8},"gpt-5.6-terra":{"draws":18,"losses":33,"wins":17},"gpt-6-astra":{"draws":3,"losses":67,"wins":2},"gpt-6-luna":{"draws":14,"losses":40,"wins":18},"gpt-6-sol":{"draws":4,"losses":63,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":63,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":12,"wins":23},"inception/mercury-3":{"draws":6,"losses":12,"wins":4},"inclusionai/ling-3.0-flash":{"draws":22,"losses":7,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":18,"wins":25},"meta/muse-glimmer-30b":{"draws":17,"losses":21,"wins":24},"meta/muse-spark-1.2":{"draws":13,"losses":39,"wins":16},"meta/muse-spark-1.3":{"draws":14,"losses":45,"wins":13},"meta/muse-spark-open":{"draws":8,"losses":25,"wins":3},"meta/muse-wonder":{"draws":11,"losses":51,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":12,"wins":18},"minimax/minimax-m3.1-flash":{"draws":12,"losses":13,"wins":13},"mistralai/mistral-large-4-0":{"draws":16,"losses":19,"wins":9},"mistralai/mistral-medium-3-5":{"draws":17,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":9,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":40,"wins":11},"nex-agi/nex-n2-pro":{"draws":7,"losses":13,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":20,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":7,"wins":5},"o3":{"draws":13,"losses":62,"wins":31},"openai/gpt-oss-120b":{"draws":19,"losses":13,"wins":32},"poolside/laguna-s-2.1":{"draws":17,"losses":21,"wins":28},"qwen/qwen3.7-max":{"draws":13,"losses":23,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":42,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":32,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":22,"wins":12},"qwen/qwen3.8-max":{"draws":21,"losses":42,"wins":9},"qwen/qwen3.8-max-0902":{"draws":9,"losses":53,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":13,"wins":9},"stealth/ox-alpha":{"draws":49,"losses":141,"wins":38},"stealth/space-bunny-alpha":{"draws":18,"losses":24,"wins":18},"stepfun/step-3.7-flash":{"draws":10,"losses":27,"wins":13},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":15,"losses":11,"wins":12},"tencent/hy4-preview":{"draws":20,"losses":40,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":34,"wins":33},"thinkingmachines/inkling-small":{"draws":20,"losses":22,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":17,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":7},"x-ai/grok-4.5":{"draws":15,"losses":48,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":46,"wins":12},"x-ai/grok-4.7":{"draws":3,"losses":56,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":8,"wins":7},"xiaomi/mimo-v2.5":{"draws":40,"losses":36,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":26,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":37,"wins":6},"z-ai/glm-5.2":{"draws":37,"losses":72,"wins":35},"z-ai/glm-5.3":{"draws":14,"losses":52,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":47,"wins":14},"z-ai/glm-5.3-flashx":{"draws":18,"losses":46,"wins":8}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":11,"losses":35,"wins":2},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":28,"wins":4},"claude-opus-4-5":{"draws":28,"losses":39,"wins":11},"claude-opus-4-8":{"draws":13,"losses":26,"wins":5},"claude-opus-5":{"draws":5,"losses":68,"wins":9},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":18,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":11,"losses":32,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":33,"losses":28,"wins":11},"deepseek/deepseek-v4-pro":{"draws":14,"losses":23,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":25,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":31,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":20,"wins":2},"elorian/glimpse":{"draws":4,"losses":8,"wins":4},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":20,"losses":23,"wins":5},"gemini-4-argon":{"draws":1,"losses":23,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":20,"losses":33,"wins":7},"google/gemini-3.5-flash-lite":{"draws":39,"losses":31,"wins":14},"google/gemini-3.6-flash":{"draws":29,"losses":56,"wins":7},"google/gemini-3.8-flash":{"draws":12,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":15,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":19,"wins":9},"gpt-5.4":{"draws":11,"losses":29,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":21,"wins":16},"gpt-5.5":{"draws":12,"losses":23,"wins":9},"gpt-5.6-luna":{"draws":19,"losses":20,"wins":9},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":24,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":16,"losses":27,"wins":5},"gpt-6-sol":{"draws":10,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":9,"wins":8},"inception/mercury-3":{"draws":6,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":20,"losses":6,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":18,"wins":16},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":6},"meta/muse-spark-1.2":{"draws":13,"losses":25,"wins":8},"meta/muse-spark-1.3":{"draws":14,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":6,"losses":15,"wins":1},"meta/muse-wonder":{"draws":8,"losses":34,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":7},"minimax/minimax-m3.1-flash":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":27,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":14,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":8,"wins":2},"o3":{"draws":15,"losses":45,"wins":6},"openai/gpt-oss-120b":{"draws":21,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":14,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":11,"losses":8,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":32,"wins":2},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":25,"wins":8},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":16,"wins":0},"stealth/ox-alpha":{"draws":41,"losses":103,"wins":14},"stealth/space-bunny-alpha":{"draws":14,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":13,"losses":31,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":18},"thinkingmachines/inkling-small":{"draws":21,"losses":13,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":34,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":38,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":31,"losses":23,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":16,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":41,"losses":40,"wins":15},"z-ai/glm-5.3":{"draws":9,"losses":33,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":15,"losses":29,"wins":4}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":21},"claude-fable-5":{"draws":7,"losses":23,"wins":12},"claude-fable-5-1":{"draws":2,"losses":40,"wins":6},"claude-haiku-5-5":{"draws":8,"losses":16,"wins":16},"claude-opus-4-5":{"draws":20,"losses":10,"wins":38},"claude-opus-4-8":{"draws":10,"losses":12,"wins":16},"claude-opus-5":{"draws":10,"losses":54,"wins":16},"claude-opus-5-5":{"draws":5,"losses":37,"wins":4},"claude-sonnet-5":{"draws":12,"losses":10,"wins":20},"claude-sonnet-5-5":{"draws":13,"losses":17,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":18,"losses":4,"wins":40},"deepseek/deepseek-v4-pro":{"draws":7,"losses":14,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":9,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":11,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":10,"wins":9},"elorian/glimpse":{"draws":1,"losses":0,"wins":9},"fireworks/ember-1":{"draws":11,"losses":13,"wins":18},"gemini-3.1-pro-preview":{"draws":10,"losses":11,"wins":21},"gemini-4-argon":{"draws":3,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":11,"losses":12,"wins":29},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":46},"google/gemini-3.6-flash":{"draws":11,"losses":26,"wins":43},"google/gemini-3.8-flash":{"draws":7,"losses":11,"wins":24},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":4,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":9,"losses":8,"wins":21},"gpt-5.4":{"draws":9,"losses":16,"wins":15},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":24},"gpt-5.5":{"draws":8,"losses":15,"wins":17},"gpt-5.6-luna":{"draws":13,"losses":6,"wins":23},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":14},"gpt-5.6-terra":{"draws":15,"losses":8,"wins":17},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":12,"losses":7,"wins":23},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-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":12,"losses":2,"wins":14},"inception/mercury-3":{"draws":9,"losses":3,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":28},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":28},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":13},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":21},"meta/muse-spark-open":{"draws":4,"losses":9,"wins":7},"meta/muse-wonder":{"draws":8,"losses":18,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":5,"losses":4,"wins":11},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":19},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":7},"o3":{"draws":8,"losses":14,"wins":32},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":25},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":16},"qwen/qwen3.8-max-0902":{"draws":13,"losses":13,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":3,"wins":7},"stealth/ox-alpha":{"draws":38,"losses":62,"wins":42},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":16,"wins":16},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":13,"losses":4,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":19,"wins":12},"x-ai/grok-4.6":{"draws":10,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":16,"losses":4,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":15,"losses":19,"wins":50},"z-ai/glm-5.3":{"draws":7,"losses":21,"wins":12},"z-ai/glm-5.3-flash":{"draws":6,"losses":15,"wins":21},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":6,"wins":31},"claude-fable-5":{"draws":8,"losses":22,"wins":18},"claude-fable-5-1":{"draws":5,"losses":41,"wins":8},"claude-haiku-5-5":{"draws":4,"losses":19,"wins":23},"claude-opus-4-5":{"draws":13,"losses":13,"wins":52},"claude-opus-4-8":{"draws":7,"losses":14,"wins":23},"claude-opus-5":{"draws":8,"losses":51,"wins":23},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":12,"losses":8,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":57},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":17,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":9,"wins":19},"elorian/glimpse":{"draws":7,"losses":3,"wins":10},"fireworks/ember-1":{"draws":11,"losses":14,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"gemini-4-argon":{"draws":6,"losses":21,"wins":3},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":43},"google/gemini-3.5-flash-lite":{"draws":13,"losses":8,"wins":63},"google/gemini-3.6-flash":{"draws":18,"losses":26,"wins":48},"google/gemini-3.8-flash":{"draws":10,"losses":14,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":19},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":7,"losses":5,"wins":30},"gpt-5.4":{"draws":8,"losses":15,"wins":23},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":35},"gpt-5.5":{"draws":9,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":6,"losses":38,"wins":4},"gpt-6-luna":{"draws":5,"losses":10,"wins":33},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":35,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"inception/mercury-3":{"draws":5,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":8,"losses":16,"wins":22},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":14},"meta/muse-spark-open":{"draws":2,"losses":4,"wins":12},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":4,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":29},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":9},"o3":{"draws":5,"losses":11,"wins":50},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":30},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":7,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":23},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":8,"losses":12,"wins":28},"qwen/qwen3.8-max-0902":{"draws":9,"losses":14,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":2,"wins":14},"stealth/ox-alpha":{"draws":28,"losses":48,"wins":82},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":19},"tencent/hy4-preview":{"draws":8,"losses":12,"wins":26},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":52},"thinkingmachines/inkling-small":{"draws":8,"losses":4,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":28},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":20},"x-ai/grok-4.7":{"draws":2,"losses":28,"wins":12},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":12,"losses":1,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":18,"losses":15,"wins":63},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":7,"wins":15},"claude-fable-5":{"draws":4,"losses":10,"wins":6},"claude-fable-5-1":{"draws":2,"losses":25,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":1,"wins":11},"claude-opus-4-5":{"draws":13,"losses":8,"wins":11},"claude-opus-4-8":{"draws":10,"losses":9,"wins":7},"claude-opus-5":{"draws":7,"losses":43,"wins":2},"claude-opus-5-5":{"draws":1,"losses":22,"wins":1},"claude-sonnet-5":{"draws":9,"losses":2,"wins":11},"claude-sonnet-5-5":{"draws":6,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":9,"losses":5,"wins":18},"deepseek/deepseek-v4-pro":{"draws":11,"losses":7,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":8,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":9,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":21,"wins":13},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":5,"losses":12,"wins":3},"gemini-3.1-pro-preview":{"draws":5,"losses":7,"wins":6},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":10},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":27},"google/gemini-3.6-flash":{"draws":10,"losses":9,"wins":17},"google/gemini-3.8-flash":{"draws":3,"losses":14,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1":{"draws":1,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":4,"wins":9},"gpt-5.4":{"draws":6,"losses":5,"wins":11},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":6},"gpt-5.4-nano":{"draws":0,"losses":5,"wins":21},"gpt-5.5":{"draws":7,"losses":6,"wins":9},"gpt-5.6-luna":{"draws":11,"losses":11,"wins":10},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":5},"gpt-6-astra":{"draws":3,"losses":19,"wins":0},"gpt-6-luna":{"draws":8,"losses":3,"wins":3},"gpt-6-sol":{"draws":4,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":20,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":6},"inception/mercury-3":{"draws":6,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":9},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":16},"meta/muse-glimmer-30b":{"draws":8,"losses":5,"wins":11},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":8},"meta/muse-spark-1.3":{"draws":6,"losses":9,"wins":3},"meta/muse-spark-open":{"draws":6,"losses":14,"wins":8},"meta/muse-wonder":{"draws":3,"losses":10,"wins":7},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":3},"minimax/minimax-m3.1-flash":{"draws":7,"losses":10,"wins":23},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":8,"wins":11},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":7,"wins":10},"o3":{"draws":8,"losses":9,"wins":23},"openai/gpt-oss-120b":{"draws":1,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":9,"losses":4,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":10,"wins":9},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":4,"losses":8,"wins":10},"qwen/qwen3.8-max-0902":{"draws":6,"losses":11,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":12,"wins":19},"stealth/ox-alpha":{"draws":15,"losses":26,"wins":23},"stealth/space-bunny-alpha":{"draws":5,"losses":7,"wins":8},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":6,"wins":11},"thinkingmachines/inkling":{"draws":11,"losses":2,"wins":15},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":10},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":5,"losses":18,"wins":7},"x-ai/grok-4.6":{"draws":4,"losses":5,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":13,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":17,"losses":0,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":15,"wins":23},"z-ai/glm-5.3":{"draws":6,"losses":8,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":9,"wins":13},"z-ai/glm-5.3-flashx":{"draws":7,"losses":14,"wins":11}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":28},"claude-fable-5":{"draws":9,"losses":16,"wins":23},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":8,"losses":11,"wins":27},"claude-opus-4-5":{"draws":11,"losses":22,"wins":45},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":7,"losses":53,"wins":22},"claude-opus-5-5":{"draws":5,"losses":37,"wins":10},"claude-sonnet-5":{"draws":8,"losses":13,"wins":27},"claude-sonnet-5-5":{"draws":6,"losses":23,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":48},"deepseek/deepseek-v4-pro":{"draws":7,"losses":12,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":10,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":11,"wins":11},"elorian/glimpse":{"draws":4,"losses":3,"wins":7},"fireworks/ember-1":{"draws":8,"losses":15,"wins":25},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":36},"gemini-4-argon":{"draws":2,"losses":20,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":15,"losses":10,"wins":59},"google/gemini-3.6-flash":{"draws":16,"losses":29,"wins":47},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":28},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":24},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":19},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":36},"gpt-5.5":{"draws":11,"losses":14,"wins":19},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":30},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":21},"gpt-5.6-terra":{"draws":3,"losses":16,"wins":27},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":9,"losses":14,"wins":25},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":33,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inception/mercury-3":{"draws":3,"losses":3,"wins":10},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":33},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":28},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":15,"wins":24},"meta/muse-spark-open":{"draws":4,"losses":7,"wins":13},"meta/muse-wonder":{"draws":5,"losses":13,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":18},"minimax/minimax-m3.1-flash":{"draws":4,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":26},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":7},"o3":{"draws":2,"losses":14,"wins":50},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":30},"poolside/laguna-s-2.1":{"draws":5,"losses":5,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":23},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":10},"stealth/ox-alpha":{"draws":29,"losses":47,"wins":82},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":20},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":8,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":42},"thinkingmachines/inkling-small":{"draws":11,"losses":6,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":28},"x-ai/grok-4.6":{"draws":11,"losses":15,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":24,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":15,"wins":14},"z-ai/glm-5.2":{"draws":23,"losses":15,"wins":58},"z-ai/glm-5.3":{"draws":9,"losses":17,"wins":20},"z-ai/glm-5.3-flash":{"draws":8,"losses":12,"wins":28},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":15,"wins":7},"claude-fable-5":{"draws":11,"losses":30,"wins":1},"claude-fable-5-1":{"draws":1,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":31,"wins":5},"claude-opus-4-5":{"draws":21,"losses":46,"wins":3},"claude-opus-4-8":{"draws":12,"losses":28,"wins":2},"claude-opus-5":{"draws":6,"losses":61,"wins":3},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":13,"losses":25,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":33,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":23,"losses":25,"wins":16},"deepseek/deepseek-v4-pro":{"draws":9,"losses":28,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":26,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":18,"wins":0},"elorian/glimpse":{"draws":4,"losses":8,"wins":4},"fireworks/ember-1":{"draws":12,"losses":29,"wins":1},"gemini-3.1-pro-preview":{"draws":13,"losses":22,"wins":7},"gemini-4-argon":{"draws":0,"losses":24,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":15,"wins":8},"google/gemini-3.5-flash":{"draws":17,"losses":30,"wins":7},"google/gemini-3.5-flash-lite":{"draws":21,"losses":36,"wins":17},"google/gemini-3.6-flash":{"draws":21,"losses":49,"wins":10},"google/gemini-3.8-flash":{"draws":12,"losses":27,"wins":3},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":20,"wins":6},"gpt-5.4":{"draws":11,"losses":26,"wins":3},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":27,"wins":8},"gpt-5.5":{"draws":16,"losses":19,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":2},"gpt-5.6-terra":{"draws":13,"losses":24,"wins":3},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":13,"losses":24,"wins":5},"gpt-6-sol":{"draws":7,"losses":33,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":8,"wins":8},"inception/mercury-3":{"draws":5,"losses":13,"wins":0},"inclusionai/ling-3.0-flash":{"draws":15,"losses":7,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":24,"wins":12},"meta/muse-glimmer-30b":{"draws":16,"losses":14,"wins":6},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":2},"meta/muse-spark-open":{"draws":9,"losses":12,"wins":1},"meta/muse-wonder":{"draws":8,"losses":30,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":2},"minimax/minimax-m3.1-flash":{"draws":6,"losses":15,"wins":3},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":10,"losses":9,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":24,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":16,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":9,"wins":1},"o3":{"draws":9,"losses":42,"wins":11},"openai/gpt-oss-120b":{"draws":14,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":16,"losses":18,"wins":4},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":11,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":27,"wins":2},"qwen/qwen3.8-27b":{"draws":7,"losses":20,"wins":3},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":13,"wins":2},"stealth/ox-alpha":{"draws":26,"losses":83,"wins":9},"stealth/space-bunny-alpha":{"draws":11,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":12,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":12,"wins":1},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":2},"thinkingmachines/inkling":{"draws":14,"losses":31,"wins":9},"thinkingmachines/inkling-small":{"draws":17,"losses":12,"wins":13},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":31,"wins":2},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":25,"losses":30,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":13,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":1},"z-ai/glm-5.2":{"draws":30,"losses":47,"wins":7},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":9,"losses":28,"wins":5},"z-ai/glm-5.3-flashx":{"draws":14,"losses":26,"wins":2}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":10,"wins":15},"claude-fable-5":{"draws":3,"losses":15,"wins":4},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":11,"wins":7},"claude-opus-4-5":{"draws":11,"losses":21,"wins":16},"claude-opus-4-8":{"draws":5,"losses":9,"wins":8},"claude-opus-5":{"draws":2,"losses":33,"wins":5},"claude-opus-5-5":{"draws":1,"losses":19,"wins":0},"claude-sonnet-5":{"draws":4,"losses":12,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":18,"wins":24},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":5,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":11,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":27,"wins":6},"elorian/glimpse":{"draws":3,"losses":15,"wins":6},"fireworks/ember-1":{"draws":8,"losses":8,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":11,"wins":7},"gemini-4-argon":{"draws":4,"losses":34,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":5,"losses":15,"wins":14},"google/gemini-3.5-flash-lite":{"draws":12,"losses":7,"wins":15},"google/gemini-3.6-flash":{"draws":15,"losses":21,"wins":20},"google/gemini-3.8-flash":{"draws":7,"losses":15,"wins":8},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-4.1":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":3,"losses":8,"wins":9},"gpt-5.4":{"draws":4,"losses":19,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":15},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":12},"gpt-5.5":{"draws":10,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":5,"losses":8,"wins":11},"gpt-5.6-sol":{"draws":3,"losses":18,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":4},"gpt-6-astra":{"draws":3,"losses":21,"wins":0},"gpt-6-luna":{"draws":5,"losses":5,"wins":8},"gpt-6-sol":{"draws":3,"losses":19,"wins":0},"gpt-6.1-sol":{"draws":4,"losses":19,"wins":1},"inception/mercury-2.5-preview":{"draws":5,"losses":3,"wins":12},"inception/mercury-3":{"draws":5,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":12},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":7,"wins":15},"meta/muse-glimmer-30b":{"draws":4,"losses":6,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":10,"wins":9},"meta/muse-spark-1.3":{"draws":4,"losses":17,"wins":9},"meta/muse-spark-open":{"draws":5,"losses":21,"wins":14},"meta/muse-wonder":{"draws":1,"losses":15,"wins":4},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":1,"losses":8,"wins":11},"mistralai/mistral-large-4-0":{"draws":1,"losses":7,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":5,"losses":16,"wins":17},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":3,"losses":6,"wins":15},"qwen/qwen3.7-max":{"draws":1,"losses":6,"wins":9},"qwen/qwen3.7-plus":{"draws":1,"losses":4,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":4,"wins":5},"qwen/qwen3.8-27b":{"draws":4,"losses":0,"wins":8},"qwen/qwen3.8-flash":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.8-max":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-max-0902":{"draws":2,"losses":12,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":16,"wins":14},"stealth/ox-alpha":{"draws":14,"losses":43,"wins":29},"stealth/space-bunny-alpha":{"draws":3,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":8,"wins":18},"thinkingmachines/inkling-small":{"draws":7,"losses":2,"wins":13},"unbiased/pareto-26.10":{"draws":0,"losses":11,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":7,"losses":17,"wins":4},"x-ai/grok-4.6":{"draws":9,"losses":9,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":9,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":8,"losses":13,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":13,"wins":20},"z-ai/glm-5.3":{"draws":3,"losses":9,"wins":4},"z-ai/glm-5.3-flash":{"draws":1,"losses":13,"wins":14},"z-ai/glm-5.3-flashx":{"draws":4,"losses":14,"wins":8}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":15},"claude-fable-5":{"draws":8,"losses":21,"wins":7},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":16,"losses":29,"wins":15},"claude-opus-4-8":{"draws":10,"losses":19,"wins":7},"claude-opus-5":{"draws":3,"losses":59,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":9,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":18,"wins":2},"elorian/glimpse":{"draws":2,"losses":3,"wins":3},"fireworks/ember-1":{"draws":11,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"gemini-4-argon":{"draws":4,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":14,"wins":33},"google/gemini-3.6-flash":{"draws":19,"losses":33,"wins":16},"google/gemini-3.8-flash":{"draws":6,"losses":13,"wins":17},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":11,"wins":15},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":16},"gpt-5.5":{"draws":13,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":23,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":13,"wins":11},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":14,"wins":10},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":14},"inception/mercury-3":{"draws":6,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":11},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":15},"meta/muse-spark-open":{"draws":2,"losses":15,"wins":5},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":13},"minimax/minimax-m3.1-flash":{"draws":3,"losses":7,"wins":8},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":15},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":4},"o3":{"draws":5,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":8,"wins":5},"stealth/ox-alpha":{"draws":24,"losses":49,"wins":29},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":9,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":28},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":22,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":11,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":16,"losses":26,"wins":30},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":21},"claude-fable-5":{"draws":15,"losses":31,"wins":2},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":23,"wins":11},"claude-opus-4-5":{"draws":29,"losses":25,"wins":24},"claude-opus-4-8":{"draws":13,"losses":18,"wins":13},"claude-opus-5":{"draws":15,"losses":59,"wins":8},"claude-opus-5-5":{"draws":2,"losses":44,"wins":6},"claude-sonnet-5":{"draws":17,"losses":13,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":18,"losses":13,"wins":41},"deepseek/deepseek-v4-pro":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":15,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":18,"wins":6},"elorian/glimpse":{"draws":3,"losses":7,"wins":2},"fireworks/ember-1":{"draws":19,"losses":19,"wins":10},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":1,"losses":19,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":20,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":24,"losses":16,"wins":44},"google/gemini-3.6-flash":{"draws":27,"losses":38,"wins":27},"google/gemini-3.8-flash":{"draws":15,"losses":27,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":14,"wins":15},"gpt-5.4":{"draws":13,"losses":27,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":24},"gpt-5.5":{"draws":18,"losses":15,"wins":11},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":32,"wins":8},"gpt-5.6-terra":{"draws":17,"losses":14,"wins":15},"gpt-6-astra":{"draws":1,"losses":43,"wins":4},"gpt-6-luna":{"draws":18,"losses":15,"wins":15},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":38,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inception/mercury-3":{"draws":10,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":8,"wins":27},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":19,"wins":17},"meta/muse-spark-1.3":{"draws":13,"losses":24,"wins":11},"meta/muse-spark-open":{"draws":5,"losses":15,"wins":4},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":4,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":14,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":3},"o3":{"draws":11,"losses":24,"wins":31},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":24},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":11,"losses":6,"wins":17},"qwen/qwen3.8-flash":{"draws":13,"losses":6,"wins":13},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":19,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":11,"wins":7},"stealth/ox-alpha":{"draws":41,"losses":66,"wins":51},"stealth/space-bunny-alpha":{"draws":16,"losses":7,"wins":15},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":32},"thinkingmachines/inkling-small":{"draws":16,"losses":4,"wins":28},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":12},"x-ai/grok-4.6":{"draws":21,"losses":20,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":29,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":25,"losses":10,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":34,"losses":27,"wins":35},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":17,"losses":22,"wins":9}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":21,"wins":4},"claude-fable-5":{"draws":3,"losses":27,"wins":0},"claude-fable-5-1":{"draws":1,"losses":33,"wins":0},"claude-haiku-5-5":{"draws":1,"losses":24,"wins":3},"claude-opus-4-5":{"draws":3,"losses":42,"wins":3},"claude-opus-4-8":{"draws":3,"losses":23,"wins":0},"claude-opus-5":{"draws":0,"losses":45,"wins":1},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":6,"losses":21,"wins":3},"claude-sonnet-5-5":{"draws":3,"losses":25,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":9,"wins":6},"deepseek/deepseek-v4-flash":{"draws":5,"losses":25,"wins":16},"deepseek/deepseek-v4-pro":{"draws":2,"losses":24,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":23,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":27,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":12,"wins":2},"elorian/glimpse":{"draws":0,"losses":3,"wins":3},"fireworks/ember-1":{"draws":2,"losses":26,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":21,"wins":5},"gemini-4-argon":{"draws":0,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":9,"wins":13},"google/gemini-3.5-flash":{"draws":5,"losses":28,"wins":5},"google/gemini-3.5-flash-lite":{"draws":5,"losses":38,"wins":11},"google/gemini-3.6-flash":{"draws":2,"losses":54,"wins":2},"google/gemini-3.8-flash":{"draws":1,"losses":28,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":4},"gpt-4.1":{"draws":0,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":21,"wins":5},"gpt-5.4":{"draws":4,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":3,"losses":18,"wins":11},"gpt-5.5":{"draws":1,"losses":26,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":21,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":26,"wins":1},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":23,"wins":5},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":10,"wins":8},"inception/mercury-3":{"draws":0,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":11,"wins":7},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":5,"losses":18,"wins":3},"meta/muse-spark-1.2":{"draws":1,"losses":25,"wins":2},"meta/muse-spark-1.3":{"draws":0,"losses":30,"wins":0},"meta/muse-spark-open":{"draws":1,"losses":13,"wins":0},"meta/muse-wonder":{"draws":1,"losses":26,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":11,"wins":4},"minimax/minimax-m3.1-flash":{"draws":3,"losses":14,"wins":3},"mistralai/mistral-large-4-0":{"draws":1,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":12,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":24,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":19,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":3,"wins":1},"o3":{"draws":1,"losses":46,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":14,"wins":10},"poolside/laguna-s-2.1":{"draws":10,"losses":20,"wins":2},"qwen/qwen3.7-max":{"draws":3,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":23,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":14,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":16,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":22,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":24,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":8,"wins":2},"stealth/ox-alpha":{"draws":14,"losses":84,"wins":10},"stealth/space-bunny-alpha":{"draws":3,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":25,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":23,"wins":11},"thinkingmachines/inkling-small":{"draws":4,"losses":19,"wins":7},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":6,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":24,"wins":4},"x-ai/grok-4.6":{"draws":3,"losses":27,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":29,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":14,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":18,"wins":1},"z-ai/glm-5.2":{"draws":15,"losses":40,"wins":5},"z-ai/glm-5.3":{"draws":2,"losses":27,"wins":1},"z-ai/glm-5.3-flash":{"draws":2,"losses":26,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":27,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":8},"claude-fable-5":{"draws":5,"losses":22,"wins":3},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":16,"wins":7},"claude-opus-4-5":{"draws":22,"losses":19,"wins":9},"claude-opus-4-8":{"draws":6,"losses":23,"wins":1},"claude-opus-5":{"draws":4,"losses":41,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":9,"losses":12,"wins":9},"claude-sonnet-5-5":{"draws":5,"losses":18,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":16,"losses":15,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":17,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":13,"wins":3},"elorian/glimpse":{"draws":0,"losses":7,"wins":3},"fireworks/ember-1":{"draws":11,"losses":14,"wins":5},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":6},"gemini-4-argon":{"draws":0,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":13},"google/gemini-3.5-flash":{"draws":10,"losses":22,"wins":6},"google/gemini-3.5-flash-lite":{"draws":16,"losses":18,"wins":16},"google/gemini-3.6-flash":{"draws":14,"losses":31,"wins":11},"google/gemini-3.8-flash":{"draws":8,"losses":20,"wins":2},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":4},"gpt-4.1":{"draws":4,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":12,"wins":7},"gpt-5.4":{"draws":7,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":14,"wins":13},"gpt-5.5":{"draws":10,"losses":12,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":22,"wins":4},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":10},"gpt-6-astra":{"draws":3,"losses":26,"wins":1},"gpt-6-luna":{"draws":13,"losses":11,"wins":6},"gpt-6-sol":{"draws":2,"losses":26,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":10},"inception/mercury-3":{"draws":7,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":13},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":7},"meta/muse-spark-1.2":{"draws":8,"losses":16,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":16,"wins":7},"meta/muse-spark-open":{"draws":2,"losses":11,"wins":3},"meta/muse-wonder":{"draws":7,"losses":19,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":4},"minimax/minimax-m3.1-flash":{"draws":3,"losses":5,"wins":4},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":7,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":2,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":1},"o3":{"draws":8,"losses":27,"wins":11},"openai/gpt-oss-120b":{"draws":9,"losses":13,"wins":4},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":5},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":11,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":5,"wins":0},"stealth/ox-alpha":{"draws":22,"losses":40,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":13,"wins":13},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":10},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":18,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":14,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":9,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":10,"wins":4},"z-ai/glm-5.2":{"draws":27,"losses":19,"wins":14},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":11,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":9}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":6,"wins":5},"claude-fable-5":{"draws":4,"losses":23,"wins":3},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":12,"wins":8},"claude-opus-4-5":{"draws":17,"losses":13,"wins":18},"claude-opus-4-8":{"draws":8,"losses":17,"wins":5},"claude-opus-5":{"draws":8,"losses":34,"wins":6},"claude-opus-5-5":{"draws":3,"losses":26,"wins":3},"claude-sonnet-5":{"draws":5,"losses":14,"wins":9},"claude-sonnet-5-5":{"draws":8,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":13,"losses":10,"wins":17},"deepseek/deepseek-v4-pro":{"draws":8,"losses":6,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":7,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":14,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":21,"wins":11},"elorian/glimpse":{"draws":6,"losses":11,"wins":7},"fireworks/ember-1":{"draws":14,"losses":9,"wins":5},"gemini-3.1-pro-preview":{"draws":6,"losses":11,"wins":11},"gemini-4-argon":{"draws":4,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":8,"losses":14,"wins":14},"google/gemini-3.5-flash-lite":{"draws":18,"losses":1,"wins":29},"google/gemini-3.6-flash":{"draws":16,"losses":23,"wins":13},"google/gemini-3.8-flash":{"draws":5,"losses":17,"wins":12},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":6},"gpt-4.1":{"draws":2,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":15},"gpt-5.4":{"draws":7,"losses":14,"wins":7},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":21},"gpt-5.5":{"draws":12,"losses":14,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":8,"losses":21,"wins":5},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":10},"gpt-6-astra":{"draws":2,"losses":38,"wins":0},"gpt-6-luna":{"draws":11,"losses":13,"wins":4},"gpt-6-sol":{"draws":3,"losses":10,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":23,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":1,"wins":20},"inception/mercury-3":{"draws":11,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":7},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":3,"wins":15},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":8,"wins":5},"meta/muse-spark-1.3":{"draws":6,"losses":18,"wins":12},"meta/muse-spark-open":{"draws":6,"losses":23,"wins":11},"meta/muse-wonder":{"draws":5,"losses":12,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":9},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":15},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":11,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":4},"o3":{"draws":7,"losses":9,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":4,"wins":17},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.8-27b":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":18,"wins":10},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":13,"wins":14},"stealth/ox-alpha":{"draws":28,"losses":43,"wins":23},"stealth/space-bunny-alpha":{"draws":9,"losses":4,"wins":9},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":9,"wins":13},"thinkingmachines/inkling-small":{"draws":10,"losses":4,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":15,"wins":6},"x-ai/grok-4.6":{"draws":5,"losses":16,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":18,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":15,"losses":9,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":8,"wins":9},"z-ai/glm-5.2":{"draws":14,"losses":16,"wins":18},"z-ai/glm-5.3":{"draws":2,"losses":21,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":6}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":17},"claude-fable-5":{"draws":4,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":25,"wins":7},"claude-opus-4-5":{"draws":16,"losses":27,"wins":17},"claude-opus-4-8":{"draws":6,"losses":20,"wins":10},"claude-opus-5":{"draws":7,"losses":45,"wins":6},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":6,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":6,"losses":13,"wins":35},"deepseek/deepseek-v4-pro":{"draws":5,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":18,"wins":3},"elorian/glimpse":{"draws":2,"losses":8,"wins":2},"fireworks/ember-1":{"draws":13,"losses":16,"wins":7},"gemini-3.1-pro-preview":{"draws":7,"losses":12,"wins":17},"gemini-4-argon":{"draws":0,"losses":9,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":8,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":17,"losses":12,"wins":37},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":24},"google/gemini-3.8-flash":{"draws":2,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":13},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":15,"wins":13},"gpt-5.4":{"draws":6,"losses":21,"wins":9},"gpt-5.4-mini":{"draws":5,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":3,"losses":16,"wins":21},"gpt-5.5":{"draws":10,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":2,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":19,"wins":8},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":6,"losses":16,"wins":14},"gpt-6-sol":{"draws":6,"losses":27,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":17},"inception/mercury-3":{"draws":1,"losses":4,"wins":5},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":25},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":20},"meta/muse-spark-1.2":{"draws":6,"losses":19,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":23,"wins":7},"meta/muse-spark-open":{"draws":2,"losses":18,"wins":2},"meta/muse-wonder":{"draws":2,"losses":29,"wins":5},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":16},"minimax/minimax-m3.1-flash":{"draws":4,"losses":9,"wins":5},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":1},"o3":{"draws":6,"losses":22,"wins":20},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":25},"poolside/laguna-s-2.1":{"draws":3,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":3,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":5,"wins":4},"stealth/ox-alpha":{"draws":15,"losses":61,"wins":26},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":29},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":9},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":16,"losses":10,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":27,"wins":29},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":12},"z-ai/glm-5.3-flashx":{"draws":3,"losses":23,"wins":10}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":14,"wins":13},"claude-fable-5":{"draws":12,"losses":35,"wins":1},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":31,"wins":3},"claude-opus-4-5":{"draws":28,"losses":41,"wins":9},"claude-opus-4-8":{"draws":14,"losses":29,"wins":1},"claude-opus-5":{"draws":12,"losses":65,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":15,"losses":26,"wins":7},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":29,"losses":23,"wins":20},"deepseek/deepseek-v4-pro":{"draws":14,"losses":23,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":27,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":25,"wins":3},"elorian/glimpse":{"draws":4,"losses":8,"wins":4},"fireworks/ember-1":{"draws":19,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":22,"wins":10},"gemini-4-argon":{"draws":0,"losses":20,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":31,"wins":23},"google/gemini-3.6-flash":{"draws":29,"losses":52,"wins":11},"google/gemini-3.8-flash":{"draws":11,"losses":36,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":7,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":22,"wins":5},"gpt-5.4":{"draws":16,"losses":28,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":18},"gpt-5.5":{"draws":19,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":17,"losses":27,"wins":2},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":16,"losses":23,"wins":9},"gpt-6-sol":{"draws":6,"losses":39,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":17,"losses":7,"wins":10},"inception/mercury-3":{"draws":5,"losses":4,"wins":1},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":24,"wins":11},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":12},"meta/muse-spark-1.2":{"draws":13,"losses":29,"wins":4},"meta/muse-spark-1.3":{"draws":13,"losses":32,"wins":3},"meta/muse-spark-open":{"draws":3,"losses":13,"wins":2},"meta/muse-wonder":{"draws":10,"losses":36,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":10,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":4},"mistralai/mistral-large-4-0":{"draws":10,"losses":18,"wins":2},"mistralai/mistral-medium-3-5":{"draws":13,"losses":7,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":26,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":13,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":1},"o3":{"draws":11,"losses":50,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":12,"wins":5},"poolside/laguna-s-2.1":{"draws":18,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":31,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":19,"losses":27,"wins":2},"qwen/qwen3.8-max-0902":{"draws":16,"losses":31,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":12,"wins":1},"stealth/ox-alpha":{"draws":42,"losses":102,"wins":14},"stealth/space-bunny-alpha":{"draws":14,"losses":17,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":15,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":12,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":24,"wins":6},"thinkingmachines/inkling":{"draws":20,"losses":24,"wins":20},"thinkingmachines/inkling-small":{"draws":19,"losses":14,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":18,"losses":29,"wins":1},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":26,"losses":25,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":21,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":24,"wins":2},"z-ai/glm-5.2":{"draws":35,"losses":44,"wins":17},"z-ai/glm-5.3":{"draws":10,"losses":34,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":34,"wins":5},"z-ai/glm-5.3-flashx":{"draws":11,"losses":29,"wins":8}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":21,"wins":14},"claude-fable-5":{"draws":17,"losses":42,"wins":7},"claude-fable-5-1":{"draws":5,"losses":66,"wins":1},"claude-haiku-5-5":{"draws":19,"losses":31,"wins":12},"claude-opus-4-5":{"draws":44,"losses":50,"wins":12},"claude-opus-4-8":{"draws":23,"losses":31,"wins":4},"claude-opus-5":{"draws":17,"losses":98,"wins":7},"claude-opus-5-5":{"draws":5,"losses":69,"wins":0},"claude-sonnet-5":{"draws":24,"losses":36,"wins":6},"claude-sonnet-5-5":{"draws":15,"losses":40,"wins":11},"cohere/north-mini-code":{"draws":8,"losses":12,"wins":4},"deepseek/deepseek-v4-flash":{"draws":44,"losses":30,"wins":24},"deepseek/deepseek-v4-pro":{"draws":23,"losses":22,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":25,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":25,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":5},"elorian/glimpse":{"draws":4,"losses":9,"wins":1},"fireworks/ember-1":{"draws":30,"losses":27,"wins":9},"gemini-3.1-pro-preview":{"draws":27,"losses":28,"wins":11},"gemini-4-argon":{"draws":3,"losses":27,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":7,"wins":16},"google/gemini-3.5-flash":{"draws":27,"losses":41,"wins":12},"google/gemini-3.5-flash-lite":{"draws":48,"losses":32,"wins":34},"google/gemini-3.6-flash":{"draws":45,"losses":67,"wins":12},"google/gemini-3.8-flash":{"draws":16,"losses":44,"wins":6},"google/gemma-4-31b-it":{"draws":20,"losses":10,"wins":8},"gpt-4.1":{"draws":11,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":1},"gpt-5":{"draws":26,"losses":24,"wins":8},"gpt-5.4":{"draws":19,"losses":37,"wins":6},"gpt-5.4-mini":{"draws":21,"losses":16,"wins":7},"gpt-5.4-nano":{"draws":24,"losses":22,"wins":20},"gpt-5.5":{"draws":27,"losses":25,"wins":8},"gpt-5.6-luna":{"draws":30,"losses":23,"wins":13},"gpt-5.6-sol":{"draws":11,"losses":54,"wins":1},"gpt-5.6-terra":{"draws":29,"losses":29,"wins":4},"gpt-6-astra":{"draws":5,"losses":61,"wins":0},"gpt-6-luna":{"draws":25,"losses":34,"wins":7},"gpt-6-sol":{"draws":12,"losses":51,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":61,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":10,"wins":10},"inception/mercury-3":{"draws":12,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":27,"losses":5,"wins":12},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":25,"wins":19},"meta/muse-glimmer-30b":{"draws":31,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":18,"losses":43,"wins":3},"meta/muse-spark-1.3":{"draws":22,"losses":37,"wins":7},"meta/muse-spark-open":{"draws":14,"losses":17,"wins":1},"meta/muse-wonder":{"draws":12,"losses":48,"wins":6},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":10,"losses":14,"wins":6},"mistralai/mistral-large-4-0":{"draws":19,"losses":19,"wins":4},"mistralai/mistral-medium-3-5":{"draws":22,"losses":7,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":28,"losses":34,"wins":2},"nex-agi/nex-n2-pro":{"draws":15,"losses":7,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":17,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":8,"wins":2},"o3":{"draws":19,"losses":43,"wins":20},"openai/gpt-oss-120b":{"draws":30,"losses":22,"wins":8},"poolside/laguna-s-2.1":{"draws":26,"losses":15,"wins":9},"qwen/qwen3.7-max":{"draws":19,"losses":11,"wins":8},"qwen/qwen3.7-plus":{"draws":15,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":36,"wins":5},"qwen/qwen3.8-27b":{"draws":16,"losses":22,"wins":6},"qwen/qwen3.8-flash":{"draws":23,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":26,"losses":30,"wins":10},"qwen/qwen3.8-max-0902":{"draws":26,"losses":35,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":13,"wins":6},"stealth/ox-alpha":{"draws":75,"losses":130,"wins":25},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":12},"stepfun/step-3.7-flash":{"draws":16,"losses":15,"wins":11},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":8},"tencent/hy4-preview":{"draws":22,"losses":31,"wins":9},"thinkingmachines/inkling":{"draws":36,"losses":26,"wins":26},"thinkingmachines/inkling-small":{"draws":33,"losses":10,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":21,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":21,"losses":39,"wins":6},"x-ai/grok-4.6":{"draws":19,"losses":42,"wins":5},"x-ai/grok-4.7":{"draws":7,"losses":46,"wins":5},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":43,"losses":27,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":26,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":67,"losses":44,"wins":21},"z-ai/glm-5.3":{"draws":18,"losses":40,"wins":6},"z-ai/glm-5.3-flash":{"draws":18,"losses":37,"wins":11},"z-ai/glm-5.3-flashx":{"draws":27,"losses":31,"wins":8}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":6,"wins":17},"claude-fable-5":{"draws":7,"losses":27,"wins":8},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":12},"claude-opus-4-5":{"draws":23,"losses":28,"wins":19},"claude-opus-4-8":{"draws":13,"losses":17,"wins":12},"claude-opus-5":{"draws":9,"losses":52,"wins":9},"claude-opus-5-5":{"draws":1,"losses":45,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":10},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":33,"losses":9,"wins":22},"deepseek/deepseek-v4-pro":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":12,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":13,"wins":1},"elorian/glimpse":{"draws":2,"losses":7,"wins":5},"fireworks/ember-1":{"draws":13,"losses":17,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":16},"gemini-4-argon":{"draws":2,"losses":17,"wins":3},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":17},"google/gemini-3.5-flash":{"draws":19,"losses":18,"wins":17},"google/gemini-3.5-flash-lite":{"draws":25,"losses":20,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":33,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":10},"gpt-4.1":{"draws":8,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":16,"losses":14,"wins":6},"gpt-5.4":{"draws":7,"losses":23,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":20},"gpt-5.5":{"draws":13,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":11,"losses":18,"wins":11},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":11,"losses":19,"wins":12},"gpt-6-sol":{"draws":7,"losses":30,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":13},"inception/mercury-3":{"draws":5,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":24},"meta/muse-glimmer-30b":{"draws":15,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":11},"meta/muse-spark-open":{"draws":3,"losses":9,"wins":6},"meta/muse-wonder":{"draws":6,"losses":33,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"minimax/minimax-m3.1-flash":{"draws":5,"losses":7,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":19,"wins":11},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":8,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":4,"wins":7},"o3":{"draws":16,"losses":22,"wins":24},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":16},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":16,"wins":5},"stealth/ox-alpha":{"draws":31,"losses":56,"wins":31},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":8,"losses":21,"wins":11},"thinkingmachines/inkling":{"draws":17,"losses":6,"wins":31},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":11},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":13,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":33,"wins":26},"z-ai/glm-5.3":{"draws":11,"losses":20,"wins":9},"z-ai/glm-5.3-flash":{"draws":15,"losses":15,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":17,"wins":12}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":13},"claude-fable-5":{"draws":7,"losses":24,"wins":5},"claude-fable-5-1":{"draws":0,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":22,"wins":7},"claude-opus-4-5":{"draws":15,"losses":24,"wins":21},"claude-opus-4-8":{"draws":8,"losses":19,"wins":9},"claude-opus-5":{"draws":10,"losses":47,"wins":1},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"claude-sonnet-5-5":{"draws":8,"losses":19,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":24},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":8,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":18,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":12,"wins":6},"elorian/glimpse":{"draws":2,"losses":9,"wins":1},"fireworks/ember-1":{"draws":11,"losses":16,"wins":9},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":12},"gemini-4-argon":{"draws":1,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":11,"losses":21,"wins":14},"google/gemini-3.5-flash-lite":{"draws":17,"losses":15,"wins":30},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":19},"google/gemini-3.8-flash":{"draws":8,"losses":24,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":9},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":16,"wins":8},"gpt-5.4":{"draws":6,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":11,"wins":22},"gpt-5.5":{"draws":15,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":12},"gpt-5.6-sol":{"draws":6,"losses":25,"wins":5},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":9},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":10},"gpt-6-sol":{"draws":3,"losses":27,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":30,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":15},"inception/mercury-3":{"draws":4,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":10,"wins":21},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":10},"meta/muse-spark-1.2":{"draws":6,"losses":23,"wins":5},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":9},"meta/muse-spark-open":{"draws":7,"losses":15,"wins":4},"meta/muse-wonder":{"draws":11,"losses":25,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":11},"minimax/minimax-m3.1-flash":{"draws":1,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":1},"mistralai/mistral-medium-3-5":{"draws":8,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":11,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":4,"wins":2},"o3":{"draws":7,"losses":27,"wins":24},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":17},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":5,"losses":10,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":11,"wins":3},"stealth/ox-alpha":{"draws":22,"losses":58,"wins":20},"stealth/space-bunny-alpha":{"draws":8,"losses":12,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":21,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":29},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":6,"losses":23,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":23,"losses":26,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":17,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":9}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":14},"claude-fable-5":{"draws":13,"losses":31,"wins":4},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":22,"wins":8},"claude-opus-4-5":{"draws":37,"losses":27,"wins":14},"claude-opus-4-8":{"draws":16,"losses":20,"wins":8},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":18,"losses":21,"wins":9},"claude-sonnet-5-5":{"draws":14,"losses":24,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":30,"losses":16,"wins":26},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":18,"wins":4},"elorian/glimpse":{"draws":3,"losses":5,"wins":6},"fireworks/ember-1":{"draws":27,"losses":19,"wins":2},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"gemini-4-argon":{"draws":0,"losses":16,"wins":2},"google/gemini-3.1-flash-lite":{"draws":12,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":14},"google/gemini-3.5-flash-lite":{"draws":34,"losses":21,"wins":29},"google/gemini-3.6-flash":{"draws":29,"losses":45,"wins":18},"google/gemini-3.8-flash":{"draws":12,"losses":29,"wins":7},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":8,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":17,"losses":14,"wins":11},"gpt-5.4":{"draws":12,"losses":26,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":17,"losses":16,"wins":15},"gpt-5.5":{"draws":17,"losses":18,"wins":9},"gpt-5.6-luna":{"draws":25,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":22,"losses":12,"wins":12},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":7,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":20,"losses":2,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":12,"wins":23},"meta/muse-glimmer-30b":{"draws":25,"losses":2,"wins":15},"meta/muse-spark-1.2":{"draws":14,"losses":23,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":3,"losses":13,"wins":6},"meta/muse-wonder":{"draws":9,"losses":33,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":13,"losses":6,"wins":5},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":8,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":7,"wins":4},"o3":{"draws":14,"losses":28,"wins":24},"openai/gpt-oss-120b":{"draws":20,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":6,"wins":19},"qwen/qwen3.7-max":{"draws":14,"losses":7,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-27b":{"draws":15,"losses":11,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":7},"qwen/qwen3.8-max":{"draws":20,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":20,"losses":24,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":5,"wins":5},"stealth/ox-alpha":{"draws":54,"losses":72,"wins":32},"stealth/space-bunny-alpha":{"draws":18,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":5,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":20,"losses":6,"wins":22},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":29,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":16,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":47,"losses":31,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":33,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":33,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":26,"wins":12}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":10,"wins":16},"claude-fable-5":{"draws":12,"losses":27,"wins":3},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":9},"claude-opus-4-5":{"draws":26,"losses":14,"wins":28},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":14,"losses":51,"wins":5},"claude-opus-5-5":{"draws":2,"losses":39,"wins":1},"claude-sonnet-5":{"draws":14,"losses":14,"wins":14},"claude-sonnet-5-5":{"draws":6,"losses":28,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":15,"wins":6},"elorian/glimpse":{"draws":5,"losses":6,"wins":3},"fireworks/ember-1":{"draws":14,"losses":13,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":17},"gemini-4-argon":{"draws":3,"losses":12,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":20,"losses":17,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":39,"wins":21},"google/gemini-3.8-flash":{"draws":6,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":13},"gpt-5.4":{"draws":10,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":20},"gpt-5.5":{"draws":17,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":15,"wins":6},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":5,"losses":32,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":4,"wins":13},"inception/mercury-3":{"draws":7,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":14,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":10},"meta/muse-spark-open":{"draws":4,"losses":10,"wins":6},"meta/muse-wonder":{"draws":10,"losses":27,"wins":5},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"wins":3},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":4},"o3":{"draws":7,"losses":20,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":16},"poolside/laguna-s-2.1":{"draws":14,"losses":9,"wins":15},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":15,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":3,"wins":1},"stealth/ox-alpha":{"draws":40,"losses":61,"wins":41},"stealth/space-bunny-alpha":{"draws":12,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":15,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":21,"losses":8,"wins":29},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":16,"losses":17,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":7,"losses":23,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":9,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":27,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":6}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":4,"wins":27},"claude-fable-5":{"draws":15,"losses":17,"wins":16},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":26,"losses":13,"wins":39},"claude-opus-4-8":{"draws":19,"losses":11,"wins":14},"claude-opus-5":{"draws":11,"losses":61,"wins":10},"claude-opus-5-5":{"draws":7,"losses":43,"wins":2},"claude-sonnet-5":{"draws":14,"losses":9,"wins":25},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":6,"wins":43},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":7,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":12,"wins":12},"elorian/glimpse":{"draws":1,"losses":3,"wins":8},"fireworks/ember-1":{"draws":17,"losses":9,"wins":22},"gemini-3.1-pro-preview":{"draws":19,"losses":11,"wins":18},"gemini-4-argon":{"draws":4,"losses":13,"wins":9},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":21,"losses":12,"wins":27},"google/gemini-3.5-flash-lite":{"draws":27,"losses":4,"wins":53},"google/gemini-3.6-flash":{"draws":27,"losses":26,"wins":39},"google/gemini-3.8-flash":{"draws":13,"losses":10,"wins":25},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":13},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":14,"losses":5,"wins":23},"gpt-5.4":{"draws":11,"losses":16,"wins":19},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":8,"wins":28},"gpt-5.5":{"draws":16,"losses":15,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":11,"losses":24,"wins":13},"gpt-5.6-terra":{"draws":19,"losses":8,"wins":19},"gpt-6-astra":{"draws":7,"losses":38,"wins":3},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":28,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":15,"losses":0,"wins":19},"inception/mercury-3":{"draws":8,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":30},"meta/muse-glimmer-30b":{"draws":16,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":15,"wins":21},"meta/muse-spark-1.3":{"draws":13,"losses":15,"wins":20},"meta/muse-spark-open":{"draws":8,"losses":5,"wins":17},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":6,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":3,"wins":16},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":13,"losses":8,"wins":25},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":3,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":7},"o3":{"draws":9,"losses":12,"wins":45},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":2,"wins":24},"qwen/qwen3.7-max":{"draws":9,"losses":2,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":11,"wins":26},"qwen/qwen3.8-27b":{"draws":11,"losses":6,"wins":17},"qwen/qwen3.8-flash":{"draws":9,"losses":0,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":13,"wins":20},"qwen/qwen3.8-max-0902":{"draws":17,"losses":10,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":3,"wins":11},"stealth/ox-alpha":{"draws":48,"losses":37,"wins":73},"stealth/space-bunny-alpha":{"draws":13,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":15,"losses":10,"wins":21},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":37},"thinkingmachines/inkling-small":{"draws":21,"losses":6,"wins":21},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":17,"wins":17},"x-ai/grok-4.6":{"draws":19,"losses":16,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":26,"wins":10},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":30,"losses":4,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":5,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":34,"losses":11,"wins":51},"z-ai/glm-5.3":{"draws":14,"losses":21,"wins":11},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":13,"losses":16,"wins":19}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":8,"wins":19},"claude-fable-5":{"draws":6,"losses":30,"wins":12},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":27,"wins":12},"claude-opus-4-5":{"draws":25,"losses":16,"wins":37},"claude-opus-4-8":{"draws":11,"losses":20,"wins":13},"claude-opus-5":{"draws":15,"losses":60,"wins":7},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":15,"losses":13,"wins":20},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":22,"losses":10,"wins":40},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":13,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":18,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":17,"wins":5},"elorian/glimpse":{"draws":3,"losses":3,"wins":4},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"gemini-4-argon":{"draws":0,"losses":19,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":16,"losses":24,"wins":20},"google/gemini-3.5-flash-lite":{"draws":30,"losses":14,"wins":40},"google/gemini-3.6-flash":{"draws":30,"losses":41,"wins":21},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":8,"wins":20},"gpt-5.4":{"draws":12,"losses":20,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":27},"gpt-5.5":{"draws":16,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":20,"losses":14,"wins":12},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":15,"losses":14,"wins":19},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":40,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":6,"losses":1,"wins":5},"inclusionai/ling-3.0-flash":{"draws":16,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":12,"wins":21},"meta/muse-spark-1.3":{"draws":10,"losses":30,"wins":8},"meta/muse-spark-open":{"draws":5,"losses":10,"wins":7},"meta/muse-wonder":{"draws":11,"losses":29,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":1,"wins":17},"minimax/minimax-m3.1-flash":{"draws":4,"losses":11,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":7},"o3":{"draws":13,"losses":19,"wins":34},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":13,"wins":19},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":8,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":6,"wins":7},"stealth/ox-alpha":{"draws":39,"losses":61,"wins":58},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":19,"losses":13,"wins":32},"thinkingmachines/inkling-small":{"draws":12,"losses":15,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":26,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":2,"losses":34,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":15,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":33,"losses":23,"wins":40},"z-ai/glm-5.3":{"draws":13,"losses":24,"wins":9},"z-ai/glm-5.3-flash":{"draws":11,"losses":22,"wins":15},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":12,"wins":22},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":11},"claude-opus-4-5":{"draws":23,"losses":39,"wins":16},"claude-opus-4-8":{"draws":13,"losses":24,"wins":7},"claude-opus-5":{"draws":16,"losses":57,"wins":9},"claude-opus-5-5":{"draws":6,"losses":45,"wins":1},"claude-sonnet-5":{"draws":13,"losses":15,"wins":20},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":24,"losses":14,"wins":34},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":24,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":22,"wins":6},"elorian/glimpse":{"draws":3,"losses":5,"wins":2},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"gemini-4-argon":{"draws":1,"losses":21,"wins":2},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":21},"google/gemini-3.5-flash-lite":{"draws":28,"losses":22,"wins":34},"google/gemini-3.6-flash":{"draws":20,"losses":51,"wins":21},"google/gemini-3.8-flash":{"draws":13,"losses":29,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":16,"wins":15},"gpt-5.4":{"draws":7,"losses":28,"wins":11},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":14,"losses":19,"wins":15},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":10},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":8,"losses":8,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":13,"wins":31},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":23,"wins":10},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":3},"meta/muse-wonder":{"draws":7,"losses":30,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":12},"minimax/minimax-m3.1-flash":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":2},"o3":{"draws":11,"losses":29,"wins":26},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":21},"poolside/laguna-s-2.1":{"draws":18,"losses":13,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":21,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":13,"losses":19,"wins":16},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":37,"losses":75,"wins":46},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":10,"losses":8,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":8,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":17,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":22,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":29,"wins":33},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":22,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":13}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":6},"claude-fable-5":{"draws":3,"losses":12,"wins":3},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":17,"wins":5},"claude-opus-4-5":{"draws":13,"losses":12,"wins":11},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":3,"losses":27,"wins":2},"claude-opus-5-5":{"draws":0,"losses":20,"wins":0},"claude-sonnet-5":{"draws":5,"losses":7,"wins":10},"claude-sonnet-5-5":{"draws":6,"losses":15,"wins":5},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":2},"deepseek/deepseek-v4-flash":{"draws":9,"losses":8,"wins":13},"deepseek/deepseek-v4-pro":{"draws":3,"losses":10,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":7,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":26,"wins":6},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":4,"losses":12,"wins":10},"gemini-3.1-pro-preview":{"draws":5,"losses":7,"wins":8},"gemini-4-argon":{"draws":3,"losses":36,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":1,"losses":12,"wins":13},"google/gemini-3.5-flash-lite":{"draws":11,"losses":10,"wins":17},"google/gemini-3.6-flash":{"draws":10,"losses":21,"wins":13},"google/gemini-3.8-flash":{"draws":6,"losses":13,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":14},"gpt-4.1":{"draws":2,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":7},"gpt-5.4":{"draws":9,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":1,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":9},"gpt-5.5":{"draws":4,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":1,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":9,"losses":2,"wins":5},"gpt-6-astra":{"draws":0,"losses":19,"wins":1},"gpt-6-luna":{"draws":4,"losses":11,"wins":5},"gpt-6-sol":{"draws":4,"losses":18,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":1,"wins":14},"inception/mercury-3":{"draws":5,"losses":17,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":5},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":18},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":9},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":6,"wins":4},"meta/muse-spark-open":{"draws":7,"losses":29,"wins":2},"meta/muse-wonder":{"draws":4,"losses":12,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3.1-flash":{"draws":8,"losses":15,"wins":9},"mistralai/mistral-large-4-0":{"draws":3,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":3,"losses":13,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":6},"o3":{"draws":6,"losses":10,"wins":20},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":6},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":13,"wins":6},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":0,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":1,"losses":16,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":11,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":10,"wins":9},"stealth/ox-alpha":{"draws":11,"losses":43,"wins":20},"stealth/space-bunny-alpha":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":4},"tencent/hy4-preview":{"draws":9,"losses":10,"wins":3},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":9},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":6},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":5,"wins":1},"x-ai/grok-4.6":{"draws":7,"losses":8,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":19,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":10,"wins":3},"z-ai/glm-5.2":{"draws":22,"losses":14,"wins":8},"z-ai/glm-5.3":{"draws":2,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":11,"wins":5},"z-ai/glm-5.3-flashx":{"draws":8,"losses":8,"wins":4}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":33,"wins":77},"claude-fable-5":{"draws":32,"losses":89,"wins":35},"claude-fable-5-1":{"draws":9,"losses":167,"wins":6},"claude-haiku-5-5":{"draws":31,"losses":59,"wins":52},"claude-opus-4-5":{"draws":73,"losses":75,"wins":98},"claude-opus-4-8":{"draws":32,"losses":49,"wins":47},"claude-opus-5":{"draws":47,"losses":189,"wins":44},"claude-opus-5-5":{"draws":19,"losses":144,"wins":5},"claude-sonnet-5":{"draws":40,"losses":43,"wins":73},"claude-sonnet-5-5":{"draws":37,"losses":70,"wins":49},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":47},"deepseek/deepseek-v4-flash":{"draws":56,"losses":47,"wins":125},"deepseek/deepseek-v4-pro":{"draws":33,"losses":46,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":51,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":62,"wins":52},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":48,"wins":25},"elorian/glimpse":{"draws":12,"losses":12,"wins":26},"fireworks/ember-1":{"draws":40,"losses":61,"wins":55},"gemini-3.1-pro-preview":{"draws":37,"losses":46,"wins":73},"gemini-4-argon":{"draws":9,"losses":40,"wins":3},"google/gemini-3.1-flash-lite":{"draws":18,"losses":14,"wins":54},"google/gemini-3.5-flash":{"draws":42,"losses":65,"wins":81},"google/gemini-3.5-flash-lite":{"draws":60,"losses":58,"wins":152},"google/gemini-3.6-flash":{"draws":77,"losses":124,"wins":99},"google/gemini-3.8-flash":{"draws":38,"losses":75,"wins":43},"google/gemma-4-31b-it":{"draws":18,"losses":17,"wins":51},"gpt-4.1":{"draws":12,"losses":9,"wins":31},"gpt-4.1-nano":{"draws":13,"losses":1,"wins":10},"gpt-5":{"draws":30,"losses":45,"wins":65},"gpt-5.4":{"draws":40,"losses":59,"wins":51},"gpt-5.4-mini":{"draws":29,"losses":18,"wins":57},"gpt-5.4-nano":{"draws":30,"losses":36,"wins":70},"gpt-5.5":{"draws":42,"losses":55,"wins":49},"gpt-5.6-luna":{"draws":51,"losses":31,"wins":74},"gpt-5.6-sol":{"draws":24,"losses":103,"wins":29},"gpt-5.6-terra":{"draws":42,"losses":39,"wins":69},"gpt-6-astra":{"draws":10,"losses":141,"wins":5},"gpt-6-luna":{"draws":38,"losses":56,"wins":62},"gpt-6-sol":{"draws":23,"losses":115,"wins":18},"gpt-6.1-sol":{"draws":16,"losses":133,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":35,"losses":11,"wins":56},"inception/mercury-3":{"draws":19,"losses":9,"wins":22},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":72},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":32,"losses":26,"wins":110},"meta/muse-glimmer-30b":{"draws":31,"losses":21,"wins":90},"meta/muse-spark-1.2":{"draws":35,"losses":57,"wins":60},"meta/muse-spark-1.3":{"draws":34,"losses":69,"wins":53},"meta/muse-spark-open":{"draws":16,"losses":35,"wins":15},"meta/muse-wonder":{"draws":37,"losses":76,"wins":43},"minimax/minimax-m3":{"draws":19,"losses":17,"wins":44},"minimax/minimax-m3.1-flash":{"draws":20,"losses":20,"wins":36},"mistralai/mistral-large-4-0":{"draws":33,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":19,"losses":18,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":16},"moonshotai/kimi-k3":{"draws":40,"losses":63,"wins":49},"nex-agi/nex-n2-pro":{"draws":19,"losses":13,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":17,"wins":68},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":11,"wins":14},"o3":{"draws":27,"losses":71,"wins":94},"openai/gpt-oss-120b":{"draws":31,"losses":24,"wins":87},"poolside/laguna-s-2.1":{"draws":37,"losses":31,"wins":92},"qwen/qwen3.7-max":{"draws":23,"losses":22,"wins":39},"qwen/qwen3.7-plus":{"draws":16,"losses":10,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":62,"wins":50},"qwen/qwen3.8-27b":{"draws":23,"losses":41,"wins":42},"qwen/qwen3.8-flash":{"draws":31,"losses":35,"wins":38},"qwen/qwen3.8-max":{"draws":50,"losses":50,"wins":56},"qwen/qwen3.8-max-0902":{"draws":35,"losses":72,"wins":49},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":22,"wins":38},"stealth/ox-alpha":{"draws":101,"losses":246,"wins":203},"stealth/space-bunny-alpha":{"draws":33,"losses":30,"wins":59},"stepfun/step-3.7-flash":{"draws":14,"losses":22,"wins":70},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":25,"losses":13,"wins":42},"tencent/hy4-preview":{"draws":31,"losses":69,"wins":50},"thinkingmachines/inkling":{"draws":53,"losses":45,"wins":118},"thinkingmachines/inkling-small":{"draws":41,"losses":34,"wins":81},"unbiased/pareto-26.10":{"draws":4,"losses":31,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":50,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":38,"losses":69,"wins":49},"x-ai/grok-4.6":{"draws":43,"losses":65,"wins":48},"x-ai/grok-4.7":{"draws":17,"losses":98,"wins":17},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":62,"losses":30,"wins":116},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":35,"wins":42},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":51,"wins":37},"z-ai/glm-5.2":{"draws":82,"losses":79,"wins":151},"z-ai/glm-5.3":{"draws":31,"losses":88,"wins":33},"z-ai/glm-5.3-flash":{"draws":30,"losses":76,"wins":50},"z-ai/glm-5.3-flashx":{"draws":24,"losses":78,"wins":54}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":14},"claude-fable-5":{"draws":9,"losses":27,"wins":6},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":18,"wins":8},"claude-opus-4-5":{"draws":21,"losses":23,"wins":24},"claude-opus-4-8":{"draws":11,"losses":22,"wins":5},"claude-opus-5":{"draws":9,"losses":56,"wins":5},"claude-opus-5-5":{"draws":1,"losses":41,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":9,"losses":29,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":9,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":16,"wins":3},"elorian/glimpse":{"draws":0,"losses":2,"wins":4},"fireworks/ember-1":{"draws":14,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":11},"gemini-4-argon":{"draws":2,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":10},"google/gemini-3.5-flash-lite":{"draws":16,"losses":29,"wins":29},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":14,"wins":15},"gpt-5.4":{"draws":11,"losses":23,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":7,"losses":18,"wins":15},"gpt-5.5":{"draws":10,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":10},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":20,"wins":5},"gpt-6-sol":{"draws":9,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":15},"inception/mercury-3":{"draws":3,"losses":4,"wins":3},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":14},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":15,"wins":10},"meta/muse-spark-1.2":{"draws":14,"losses":18,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":31,"wins":4},"meta/muse-spark-open":{"draws":7,"losses":11,"wins":8},"meta/muse-wonder":{"draws":14,"losses":21,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"minimax/minimax-m3.1-flash":{"draws":7,"losses":8,"wins":13},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":11,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":2},"o3":{"draws":6,"losses":26,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":15},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":15,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":5,"wins":1},"stealth/ox-alpha":{"draws":31,"losses":76,"wins":35},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":16},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":18,"wins":21},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":23,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":11},"z-ai/glm-5.2":{"draws":33,"losses":28,"wins":23},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":13},"claude-fable-5":{"draws":2,"losses":30,"wins":4},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":23,"wins":7},"claude-opus-4-5":{"draws":10,"losses":32,"wins":16},"claude-opus-4-8":{"draws":3,"losses":19,"wins":10},"claude-opus-5":{"draws":2,"losses":54,"wins":2},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":7,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":3,"losses":23,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":13,"losses":24,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":19,"wins":3},"elorian/glimpse":{"draws":0,"losses":13,"wins":3},"fireworks/ember-1":{"draws":5,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":4,"losses":19,"wins":13},"gemini-4-argon":{"draws":0,"losses":15,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":29,"wins":10},"google/gemini-3.5-flash-lite":{"draws":13,"losses":23,"wins":28},"google/gemini-3.6-flash":{"draws":9,"losses":45,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":9},"gpt-4.1":{"draws":1,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":15,"wins":8},"gpt-5.4":{"draws":6,"losses":25,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":22,"wins":12},"gpt-5.5":{"draws":8,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":19,"wins":7},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":6,"losses":21,"wins":9},"gpt-6-sol":{"draws":4,"losses":32,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":7,"wins":11},"inception/mercury-3":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":14,"wins":19},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":14},"meta/muse-spark-1.2":{"draws":0,"losses":27,"wins":7},"meta/muse-spark-1.3":{"draws":3,"losses":24,"wins":9},"meta/muse-spark-open":{"draws":0,"losses":16,"wins":4},"meta/muse-wonder":{"draws":1,"losses":32,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":1,"losses":11,"wins":10},"mistralai/mistral-large-4-0":{"draws":6,"losses":12,"wins":4},"mistralai/mistral-medium-3-5":{"draws":5,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":20,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":13,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":5,"wins":2},"o3":{"draws":10,"losses":32,"wins":18},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":12},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":24,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":5,"wins":6},"stealth/ox-alpha":{"draws":17,"losses":88,"wins":19},"stealth/space-bunny-alpha":{"draws":4,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":7},"thinkingmachines/inkling":{"draws":11,"losses":19,"wins":20},"thinkingmachines/inkling-small":{"draws":10,"losses":11,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":0,"losses":27,"wins":9},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":12,"losses":16,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":18,"losses":37,"wins":17},"z-ai/glm-5.3":{"draws":3,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":6,"losses":24,"wins":6}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":4},"claude-fable-5":{"draws":0,"losses":1,"wins":5},"claude-fable-5-1":{"draws":0,"losses":4,"wins":2},"claude-haiku-5-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":0,"wins":10},"claude-opus-4-8":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":5,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":4},"claude-sonnet-5":{"draws":0,"losses":0,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":0,"wins":4},"elorian/glimpse":{"draws":0,"losses":2,"wins":2},"fireworks/ember-1":{"draws":0,"losses":2,"wins":4},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":4},"gemini-4-argon":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"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":1,"wins":9},"google/gemini-3.8-flash":{"draws":0,"losses":2,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":0,"losses":0,"wins":6},"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":3,"wins":3},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":6},"gpt-6-astra":{"draws":0,"losses":2,"wins":4},"gpt-6-luna":{"draws":0,"losses":1,"wins":5},"gpt-6-sol":{"draws":1,"losses":2,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":4,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inception/mercury-3":{"draws":0,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":8},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":1,"wins":5},"meta/muse-spark-open":{"draws":0,"losses":1,"wins":1},"meta/muse-wonder":{"draws":0,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-large-4-0":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":10},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"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":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":1,"wins":5},"stealth/ox-alpha":{"draws":0,"losses":1,"wins":15},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":10},"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":2,"wins":2},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":11},"z-ai/glm-5.3":{"draws":0,"losses":2,"wins":4},"z-ai/glm-5.3-flash":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":6}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":6,"wins":25},"claude-fable-5":{"draws":3,"losses":28,"wins":11},"claude-fable-5-1":{"draws":1,"losses":44,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":13,"wins":22},"claude-opus-4-5":{"draws":13,"losses":14,"wins":41},"claude-opus-4-8":{"draws":7,"losses":13,"wins":18},"claude-opus-5":{"draws":2,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":35,"wins":7},"claude-sonnet-5":{"draws":11,"losses":12,"wins":19},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":40},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":19,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":14,"wins":7},"elorian/glimpse":{"draws":4,"losses":5,"wins":7},"fireworks/ember-1":{"draws":8,"losses":15,"wins":19},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":25},"gemini-4-argon":{"draws":7,"losses":14,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":15,"wins":32},"google/gemini-3.5-flash-lite":{"draws":12,"losses":15,"wins":49},"google/gemini-3.6-flash":{"draws":9,"losses":37,"wins":36},"google/gemini-3.8-flash":{"draws":9,"losses":13,"wins":20},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":13,"wins":19},"gpt-5.4":{"draws":4,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":34},"gpt-5.5":{"draws":10,"losses":14,"wins":16},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":5,"losses":17,"wins":20},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":20},"gpt-6-astra":{"draws":2,"losses":38,"wins":2},"gpt-6-luna":{"draws":8,"losses":10,"wins":24},"gpt-6-sol":{"draws":3,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":18},"inception/mercury-3":{"draws":2,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":34},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":6,"losses":14,"wins":20},"meta/muse-spark-1.3":{"draws":3,"losses":17,"wins":22},"meta/muse-spark-open":{"draws":3,"losses":16,"wins":3},"meta/muse-wonder":{"draws":6,"losses":19,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":3,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":2,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":2},"o3":{"draws":5,"losses":13,"wins":46},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":24},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":15},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":6,"losses":18,"wins":18},"qwen/qwen3.8-max-0902":{"draws":6,"losses":18,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":31,"losses":56,"wins":55},"stealth/space-bunny-alpha":{"draws":9,"losses":8,"wins":17},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":11},"thinkingmachines/inkling":{"draws":13,"losses":5,"wins":40},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":29},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":9,"losses":17,"wins":16},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":10,"losses":8,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3":{"draws":4,"losses":29,"wins":7},"z-ai/glm-5.3-flash":{"draws":2,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":5,"losses":18,"wins":19}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":24,"wins":2},"claude-opus-4-5":{"draws":18,"losses":37,"wins":3},"claude-opus-4-8":{"draws":6,"losses":25,"wins":1},"claude-opus-5":{"draws":10,"losses":43,"wins":5},"claude-opus-5-5":{"draws":5,"losses":31,"wins":0},"claude-sonnet-5":{"draws":10,"losses":23,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":26,"wins":13},"deepseek/deepseek-v4-pro":{"draws":13,"losses":21,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":25,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":12,"wins":1},"elorian/glimpse":{"draws":4,"losses":4,"wins":2},"fireworks/ember-1":{"draws":8,"losses":27,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":7},"gemini-4-argon":{"draws":2,"losses":15,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":36,"wins":3},"google/gemini-3.5-flash-lite":{"draws":16,"losses":32,"wins":18},"google/gemini-3.6-flash":{"draws":14,"losses":54,"wins":4},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":7},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":23,"wins":2},"gpt-5.4":{"draws":9,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":20,"wins":10},"gpt-5.5":{"draws":13,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":21,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":32,"wins":1},"gpt-5.6-terra":{"draws":9,"losses":22,"wins":3},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":10,"losses":24,"wins":2},"gpt-6-sol":{"draws":4,"losses":31,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":8,"wins":10},"inception/mercury-3":{"draws":3,"losses":4,"wins":1},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":23,"wins":7},"meta/muse-glimmer-30b":{"draws":9,"losses":17,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":31,"wins":1},"meta/muse-spark-open":{"draws":3,"losses":16,"wins":1},"meta/muse-wonder":{"draws":8,"losses":27,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":8},"minimax/minimax-m3.1-flash":{"draws":4,"losses":9,"wins":3},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":4},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":4,"wins":1},"o3":{"draws":5,"losses":46,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.7-max":{"draws":3,"losses":15,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":28,"wins":1},"qwen/qwen3.8-27b":{"draws":6,"losses":19,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":8,"losses":28,"wins":0},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":34,"losses":77,"wins":15},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":17,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":25,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":19,"wins":8},"thinkingmachines/inkling-small":{"draws":11,"losses":13,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":27,"wins":1},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":14,"losses":29,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":15,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":43,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":2,"losses":31,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":1}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":16,"wins":12},"claude-fable-5":{"draws":12,"losses":32,"wins":4},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":3},"claude-opus-4-5":{"draws":23,"losses":47,"wins":8},"claude-opus-4-8":{"draws":14,"losses":26,"wins":4},"claude-opus-5":{"draws":13,"losses":63,"wins":6},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":16,"losses":25,"wins":7},"claude-sonnet-5-5":{"draws":11,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":31,"losses":27,"wins":14},"deepseek/deepseek-v4-pro":{"draws":11,"losses":27,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":25,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":18,"wins":1},"elorian/glimpse":{"draws":4,"losses":7,"wins":3},"fireworks/ember-1":{"draws":17,"losses":26,"wins":5},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":6},"gemini-4-argon":{"draws":0,"losses":21,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":16,"losses":32,"wins":12},"google/gemini-3.5-flash-lite":{"draws":30,"losses":39,"wins":15},"google/gemini-3.6-flash":{"draws":25,"losses":52,"wins":15},"google/gemini-3.8-flash":{"draws":13,"losses":27,"wins":8},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":5},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":13,"losses":21,"wins":8},"gpt-5.4":{"draws":16,"losses":27,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":25,"wins":10},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":15,"losses":22,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":12,"losses":28,"wins":8},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":9,"wins":10},"inception/mercury-3":{"draws":7,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":22,"wins":16},"meta/muse-glimmer-30b":{"draws":18,"losses":16,"wins":8},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":10},"meta/muse-spark-1.3":{"draws":8,"losses":35,"wins":5},"meta/muse-spark-open":{"draws":2,"losses":18,"wins":2},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":4},"minimax/minimax-m3.1-flash":{"draws":8,"losses":12,"wins":6},"mistralai/mistral-large-4-0":{"draws":10,"losses":15,"wins":5},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":7},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":17,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":10,"wins":1},"o3":{"draws":12,"losses":44,"wins":10},"openai/gpt-oss-120b":{"draws":14,"losses":20,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":22,"wins":6},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":31,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":14,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":26,"wins":8},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":12,"wins":4},"stealth/ox-alpha":{"draws":48,"losses":89,"wins":21},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":2},"tencent/hy4-preview":{"draws":14,"losses":28,"wins":4},"thinkingmachines/inkling":{"draws":21,"losses":32,"wins":11},"thinkingmachines/inkling-small":{"draws":12,"losses":12,"wins":8},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":39,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":26,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":35,"losses":44,"wins":17},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":34,"wins":4},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":7,"wins":5},"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":10,"wins":2},"claude-opus-4-5":{"draws":1,"losses":18,"wins":1},"claude-opus-4-8":{"draws":0,"losses":12,"wins":0},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":1,"losses":10,"wins":1},"claude-sonnet-5-5":{"draws":0,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":11,"wins":3},"deepseek/deepseek-v4-pro":{"draws":1,"losses":9,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":10,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":8,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":2},"fireworks/ember-1":{"draws":0,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":3},"gemini-4-argon":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":12,"wins":3},"google/gemini-3.5-flash-lite":{"draws":9,"losses":10,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":20,"wins":2},"google/gemini-3.8-flash":{"draws":1,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":2},"gpt-4.1":{"draws":0,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":10,"wins":0},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":11,"wins":3},"gpt-5.5":{"draws":0,"losses":9,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":8,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":12,"wins":0},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":0,"losses":11,"wins":1},"gpt-6-sol":{"draws":1,"losses":9,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":12,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":4,"wins":4},"inception/mercury-3":{"draws":0,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"meta/muse-glimmer-30b":{"draws":1,"losses":3,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":9,"wins":1},"meta/muse-spark-open":{"draws":0,"losses":8,"wins":0},"meta/muse-wonder":{"draws":0,"losses":12,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":0,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":7,"wins":3},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":0},"o3":{"draws":5,"losses":16,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":12,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":12,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":3,"losses":26,"wins":3},"stealth/space-bunny-alpha":{"draws":0,"losses":7,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":2,"losses":10,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":10,"wins":3},"thinkingmachines/inkling-small":{"draws":0,"losses":7,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":10,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":7,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":2},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":6,"losses":26,"wins":16},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":21},"claude-opus-4-5":{"draws":19,"losses":19,"wins":40},"claude-opus-4-8":{"draws":7,"losses":15,"wins":22},"claude-opus-5":{"draws":12,"losses":55,"wins":15},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":12,"losses":11,"wins":25},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":51},"deepseek/deepseek-v4-pro":{"draws":8,"losses":12,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":14,"wins":10},"elorian/glimpse":{"draws":2,"losses":6,"wins":4},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":11,"wins":27},"gemini-4-argon":{"draws":1,"losses":13,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":21,"wins":29},"google/gemini-3.5-flash-lite":{"draws":18,"losses":14,"wins":52},"google/gemini-3.6-flash":{"draws":23,"losses":28,"wins":41},"google/gemini-3.8-flash":{"draws":8,"losses":15,"wins":25},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":18},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":7,"wins":27},"gpt-5.4":{"draws":14,"losses":17,"wins":15},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":27},"gpt-5.5":{"draws":13,"losses":11,"wins":20},"gpt-5.6-luna":{"draws":15,"losses":8,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":7,"wins":25},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":11,"losses":14,"wins":23},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":6,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":36},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":11,"losses":10,"wins":25},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":21},"meta/muse-spark-open":{"draws":2,"losses":8,"wins":14},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"minimax/minimax-m3.1-flash":{"draws":5,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":3,"wins":5},"o3":{"draws":7,"losses":17,"wins":42},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":30},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":23},"qwen/qwen3.8-flash":{"draws":12,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":0,"wins":11},"stealth/ox-alpha":{"draws":31,"losses":46,"wins":81},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":7,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":22},"thinkingmachines/inkling":{"draws":19,"losses":5,"wins":40},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":8,"wins":16},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":16},"x-ai/grok-4.7":{"draws":6,"losses":24,"wins":12},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":20,"losses":5,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":12,"wins":14},"z-ai/glm-5.2":{"draws":25,"losses":15,"wins":56},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":16,"wins":24},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":2,"wins":37},"claude-fable-5":{"draws":8,"losses":17,"wins":23},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-5":{"draws":15,"losses":11,"wins":52},"claude-opus-4-8":{"draws":11,"losses":9,"wins":24},"claude-opus-5":{"draws":10,"losses":50,"wins":22},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":7,"losses":15,"wins":26},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":57},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":11,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":7,"wins":10},"elorian/glimpse":{"draws":3,"losses":2,"wins":7},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":11,"losses":7,"wins":30},"gemini-4-argon":{"draws":5,"losses":19,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":41},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":68},"google/gemini-3.6-flash":{"draws":20,"losses":17,"wins":55},"google/gemini-3.8-flash":{"draws":11,"losses":15,"wins":22},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":24},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":3,"wins":29},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":23},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":44},"gpt-5.5":{"draws":8,"losses":13,"wins":23},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":35},"gpt-5.6-sol":{"draws":10,"losses":15,"wins":23},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":2,"losses":40,"wins":6},"gpt-6-luna":{"draws":8,"losses":2,"wins":38},"gpt-6-sol":{"draws":9,"losses":25,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":26},"inception/mercury-3":{"draws":4,"losses":1,"wins":11},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":39},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":35},"meta/muse-spark-1.2":{"draws":7,"losses":7,"wins":32},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":27},"meta/muse-spark-open":{"draws":5,"losses":2,"wins":15},"meta/muse-wonder":{"draws":10,"losses":16,"wins":22},"minimax/minimax-m3":{"draws":7,"losses":0,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":4,"wins":11},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":18},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":10,"wins":26},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":8},"o3":{"draws":9,"losses":3,"wins":54},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":34},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":40},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":9,"wins":29},"qwen/qwen3.8-27b":{"draws":7,"losses":3,"wins":24},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":19},"qwen/qwen3.8-max":{"draws":12,"losses":6,"wins":30},"qwen/qwen3.8-max-0902":{"draws":11,"losses":8,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":6,"wins":10},"stealth/ox-alpha":{"draws":30,"losses":29,"wins":99},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":8,"losses":7,"wins":31},"thinkingmachines/inkling":{"draws":19,"losses":3,"wins":42},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":38},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":14,"losses":9,"wins":25},"x-ai/grok-4.6":{"draws":12,"losses":7,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":19,"wins":17},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":21,"losses":1,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":16},"z-ai/glm-5.2":{"draws":20,"losses":8,"wins":68},"z-ai/glm-5.3":{"draws":8,"losses":20,"wins":18},"z-ai/glm-5.3-flash":{"draws":12,"losses":11,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":36},"claude-fable-5":{"draws":1,"losses":5,"wins":36},"claude-fable-5-1":{"draws":2,"losses":30,"wins":16},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":36},"claude-opus-4-5":{"draws":2,"losses":3,"wins":63},"claude-opus-4-8":{"draws":2,"losses":5,"wins":31},"claude-opus-5":{"draws":9,"losses":26,"wins":45},"claude-opus-5-5":{"draws":6,"losses":28,"wins":12},"claude-sonnet-5":{"draws":3,"losses":4,"wins":35},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":10,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":5,"wins":18},"elorian/glimpse":{"draws":1,"losses":0,"wins":5},"fireworks/ember-1":{"draws":2,"losses":5,"wins":35},"gemini-3.1-pro-preview":{"draws":5,"losses":4,"wins":33},"gemini-4-argon":{"draws":3,"losses":12,"wins":7},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":1,"losses":7,"wins":44},"google/gemini-3.5-flash-lite":{"draws":6,"losses":8,"wins":58},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":71},"google/gemini-3.8-flash":{"draws":0,"losses":5,"wins":37},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":22},"gpt-4.1":{"draws":1,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":0,"wins":37},"gpt-5.4":{"draws":2,"losses":5,"wins":33},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":34},"gpt-5.5":{"draws":0,"losses":8,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":29},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":35},"gpt-6-astra":{"draws":5,"losses":28,"wins":9},"gpt-6-luna":{"draws":3,"losses":1,"wins":38},"gpt-6-sol":{"draws":3,"losses":15,"wins":24},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":25},"inception/mercury-3":{"draws":0,"losses":1,"wins":13},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":36},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":33},"meta/muse-spark-open":{"draws":2,"losses":3,"wins":13},"meta/muse-wonder":{"draws":1,"losses":10,"wins":31},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":20},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":35},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":10},"o3":{"draws":3,"losses":2,"wins":49},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":36},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":1,"losses":3,"wins":24},"qwen/qwen3.8-max":{"draws":2,"losses":5,"wins":35},"qwen/qwen3.8-max-0902":{"draws":3,"losses":5,"wins":34},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":3,"wins":10},"stealth/ox-alpha":{"draws":14,"losses":13,"wins":115},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":30},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":1,"losses":8,"wins":31},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":51},"thinkingmachines/inkling-small":{"draws":2,"losses":1,"wins":39},"unbiased/pareto-26.10":{"draws":2,"losses":4,"wins":4},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":34},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":34},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":13},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":21},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":2,"losses":9,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":28},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":33}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":18,"wins":10},"claude-fable-5":{"draws":11,"losses":31,"wins":6},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":27,"losses":40,"wins":11},"claude-opus-4-8":{"draws":10,"losses":28,"wins":6},"claude-opus-5":{"draws":13,"losses":65,"wins":4},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":19,"losses":26,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":27,"wins":18},"deepseek/deepseek-v4-pro":{"draws":18,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":19,"wins":5},"elorian/glimpse":{"draws":4,"losses":10,"wins":6},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"gemini-4-argon":{"draws":0,"losses":27,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":20,"losses":31,"wins":9},"google/gemini-3.5-flash-lite":{"draws":34,"losses":26,"wins":24},"google/gemini-3.6-flash":{"draws":30,"losses":57,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":9},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":18,"wins":9},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":23,"wins":14},"gpt-5.5":{"draws":23,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":24,"wins":5},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":8,"wins":8},"inception/mercury-3":{"draws":4,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":16,"wins":17},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":14},"meta/muse-spark-1.2":{"draws":10,"losses":28,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":6,"losses":17,"wins":3},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":8,"wins":10},"minimax/minimax-m3.1-flash":{"draws":10,"losses":14,"wins":4},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":9,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":10,"wins":2},"o3":{"draws":13,"losses":38,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":21,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":17,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":11,"wins":1},"stealth/ox-alpha":{"draws":40,"losses":100,"wins":18},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":5},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":26},"thinkingmachines/inkling-small":{"draws":20,"losses":14,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":20,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":42,"losses":36,"wins":18},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":35,"wins":13},"claude-fable-5":{"draws":20,"losses":67,"wins":3},"claude-fable-5-1":{"draws":6,"losses":91,"wins":3},"claude-haiku-5-5":{"draws":28,"losses":52,"wins":10},"claude-opus-4-5":{"draws":57,"losses":73,"wins":20},"claude-opus-4-8":{"draws":33,"losses":51,"wins":6},"claude-opus-5":{"draws":24,"losses":122,"wins":16},"claude-opus-5-5":{"draws":5,"losses":89,"wins":4},"claude-sonnet-5":{"draws":37,"losses":38,"wins":15},"claude-sonnet-5-5":{"draws":23,"losses":55,"wins":12},"cohere/north-mini-code":{"draws":9,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":53,"losses":38,"wins":43},"deepseek/deepseek-v4-pro":{"draws":30,"losses":40,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":40,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":49,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":37,"wins":1},"elorian/glimpse":{"draws":12,"losses":8,"wins":4},"fireworks/ember-1":{"draws":34,"losses":48,"wins":8},"gemini-3.1-pro-preview":{"draws":35,"losses":37,"wins":18},"gemini-4-argon":{"draws":3,"losses":30,"wins":1},"google/gemini-3.1-flash-lite":{"draws":23,"losses":13,"wins":28},"google/gemini-3.5-flash":{"draws":36,"losses":59,"wins":19},"google/gemini-3.5-flash-lite":{"draws":54,"losses":48,"wins":54},"google/gemini-3.6-flash":{"draws":59,"losses":100,"wins":11},"google/gemini-3.8-flash":{"draws":25,"losses":58,"wins":7},"google/gemma-4-31b-it":{"draws":28,"losses":15,"wins":13},"gpt-4.1":{"draws":14,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":25,"losses":35,"wins":16},"gpt-5.4":{"draws":26,"losses":48,"wins":10},"gpt-5.4-mini":{"draws":25,"losses":23,"wins":12},"gpt-5.4-nano":{"draws":24,"losses":38,"wins":30},"gpt-5.5":{"draws":32,"losses":45,"wins":5},"gpt-5.6-luna":{"draws":39,"losses":33,"wins":18},"gpt-5.6-sol":{"draws":17,"losses":72,"wins":1},"gpt-5.6-terra":{"draws":32,"losses":48,"wins":6},"gpt-6-astra":{"draws":4,"losses":85,"wins":1},"gpt-6-luna":{"draws":36,"losses":41,"wins":13},"gpt-6-sol":{"draws":16,"losses":69,"wins":5},"gpt-6.1-sol":{"draws":8,"losses":80,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":36,"losses":10,"wins":24},"inception/mercury-3":{"draws":8,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":29,"losses":13,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":31,"wins":32},"meta/muse-glimmer-30b":{"draws":31,"losses":27,"wins":22},"meta/muse-spark-1.2":{"draws":29,"losses":51,"wins":8},"meta/muse-spark-1.3":{"draws":26,"losses":56,"wins":8},"meta/muse-spark-open":{"draws":13,"losses":41,"wins":2},"meta/muse-wonder":{"draws":26,"losses":60,"wins":4},"minimax/minimax-m3":{"draws":21,"losses":16,"wins":15},"minimax/minimax-m3.1-flash":{"draws":15,"losses":15,"wins":10},"mistralai/mistral-large-4-0":{"draws":24,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":27,"losses":8,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":32,"losses":43,"wins":13},"nex-agi/nex-n2-pro":{"draws":11,"losses":14,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":32,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":14,"wins":2},"o3":{"draws":22,"losses":79,"wins":17},"openai/gpt-oss-120b":{"draws":31,"losses":24,"wins":23},"poolside/laguna-s-2.1":{"draws":23,"losses":30,"wins":27},"qwen/qwen3.7-max":{"draws":22,"losses":25,"wins":7},"qwen/qwen3.7-plus":{"draws":21,"losses":17,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":44,"wins":7},"qwen/qwen3.8-27b":{"draws":21,"losses":34,"wins":7},"qwen/qwen3.8-flash":{"draws":24,"losses":22,"wins":14},"qwen/qwen3.8-max":{"draws":36,"losses":44,"wins":10},"qwen/qwen3.8-max-0902":{"draws":31,"losses":46,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":19,"wins":4},"stealth/ox-alpha":{"draws":75,"losses":144,"wins":35},"stealth/space-bunny-alpha":{"draws":32,"losses":29,"wins":13},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":19},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":13},"tencent/hy4-preview":{"draws":27,"losses":47,"wins":10},"thinkingmachines/inkling":{"draws":43,"losses":31,"wins":42},"thinkingmachines/inkling-small":{"draws":37,"losses":29,"wins":24},"unbiased/pareto-26.10":{"draws":3,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":30,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":3},"x-ai/grok-4.5":{"draws":27,"losses":59,"wins":4},"x-ai/grok-4.6":{"draws":26,"losses":57,"wins":7},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":6},"x-ai/grok-build-0.1":{"draws":15,"losses":8,"wins":7},"xiaomi/mimo-v2.5":{"draws":59,"losses":35,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":20,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":33,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":38,"wins":4},"z-ai/glm-5.2":{"draws":68,"losses":78,"wins":34},"z-ai/glm-5.3":{"draws":24,"losses":61,"wins":1},"z-ai/glm-5.3-flash":{"draws":27,"losses":52,"wins":11},"z-ai/glm-5.3-flashx":{"draws":35,"losses":50,"wins":5}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":16},"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":10},"claude-opus-4-5":{"draws":14,"losses":24,"wins":22},"claude-opus-4-8":{"draws":7,"losses":20,"wins":9},"claude-opus-5":{"draws":8,"losses":46,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":3,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":12,"wins":27},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":12,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":15,"wins":10},"elorian/glimpse":{"draws":1,"losses":8,"wins":5},"fireworks/ember-1":{"draws":10,"losses":14,"wins":12},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":15},"gemini-4-argon":{"draws":0,"losses":12,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":20,"losses":16,"wins":30},"google/gemini-3.6-flash":{"draws":16,"losses":37,"wins":17},"google/gemini-3.8-flash":{"draws":6,"losses":23,"wins":7},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":12},"gpt-4.1":{"draws":3,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":9},"gpt-5.4":{"draws":5,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":5,"losses":13,"wins":22},"gpt-5.5":{"draws":8,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":9,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":17,"wins":8},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":8,"losses":16,"wins":12},"gpt-6-sol":{"draws":4,"losses":29,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":4,"wins":15},"inception/mercury-3":{"draws":3,"losses":4,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":14},"meta/muse-spark-1.2":{"draws":2,"losses":18,"wins":14},"meta/muse-spark-1.3":{"draws":5,"losses":20,"wins":11},"meta/muse-spark-open":{"draws":3,"losses":10,"wins":1},"meta/muse-wonder":{"draws":3,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":10},"minimax/minimax-m3.1-flash":{"draws":3,"losses":6,"wins":9},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":6,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":6,"wins":5},"o3":{"draws":7,"losses":22,"wins":31},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":16},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":17,"wins":13},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":14},"qwen/qwen3.8-flash":{"draws":5,"losses":11,"wins":8},"qwen/qwen3.8-max":{"draws":1,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":5,"losses":19,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":5,"wins":5},"stealth/ox-alpha":{"draws":15,"losses":52,"wins":35},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":8,"losses":10,"wins":30},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":5,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":16},"x-ai/grok-4.6":{"draws":7,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":0,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":12,"wins":11},"z-ai/glm-5.2":{"draws":20,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":23,"wins":10},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":11}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":9,"wins":32},"claude-fable-5":{"draws":5,"losses":25,"wins":18},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":9,"losses":20,"wins":17},"claude-opus-4-5":{"draws":11,"losses":18,"wins":49},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":8,"losses":63,"wins":11},"claude-opus-5-5":{"draws":5,"losses":45,"wins":2},"claude-sonnet-5":{"draws":6,"losses":10,"wins":32},"claude-sonnet-5-5":{"draws":2,"losses":23,"wins":23},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":50},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":22,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":12,"wins":5},"elorian/glimpse":{"draws":2,"losses":2,"wins":2},"fireworks/ember-1":{"draws":5,"losses":18,"wins":25},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"gemini-4-argon":{"draws":0,"losses":25,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":18,"wins":33},"google/gemini-3.5-flash-lite":{"draws":14,"losses":10,"wins":60},"google/gemini-3.6-flash":{"draws":9,"losses":35,"wins":48},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":21},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":10,"wins":27},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":29},"gpt-5.5":{"draws":6,"losses":19,"wins":19},"gpt-5.6-luna":{"draws":10,"losses":10,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":7,"losses":16,"wins":23},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":8,"losses":13,"wins":27},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":25},"inception/mercury-3":{"draws":3,"losses":6,"wins":9},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":9,"wins":32},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":18},"meta/muse-spark-1.3":{"draws":8,"losses":21,"wins":19},"meta/muse-spark-open":{"draws":1,"losses":17,"wins":6},"meta/muse-wonder":{"draws":1,"losses":31,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"minimax/minimax-m3.1-flash":{"draws":1,"losses":5,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":13,"wins":24},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":7},"o3":{"draws":9,"losses":15,"wins":42},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":16,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":6,"losses":17,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":12,"wins":13},"stealth/ox-alpha":{"draws":22,"losses":61,"wins":75},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":13,"losses":9,"wins":42},"thinkingmachines/inkling-small":{"draws":13,"losses":1,"wins":34},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":19,"wins":26},"x-ai/grok-4.6":{"draws":8,"losses":19,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":11,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":12,"losses":20,"wins":64},"z-ai/glm-5.3":{"draws":7,"losses":28,"wins":11},"z-ai/glm-5.3-flash":{"draws":7,"losses":18,"wins":23},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":38},"claude-fable-5":{"draws":2,"losses":15,"wins":31},"claude-fable-5-1":{"draws":9,"losses":38,"wins":7},"claude-haiku-5-5":{"draws":4,"losses":11,"wins":31},"claude-opus-4-5":{"draws":11,"losses":8,"wins":59},"claude-opus-4-8":{"draws":2,"losses":13,"wins":29},"claude-opus-5":{"draws":16,"losses":39,"wins":27},"claude-opus-5-5":{"draws":4,"losses":39,"wins":9},"claude-sonnet-5":{"draws":0,"losses":9,"wins":39},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":9,"wins":60},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":9,"wins":13},"elorian/glimpse":{"draws":3,"losses":7,"wins":4},"fireworks/ember-1":{"draws":7,"losses":11,"wins":30},"gemini-3.1-pro-preview":{"draws":2,"losses":9,"wins":37},"gemini-4-argon":{"draws":2,"losses":11,"wins":7},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":30},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":72},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":64},"google/gemini-3.8-flash":{"draws":7,"losses":8,"wins":33},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":26},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":8,"wins":32},"gpt-5.4":{"draws":5,"losses":14,"wins":27},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":25},"gpt-5.4-nano":{"draws":0,"losses":8,"wins":40},"gpt-5.5":{"draws":8,"losses":10,"wins":26},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":40},"gpt-5.6-sol":{"draws":9,"losses":14,"wins":25},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":30},"gpt-6-astra":{"draws":5,"losses":37,"wins":6},"gpt-6-luna":{"draws":9,"losses":10,"wins":29},"gpt-6-sol":{"draws":8,"losses":21,"wins":19},"gpt-6.1-sol":{"draws":8,"losses":27,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":2,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":43},"meta/muse-glimmer-30b":{"draws":0,"losses":7,"wins":35},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":35},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-spark-open":{"draws":3,"losses":6,"wins":17},"meta/muse-wonder":{"draws":9,"losses":15,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":22},"minimax/minimax-m3.1-flash":{"draws":1,"losses":3,"wins":16},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":31},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":5,"wins":7},"o3":{"draws":1,"losses":8,"wins":57},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":40},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":27},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":24},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":36},"qwen/qwen3.8-max-0902":{"draws":4,"losses":11,"wins":33},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":3,"wins":16},"stealth/ox-alpha":{"draws":14,"losses":37,"wins":107},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":27},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":10,"wins":30},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":43},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":9,"losses":11,"wins":28},"x-ai/grok-4.7":{"draws":1,"losses":25,"wins":16},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":7,"losses":9,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":13},"z-ai/glm-5.2":{"draws":9,"losses":15,"wins":72},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":26},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":30}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":16,"wins":44},"claude-fable-5":{"draws":20,"losses":60,"wins":16},"claude-fable-5-1":{"draws":9,"losses":96,"wins":3},"claude-haiku-5-5":{"draws":23,"losses":40,"wins":29},"claude-opus-4-5":{"draws":55,"losses":46,"wins":55},"claude-opus-4-8":{"draws":27,"losses":38,"wins":23},"claude-opus-5":{"draws":25,"losses":130,"wins":9},"claude-opus-5-5":{"draws":5,"losses":94,"wins":5},"claude-sonnet-5":{"draws":25,"losses":35,"wins":36},"claude-sonnet-5-5":{"draws":19,"losses":52,"wins":25},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":53,"losses":31,"wins":60},"deepseek/deepseek-v4-pro":{"draws":34,"losses":29,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":32,"wins":11},"elorian/glimpse":{"draws":6,"losses":8,"wins":10},"fireworks/ember-1":{"draws":33,"losses":40,"wins":23},"gemini-3.1-pro-preview":{"draws":32,"losses":29,"wins":35},"gemini-4-argon":{"draws":3,"losses":40,"wins":1},"google/gemini-3.1-flash-lite":{"draws":19,"losses":5,"wins":40},"google/gemini-3.5-flash":{"draws":43,"losses":35,"wins":42},"google/gemini-3.5-flash-lite":{"draws":62,"losses":33,"wins":73},"google/gemini-3.6-flash":{"draws":44,"losses":76,"wins":64},"google/gemini-3.8-flash":{"draws":24,"losses":48,"wins":24},"google/gemma-4-31b-it":{"draws":25,"losses":8,"wins":23},"gpt-4.1":{"draws":13,"losses":5,"wins":14},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":4},"gpt-5":{"draws":31,"losses":25,"wins":28},"gpt-5.4":{"draws":30,"losses":37,"wins":25},"gpt-5.4-mini":{"draws":31,"losses":9,"wins":24},"gpt-5.4-nano":{"draws":29,"losses":26,"wins":41},"gpt-5.5":{"draws":37,"losses":37,"wins":14},"gpt-5.6-luna":{"draws":43,"losses":19,"wins":34},"gpt-5.6-sol":{"draws":12,"losses":60,"wins":24},"gpt-5.6-terra":{"draws":41,"losses":28,"wins":23},"gpt-6-astra":{"draws":8,"losses":82,"wins":6},"gpt-6-luna":{"draws":31,"losses":35,"wins":30},"gpt-6-sol":{"draws":12,"losses":72,"wins":12},"gpt-6.1-sol":{"draws":15,"losses":78,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":32,"losses":3,"wins":33},"inception/mercury-3":{"draws":12,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":37,"losses":5,"wins":26},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":23,"wins":48},"meta/muse-glimmer-30b":{"draws":38,"losses":14,"wins":32},"meta/muse-spark-1.2":{"draws":24,"losses":45,"wins":23},"meta/muse-spark-1.3":{"draws":23,"losses":45,"wins":28},"meta/muse-spark-open":{"draws":14,"losses":24,"wins":10},"meta/muse-wonder":{"draws":26,"losses":52,"wins":18},"minimax/minimax-m3":{"draws":14,"losses":11,"wins":27},"minimax/minimax-m3.1-flash":{"draws":17,"losses":14,"wins":19},"mistralai/mistral-large-4-0":{"draws":29,"losses":19,"wins":12},"mistralai/mistral-medium-3-5":{"draws":24,"losses":6,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":7,"wins":12},"moonshotai/kimi-k3":{"draws":35,"losses":30,"wins":27},"nex-agi/nex-n2-pro":{"draws":20,"losses":2,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":17,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":24,"losses":50,"wins":58},"openai/gpt-oss-120b":{"draws":39,"losses":10,"wins":35},"poolside/laguna-s-2.1":{"draws":49,"losses":12,"wins":31},"qwen/qwen3.7-max":{"draws":21,"losses":11,"wins":24},"qwen/qwen3.7-plus":{"draws":16,"losses":9,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":38,"wins":26},"qwen/qwen3.8-27b":{"draws":22,"losses":19,"wins":27},"qwen/qwen3.8-flash":{"draws":21,"losses":24,"wins":19},"qwen/qwen3.8-max":{"draws":28,"losses":38,"wins":30},"qwen/qwen3.8-max-0902":{"draws":32,"losses":42,"wins":22},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":12,"wins":14},"stealth/ox-alpha":{"draws":85,"losses":144,"wins":87},"stealth/space-bunny-alpha":{"draws":31,"losses":19,"wins":26},"stepfun/step-3.7-flash":{"draws":18,"losses":7,"wins":43},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":24,"losses":47,"wins":21},"thinkingmachines/inkling":{"draws":41,"losses":27,"wins":60},"thinkingmachines/inkling-small":{"draws":38,"losses":11,"wins":47},"unbiased/pareto-26.10":{"draws":1,"losses":20,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":29,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":28,"losses":41,"wins":27},"x-ai/grok-4.6":{"draws":27,"losses":51,"wins":18},"x-ai/grok-4.7":{"draws":9,"losses":60,"wins":15},"x-ai/grok-build-0.1":{"draws":16,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":57,"losses":18,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":10,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":31,"wins":15},"z-ai/glm-5.2":{"draws":66,"losses":38,"wins":56},"z-ai/glm-5.3":{"draws":20,"losses":54,"wins":18},"z-ai/glm-5.3-flash":{"draws":26,"losses":42,"wins":28},"z-ai/glm-5.3-flashx":{"draws":31,"losses":41,"wins":24}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":5,"wins":29},"claude-fable-5":{"draws":9,"losses":17,"wins":22},"claude-fable-5-1":{"draws":4,"losses":41,"wins":9},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":28},"claude-opus-4-5":{"draws":15,"losses":5,"wins":58},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":15,"losses":51,"wins":16},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":7,"losses":14,"wins":27},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":56},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":5,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":9,"wins":19},"elorian/glimpse":{"draws":2,"losses":3,"wins":7},"fireworks/ember-1":{"draws":5,"losses":11,"wins":32},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"gemini-4-argon":{"draws":2,"losses":15,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":43},"google/gemini-3.5-flash-lite":{"draws":11,"losses":3,"wins":70},"google/gemini-3.6-flash":{"draws":19,"losses":18,"wins":55},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":28},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":3,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":5,"losses":8,"wins":29},"gpt-5.4":{"draws":5,"losses":12,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":37},"gpt-5.5":{"draws":13,"losses":10,"wins":21},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":9,"losses":22,"wins":17},"gpt-5.6-terra":{"draws":14,"losses":4,"wins":28},"gpt-6-astra":{"draws":7,"losses":39,"wins":2},"gpt-6-luna":{"draws":10,"losses":7,"wins":31},"gpt-6-sol":{"draws":6,"losses":23,"wins":19},"gpt-6.1-sol":{"draws":11,"losses":29,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inception/mercury-3":{"draws":4,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":42},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":34},"meta/muse-spark-1.2":{"draws":6,"losses":13,"wins":27},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":26},"meta/muse-spark-open":{"draws":4,"losses":5,"wins":15},"meta/muse-wonder":{"draws":4,"losses":23,"wins":21},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"minimax/minimax-m3.1-flash":{"draws":4,"losses":1,"wins":17},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":17,"wins":25},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":13},"o3":{"draws":7,"losses":8,"wins":51},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":32},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":29},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":4,"wins":21},"qwen/qwen3.8-max":{"draws":10,"losses":8,"wins":30},"qwen/qwen3.8-max-0902":{"draws":9,"losses":7,"wins":32},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":2,"wins":18},"stealth/ox-alpha":{"draws":21,"losses":38,"wins":99},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":10,"wins":31},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":41},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":11,"losses":14,"wins":23},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":15,"losses":1,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":17,"losses":14,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":8,"wins":13},"z-ai/glm-5.3-flash":{"draws":12,"losses":9,"wins":27},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":6,"wins":27},"claude-fable-5":{"draws":9,"losses":22,"wins":17},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":20,"losses":12,"wins":46},"claude-opus-4-8":{"draws":9,"losses":11,"wins":24},"claude-opus-5":{"draws":9,"losses":55,"wins":18},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"claude-sonnet-5-5":{"draws":5,"losses":24,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":18,"losses":6,"wins":48},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":14,"wins":8},"elorian/glimpse":{"draws":5,"losses":6,"wins":7},"fireworks/ember-1":{"draws":10,"losses":13,"wins":25},"gemini-3.1-pro-preview":{"draws":12,"losses":10,"wins":26},"gemini-4-argon":{"draws":4,"losses":16,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":11,"losses":15,"wins":34},"google/gemini-3.5-flash-lite":{"draws":17,"losses":5,"wins":62},"google/gemini-3.6-flash":{"draws":16,"losses":21,"wins":55},"google/gemini-3.8-flash":{"draws":10,"losses":19,"wins":19},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":8,"losses":10,"wins":24},"gpt-5.4":{"draws":10,"losses":19,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":33},"gpt-5.5":{"draws":9,"losses":14,"wins":21},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":20},"gpt-5.6-terra":{"draws":13,"losses":11,"wins":22},"gpt-6-astra":{"draws":5,"losses":38,"wins":5},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":24},"inception/mercury-3":{"draws":4,"losses":2,"wins":10},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":36},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":6,"losses":18,"wins":22},"meta/muse-spark-1.3":{"draws":11,"losses":14,"wins":23},"meta/muse-spark-open":{"draws":7,"losses":6,"wins":11},"meta/muse-wonder":{"draws":7,"losses":23,"wins":18},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"minimax/minimax-m3.1-flash":{"draws":1,"losses":8,"wins":19},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":15,"wins":22},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":4,"wins":6},"o3":{"draws":10,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":12,"losses":2,"wins":28},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":14,"wins":21},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-max-0902":{"draws":16,"losses":14,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":0,"wins":7},"stealth/ox-alpha":{"draws":30,"losses":46,"wins":82},"stealth/space-bunny-alpha":{"draws":9,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":15,"wins":25},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":48},"thinkingmachines/inkling-small":{"draws":13,"losses":2,"wins":33},"unbiased/pareto-26.10":{"draws":0,"losses":11,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":19,"wins":23},"x-ai/grok-4.6":{"draws":11,"losses":16,"wins":21},"x-ai/grok-4.7":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":3,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":25,"losses":10,"wins":61},"z-ai/glm-5.3":{"draws":10,"losses":21,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":23}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":12,"losses":27,"wins":9},"claude-fable-5-1":{"draws":4,"losses":45,"wins":5},"claude-haiku-5-5":{"draws":7,"losses":26,"wins":13},"claude-opus-4-5":{"draws":22,"losses":18,"wins":38},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":10,"losses":15,"wins":23},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":19},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":16,"wins":6},"elorian/glimpse":{"draws":4,"losses":2,"wins":4},"fireworks/ember-1":{"draws":12,"losses":21,"wins":15},"gemini-3.1-pro-preview":{"draws":7,"losses":15,"wins":26},"gemini-4-argon":{"draws":0,"losses":21,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":22},"google/gemini-3.5-flash":{"draws":16,"losses":18,"wins":26},"google/gemini-3.5-flash-lite":{"draws":15,"losses":26,"wins":43},"google/gemini-3.6-flash":{"draws":17,"losses":41,"wins":34},"google/gemini-3.8-flash":{"draws":10,"losses":25,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":17,"wins":15},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":13,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":13,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":12,"losses":16,"wins":20},"gpt-6-sol":{"draws":4,"losses":34,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":22},"inception/mercury-3":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":13},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-spark-open":{"draws":6,"losses":11,"wins":7},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"minimax/minimax-m3.1-flash":{"draws":5,"losses":7,"wins":12},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":11},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":11,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":8},"o3":{"draws":4,"losses":31,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":14,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":17},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":8,"wins":5},"stealth/ox-alpha":{"draws":31,"losses":64,"wins":63},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":17},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":28},"unbiased/pareto-26.10":{"draws":0,"losses":7,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":8,"losses":22,"wins":18},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":10},"xiaomi/mimo-v2.5":{"draws":26,"losses":10,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":43},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":19,"wins":19},"z-ai/glm-5.3-flashx":{"draws":12,"losses":15,"wins":5}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":5},"claude-fable-5":{"draws":5,"losses":34,"wins":3},"claude-fable-5-1":{"draws":0,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":30,"wins":3},"claude-opus-4-5":{"draws":20,"losses":38,"wins":10},"claude-opus-4-8":{"draws":7,"losses":31,"wins":0},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":10,"losses":28,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":21,"losses":25,"wins":16},"deepseek/deepseek-v4-pro":{"draws":11,"losses":26,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":21,"wins":1},"elorian/glimpse":{"draws":2,"losses":6,"wins":2},"fireworks/ember-1":{"draws":13,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":24,"wins":7},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":11},"google/gemini-3.5-flash":{"draws":10,"losses":33,"wins":11},"google/gemini-3.5-flash-lite":{"draws":22,"losses":35,"wins":19},"google/gemini-3.6-flash":{"draws":19,"losses":54,"wins":9},"google/gemini-3.8-flash":{"draws":9,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":11,"losses":18,"wins":9},"gpt-5.4":{"draws":10,"losses":26,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":15},"gpt-5.5":{"draws":14,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":20,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":26,"wins":4},"gpt-6-astra":{"draws":1,"losses":40,"wins":1},"gpt-6-luna":{"draws":13,"losses":22,"wins":7},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":11},"inception/mercury-3":{"draws":0,"losses":11,"wins":3},"inclusionai/ling-3.0-flash":{"draws":14,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":18,"wins":14},"meta/muse-glimmer-30b":{"draws":16,"losses":15,"wins":7},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":2,"losses":14,"wins":2},"meta/muse-wonder":{"draws":5,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":5,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":11,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":14,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":5,"wins":1},"o3":{"draws":15,"losses":38,"wins":11},"openai/gpt-oss-120b":{"draws":11,"losses":16,"wins":9},"poolside/laguna-s-2.1":{"draws":13,"losses":18,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":11,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":28,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":6},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":2},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":26,"losses":97,"wins":19},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":6},"stepfun/step-3.7-flash":{"draws":10,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":14,"losses":25,"wins":3},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":18},"thinkingmachines/inkling-small":{"draws":16,"losses":11,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":32,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":23,"losses":24,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":2},"z-ai/glm-5.2":{"draws":35,"losses":37,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":29,"wins":6}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":5,"wins":30},"claude-fable-5":{"draws":5,"losses":18,"wins":9},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":7,"losses":15,"wins":24},"claude-opus-4-5":{"draws":19,"losses":16,"wins":43},"claude-opus-4-8":{"draws":12,"losses":15,"wins":17},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":13,"losses":11,"wins":24},"claude-sonnet-5-5":{"draws":14,"losses":22,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":7,"wins":48},"deepseek/deepseek-v4-pro":{"draws":14,"losses":10,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":9,"wins":14},"elorian/glimpse":{"draws":2,"losses":9,"wins":7},"fireworks/ember-1":{"draws":14,"losses":10,"wins":24},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":1,"losses":19,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":14,"losses":16,"wins":30},"google/gemini-3.5-flash-lite":{"draws":22,"losses":12,"wins":50},"google/gemini-3.6-flash":{"draws":21,"losses":32,"wins":39},"google/gemini-3.8-flash":{"draws":11,"losses":19,"wins":18},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":4,"wins":25},"gpt-5.4":{"draws":14,"losses":14,"wins":18},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":10,"losses":3,"wins":35},"gpt-5.5":{"draws":15,"losses":11,"wins":18},"gpt-5.6-luna":{"draws":15,"losses":6,"wins":27},"gpt-5.6-sol":{"draws":9,"losses":23,"wins":16},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":3,"losses":37,"wins":8},"gpt-6-luna":{"draws":11,"losses":10,"wins":27},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inception/mercury-3":{"draws":9,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":12,"losses":1,"wins":29},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":22},"meta/muse-spark-1.3":{"draws":8,"losses":19,"wins":21},"meta/muse-spark-open":{"draws":3,"losses":8,"wins":13},"meta/muse-wonder":{"draws":11,"losses":22,"wins":15},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":18},"minimax/minimax-m3.1-flash":{"draws":4,"losses":7,"wins":7},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":14,"losses":9,"wins":23},"nex-agi/nex-n2-pro":{"draws":7,"losses":1,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":4,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":6},"o3":{"draws":7,"losses":10,"wins":49},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":26},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":14,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":7,"wins":6},"stealth/ox-alpha":{"draws":37,"losses":49,"wins":72},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":7,"losses":17,"wins":22},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":30},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"x-ai/grok-4.7":{"draws":1,"losses":28,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":29,"losses":18,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":8,"losses":19,"wins":21}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":39},"claude-fable-5":{"draws":3,"losses":6,"wins":39},"claude-fable-5-1":{"draws":2,"losses":26,"wins":10},"claude-haiku-5-5":{"draws":2,"losses":6,"wins":38},"claude-opus-4-5":{"draws":7,"losses":2,"wins":69},"claude-opus-4-8":{"draws":4,"losses":3,"wins":37},"claude-opus-5":{"draws":12,"losses":24,"wins":46},"claude-opus-5-5":{"draws":4,"losses":27,"wins":21},"claude-sonnet-5":{"draws":5,"losses":1,"wins":42},"claude-sonnet-5-5":{"draws":5,"losses":12,"wins":31},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":70},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":2,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":4,"wins":16},"elorian/glimpse":{"draws":4,"losses":1,"wins":9},"fireworks/ember-1":{"draws":4,"losses":2,"wins":42},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":45},"gemini-4-argon":{"draws":3,"losses":13,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":51},"google/gemini-3.5-flash-lite":{"draws":11,"losses":0,"wins":73},"google/gemini-3.6-flash":{"draws":13,"losses":3,"wins":76},"google/gemini-3.8-flash":{"draws":2,"losses":6,"wins":40},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":1,"wins":38},"gpt-5.4":{"draws":3,"losses":8,"wins":35},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":2,"losses":6,"wins":36},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":36},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":40},"gpt-6-astra":{"draws":5,"losses":32,"wins":11},"gpt-6-luna":{"draws":4,"losses":1,"wins":43},"gpt-6-sol":{"draws":7,"losses":14,"wins":27},"gpt-6.1-sol":{"draws":6,"losses":23,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inception/mercury-3":{"draws":2,"losses":0,"wins":16},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":37},"meta/muse-spark-1.2":{"draws":4,"losses":1,"wins":41},"meta/muse-spark-1.3":{"draws":6,"losses":6,"wins":36},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":23},"meta/muse-wonder":{"draws":6,"losses":10,"wins":32},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":26},"mistralai/mistral-large-4-0":{"draws":1,"losses":1,"wins":28},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":38},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":10},"o3":{"draws":2,"losses":3,"wins":61},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":39},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":44},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":1,"wins":40},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":28},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":43},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":0,"wins":12},"stealth/ox-alpha":{"draws":15,"losses":9,"wins":134},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":4,"losses":5,"wins":37},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":60},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10":{"draws":1,"losses":4,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":5,"losses":3,"wins":40},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":39},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":6,"wins":21},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":85},"z-ai/glm-5.3":{"draws":4,"losses":10,"wins":32},"z-ai/glm-5.3-flash":{"draws":6,"losses":2,"wins":40},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":39}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":14},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":18,"wins":7},"claude-opus-4-5":{"draws":30,"losses":32,"wins":16},"claude-opus-4-8":{"draws":15,"losses":27,"wins":2},"claude-opus-5":{"draws":10,"losses":66,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":22,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":30,"losses":18,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":14,"wins":4},"elorian/glimpse":{"draws":3,"losses":7,"wins":4},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":23,"wins":10},"gemini-4-argon":{"draws":1,"losses":15,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":20,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":30,"losses":49,"wins":13},"google/gemini-3.8-flash":{"draws":13,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":14,"wins":11},"gpt-5.4":{"draws":18,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":13},"gpt-5.5":{"draws":22,"losses":15,"wins":7},"gpt-5.6-luna":{"draws":22,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":18,"wins":11},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":14},"inception/mercury-3":{"draws":7,"losses":7,"wins":4},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":10,"wins":20},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":23,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-spark-open":{"draws":8,"losses":21,"wins":1},"meta/muse-wonder":{"draws":11,"losses":36,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":12},"minimax/minimax-m3.1-flash":{"draws":10,"losses":5,"wins":7},"mistralai/mistral-large-4-0":{"draws":16,"losses":11,"wins":3},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":9,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":11,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":3},"o3":{"draws":16,"losses":35,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":17,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-27b":{"draws":12,"losses":15,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-max-0902":{"draws":19,"losses":23,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":6,"wins":1},"stealth/ox-alpha":{"draws":43,"losses":84,"wins":31},"stealth/space-bunny-alpha":{"draws":17,"losses":11,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":29,"wins":4},"thinkingmachines/inkling":{"draws":28,"losses":14,"wins":22},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":18},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":16,"losses":26,"wins":6},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":30,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":21,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":34,"wins":27},"z-ai/glm-5.3":{"draws":10,"losses":34,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":17,"wins":13},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":19,"wins":12},"claude-opus-4-5":{"draws":24,"losses":18,"wins":20},"claude-opus-4-8":{"draws":11,"losses":23,"wins":10},"claude-opus-5":{"draws":16,"losses":59,"wins":7},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":17,"losses":21,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":22,"losses":18,"wins":32},"deepseek/deepseek-v4-pro":{"draws":13,"losses":20,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":20,"wins":2},"elorian/glimpse":{"draws":2,"losses":9,"wins":5},"fireworks/ember-1":{"draws":18,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":12,"losses":19,"wins":17},"gemini-4-argon":{"draws":3,"losses":22,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":19},"google/gemini-3.5-flash-lite":{"draws":28,"losses":20,"wins":36},"google/gemini-3.6-flash":{"draws":29,"losses":41,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":22,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":13,"wins":15},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":22},"gpt-5.5":{"draws":22,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":15,"wins":9},"gpt-6-astra":{"draws":2,"losses":40,"wins":6},"gpt-6-luna":{"draws":15,"losses":19,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inception/mercury-3":{"draws":7,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":5,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-spark-open":{"draws":7,"losses":12,"wins":5},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":12,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":6,"wins":14},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":19,"losses":15,"wins":12},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":4,"wins":3},"o3":{"draws":10,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":19},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":12,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":46,"losses":76,"wins":36},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":13},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":24,"losses":11,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":19,"wins":16},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":10,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":26,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":31,"wins":7}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":19},"claude-fable-5":{"draws":7,"losses":29,"wins":6},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":15},"claude-opus-4-5":{"draws":24,"losses":19,"wins":27},"claude-opus-4-8":{"draws":6,"losses":16,"wins":6},"claude-opus-5":{"draws":13,"losses":49,"wins":8},"claude-opus-5-5":{"draws":1,"losses":40,"wins":5},"claude-sonnet-5":{"draws":12,"losses":14,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":11,"wins":3},"elorian/glimpse":{"draws":2,"losses":8,"wins":2},"fireworks/ember-1":{"draws":15,"losses":15,"wins":12},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":19},"gemini-4-argon":{"draws":0,"losses":21,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":24,"losses":10,"wins":40},"google/gemini-3.6-flash":{"draws":18,"losses":40,"wins":22},"google/gemini-3.8-flash":{"draws":8,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":13},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":14,"wins":12},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":23},"gpt-5.5":{"draws":11,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":15,"wins":13},"gpt-6-astra":{"draws":2,"losses":36,"wins":4},"gpt-6-luna":{"draws":9,"losses":16,"wins":17},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":16},"inception/mercury-3":{"draws":7,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":11,"losses":0,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":6,"losses":15,"wins":3},"meta/muse-wonder":{"draws":8,"losses":22,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":4,"losses":10,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":4},"o3":{"draws":7,"losses":28,"wins":27},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":19},"poolside/laguna-s-2.1":{"draws":14,"losses":7,"wins":17},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":16,"wins":12},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":5,"wins":8},"stealth/ox-alpha":{"draws":19,"losses":64,"wins":35},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":15},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":13},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":13,"losses":7,"wins":34},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":7,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":23,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":12,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":23,"losses":29,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":22,"wins":14}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":8,"wins":57},"claude-fable-5":{"draws":24,"losses":23,"wins":37},"claude-fable-5-1":{"draws":12,"losses":63,"wins":19},"claude-haiku-5-5":{"draws":19,"losses":14,"wins":47},"claude-opus-4-5":{"draws":35,"losses":21,"wins":80},"claude-opus-4-8":{"draws":18,"losses":11,"wins":47},"claude-opus-5":{"draws":22,"losses":68,"wins":36},"claude-opus-5-5":{"draws":13,"losses":64,"wins":15},"claude-sonnet-5":{"draws":17,"losses":18,"wins":49},"claude-sonnet-5-5":{"draws":15,"losses":33,"wins":36},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":26},"deepseek/deepseek-v4-flash":{"draws":22,"losses":12,"wins":90},"deepseek/deepseek-v4-pro":{"draws":14,"losses":15,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":12,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":13,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":13,"wins":26},"elorian/glimpse":{"draws":3,"losses":5,"wins":14},"fireworks/ember-1":{"draws":15,"losses":14,"wins":55},"gemini-3.1-pro-preview":{"draws":8,"losses":22,"wins":54},"gemini-4-argon":{"draws":5,"losses":15,"wins":12},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":42},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":71},"google/gemini-3.5-flash-lite":{"draws":25,"losses":16,"wins":105},"google/gemini-3.6-flash":{"draws":37,"losses":37,"wins":86},"google/gemini-3.8-flash":{"draws":16,"losses":24,"wins":44},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":34},"gpt-4.1":{"draws":7,"losses":2,"wins":19},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":15,"losses":9,"wins":50},"gpt-5.4":{"draws":16,"losses":13,"wins":51},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":34},"gpt-5.4-nano":{"draws":12,"losses":6,"wins":64},"gpt-5.5":{"draws":18,"losses":15,"wins":45},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":60},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":49},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":58},"gpt-6-astra":{"draws":11,"losses":58,"wins":15},"gpt-6-luna":{"draws":20,"losses":9,"wins":55},"gpt-6-sol":{"draws":14,"losses":37,"wins":33},"gpt-6.1-sol":{"draws":13,"losses":53,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":42},"inception/mercury-3":{"draws":6,"losses":6,"wins":20},"inclusionai/ling-3.0-flash":{"draws":17,"losses":2,"wins":39},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":68},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":58},"meta/muse-spark-1.2":{"draws":16,"losses":16,"wins":50},"meta/muse-spark-1.3":{"draws":16,"losses":23,"wins":45},"meta/muse-spark-open":{"draws":5,"losses":6,"wins":27},"meta/muse-wonder":{"draws":15,"losses":27,"wins":42},"minimax/minimax-m3":{"draws":11,"losses":0,"wins":35},"minimax/minimax-m3.1-flash":{"draws":7,"losses":3,"wins":28},"mistralai/mistral-large-4-0":{"draws":12,"losses":7,"wins":35},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":17},"moonshotai/kimi-k3":{"draws":19,"losses":22,"wins":41},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":33},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":1,"wins":13},"o3":{"draws":15,"losses":5,"wins":88},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":52},"poolside/laguna-s-2.1":{"draws":16,"losses":6,"wins":62},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":50},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":39},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":33},"qwen/qwen3.8-max":{"draws":21,"losses":19,"wins":44},"qwen/qwen3.8-max-0902":{"draws":17,"losses":19,"wins":48},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":69,"losses":68,"wins":145},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":46},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":44},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":33},"tencent/hy4-preview":{"draws":15,"losses":15,"wins":50},"thinkingmachines/inkling":{"draws":22,"losses":18,"wins":74},"thinkingmachines/inkling-small":{"draws":18,"losses":3,"wins":63},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":20,"wins":7},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":16,"losses":16,"wins":52},"x-ai/grok-4.6":{"draws":17,"losses":23,"wins":44},"x-ai/grok-4.7":{"draws":9,"losses":38,"wins":27},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":19},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":16,"wins":27},"z-ai/glm-5.2":{"draws":41,"losses":13,"wins":114},"z-ai/glm-5.3":{"draws":15,"losses":32,"wins":33},"z-ai/glm-5.3-flash":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3-flashx":{"draws":17,"losses":24,"wins":43}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":38},"claude-fable-5":{"draws":7,"losses":15,"wins":32},"claude-fable-5-1":{"draws":7,"losses":37,"wins":16},"claude-haiku-5-5":{"draws":12,"losses":7,"wins":33},"claude-opus-4-5":{"draws":16,"losses":15,"wins":57},"claude-opus-4-8":{"draws":9,"losses":14,"wins":27},"claude-opus-5":{"draws":17,"losses":50,"wins":27},"claude-opus-5-5":{"draws":1,"losses":33,"wins":10},"claude-sonnet-5":{"draws":11,"losses":10,"wins":33},"claude-sonnet-5-5":{"draws":7,"losses":16,"wins":31},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":66},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":10,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":9,"wins":17},"elorian/glimpse":{"draws":2,"losses":1,"wins":9},"fireworks/ember-1":{"draws":8,"losses":11,"wins":35},"gemini-3.1-pro-preview":{"draws":8,"losses":5,"wins":41},"gemini-4-argon":{"draws":2,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":52},"google/gemini-3.5-flash-lite":{"draws":17,"losses":1,"wins":76},"google/gemini-3.6-flash":{"draws":19,"losses":9,"wins":74},"google/gemini-3.8-flash":{"draws":12,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":27},"gpt-4.1":{"draws":5,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":4,"wins":35},"gpt-5.4":{"draws":10,"losses":4,"wins":38},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":48},"gpt-5.5":{"draws":11,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":10,"losses":12,"wins":32},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":42},"gpt-6-astra":{"draws":8,"losses":34,"wins":12},"gpt-6-luna":{"draws":13,"losses":1,"wins":40},"gpt-6-sol":{"draws":8,"losses":26,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":30},"inception/mercury-3":{"draws":1,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":46},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":10,"losses":5,"wins":37},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":36},"meta/muse-spark-open":{"draws":6,"losses":4,"wins":20},"meta/muse-wonder":{"draws":6,"losses":20,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":27},"minimax/minimax-m3.1-flash":{"draws":3,"losses":0,"wins":23},"mistralai/mistral-large-4-0":{"draws":11,"losses":2,"wins":21},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":38},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":45},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":11},"o3":{"draws":8,"losses":1,"wins":67},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":9,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":29},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":31},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":12,"losses":5,"wins":37},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":2,"wins":11},"stealth/ox-alpha":{"draws":39,"losses":25,"wins":110},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":24},"tencent/hy4-preview":{"draws":11,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":15,"losses":0,"wins":55},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":46},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":4},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":12,"wins":30},"x-ai/grok-4.6":{"draws":13,"losses":13,"wins":28},"x-ai/grok-4.7":{"draws":8,"losses":22,"wins":18},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":17},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":2,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":17,"losses":10,"wins":81},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":29},"z-ai/glm-5.3-flash":{"draws":7,"losses":6,"wins":41},"z-ai/glm-5.3-flashx":{"draws":10,"losses":6,"wins":38}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":16},"claude-fable-5":{"draws":10,"losses":32,"wins":6},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":28,"losses":31,"wins":19},"claude-opus-4-8":{"draws":13,"losses":23,"wins":8},"claude-opus-5":{"draws":12,"losses":61,"wins":9},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":9,"losses":15,"wins":8},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":3},"elorian/glimpse":{"draws":2,"losses":5,"wins":5},"fireworks/ember-1":{"draws":19,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":15,"losses":20,"wins":13},"gemini-4-argon":{"draws":0,"losses":20,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":29,"wins":15},"google/gemini-3.5-flash-lite":{"draws":25,"losses":20,"wins":39},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":26},"google/gemini-3.8-flash":{"draws":10,"losses":28,"wins":10},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":18,"wins":11},"gpt-5.4":{"draws":13,"losses":25,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":12,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":21},"gpt-5.5":{"draws":17,"losses":21,"wins":6},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":9},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":0,"losses":45,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":6,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":23},"meta/muse-glimmer-30b":{"draws":16,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":26,"wins":7},"meta/muse-spark-open":{"draws":9,"losses":16,"wins":3},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"minimax/minimax-m3.1-flash":{"draws":7,"losses":9,"wins":8},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":13},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":7},"o3":{"draws":11,"losses":27,"wins":28},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":22,"wins":9},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":38,"losses":81,"wins":39},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":23,"wins":9},"thinkingmachines/inkling":{"draws":21,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":27,"wins":10},"x-ai/grok-4.6":{"draws":15,"losses":26,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":30,"losses":17,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":19,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":9},"z-ai/glm-5.2":{"draws":26,"losses":33,"wins":37},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":14,"losses":27,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":18,"wins":18},"claude-fable-5":{"draws":8,"losses":32,"wins":8},"claude-fable-5-1":{"draws":0,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":22,"wins":15},"claude-opus-4-5":{"draws":18,"losses":34,"wins":26},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":15},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":21,"wins":30},"deepseek/deepseek-v4-pro":{"draws":16,"losses":19,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":25,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":20,"wins":2},"elorian/glimpse":{"draws":0,"losses":6,"wins":6},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"gemini-4-argon":{"draws":2,"losses":23,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":10,"wins":14},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":21},"google/gemini-3.5-flash-lite":{"draws":21,"losses":21,"wins":42},"google/gemini-3.6-flash":{"draws":21,"losses":53,"wins":18},"google/gemini-3.8-flash":{"draws":9,"losses":28,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":10,"wins":11},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":14,"wins":18},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":16},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":23},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":11,"losses":27,"wins":10},"gpt-6-sol":{"draws":4,"losses":42,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":17},"inception/mercury-3":{"draws":2,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":28,"wins":8},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":8},"meta/muse-spark-open":{"draws":5,"losses":11,"wins":4},"meta/muse-wonder":{"draws":5,"losses":32,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":8,"losses":9,"wins":7},"mistralai/mistral-large-4-0":{"draws":11,"losses":15,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":14,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":4,"wins":9},"o3":{"draws":8,"losses":30,"wins":28},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":21},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":14,"wins":14},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":25,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":28,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":12,"wins":8},"stealth/ox-alpha":{"draws":42,"losses":90,"wins":26},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":14},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":28,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":24},"thinkingmachines/inkling-small":{"draws":14,"losses":16,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.6":{"draws":9,"losses":30,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":16,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":19,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":42,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":27,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":27,"wins":10}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":10,"wins":2},"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":13,"wins":2},"claude-opus-4-5":{"draws":3,"losses":27,"wins":0},"claude-opus-4-8":{"draws":2,"losses":15,"wins":1},"claude-opus-5":{"draws":0,"losses":32,"wins":0},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":3,"losses":15,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":9,"losses":14,"wins":5},"deepseek/deepseek-v4-pro":{"draws":4,"losses":12,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":12,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":0},"fireworks/ember-1":{"draws":3,"losses":13,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":4},"gemini-4-argon":{"draws":0,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":7,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":15,"wins":3},"google/gemini-3.5-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.6-flash":{"draws":6,"losses":28,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":1},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":6,"losses":12,"wins":0},"gpt-5.4":{"draws":4,"losses":14,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":16,"wins":2},"gpt-5.5":{"draws":4,"losses":14,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":18,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":0},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":4,"losses":12,"wins":2},"gpt-6-sol":{"draws":0,"losses":18,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":6,"wins":2},"inception/mercury-3":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":14,"wins":4},"meta/muse-glimmer-30b":{"draws":6,"losses":9,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":18,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":16,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":14,"wins":0},"meta/muse-wonder":{"draws":0,"losses":18,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":5,"wins":1},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":1},"o3":{"draws":8,"losses":25,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":10,"wins":2},"qwen/qwen3.7-max":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":16,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":9,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":6,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":14,"wins":0},"qwen/qwen3.8-max-0902":{"draws":4,"losses":14,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":5,"losses":46,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":13,"wins":8},"thinkingmachines/inkling-small":{"draws":6,"losses":9,"wins":3},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":18,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":15,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":18,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":13,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":25,"wins":1},"z-ai/glm-5.3":{"draws":3,"losses":15,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":13,"wins":1}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":13,"wins":15},"claude-fable-5":{"draws":8,"losses":34,"wins":0},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":24,"wins":4},"claude-opus-4-5":{"draws":22,"losses":35,"wins":11},"claude-opus-4-8":{"draws":8,"losses":26,"wins":4},"claude-opus-5":{"draws":7,"losses":61,"wins":2},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":9,"losses":24,"wins":9},"claude-sonnet-5-5":{"draws":7,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":18},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":24,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":3},"elorian/glimpse":{"draws":3,"losses":7,"wins":4},"fireworks/ember-1":{"draws":14,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":10},"gemini-4-argon":{"draws":0,"losses":20,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":22,"losses":25,"wins":25},"google/gemini-3.6-flash":{"draws":15,"losses":57,"wins":8},"google/gemini-3.8-flash":{"draws":6,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":2,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":24,"wins":8},"gpt-5.4":{"draws":7,"losses":28,"wins":5},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":18},"gpt-5.5":{"draws":10,"losses":22,"wins":6},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":12},"gpt-5.6-sol":{"draws":5,"losses":30,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":22,"wins":6},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":15},"inception/mercury-3":{"draws":8,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":11,"losses":16,"wins":19},"meta/muse-glimmer-30b":{"draws":16,"losses":12,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":2,"losses":19,"wins":1},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":6},"minimax/minimax-m3.1-flash":{"draws":2,"losses":11,"wins":9},"mistralai/mistral-large-4-0":{"draws":6,"losses":16,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":21,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":3,"wins":2},"o3":{"draws":10,"losses":33,"wins":19},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":10},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":12},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":11,"losses":23,"wins":8},"qwen/qwen3.8-max-0902":{"draws":7,"losses":30,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":6,"wins":2},"stealth/ox-alpha":{"draws":29,"losses":80,"wins":31},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":12},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":9,"losses":24,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":20},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":7,"losses":28,"wins":7},"x-ai/grok-4.6":{"draws":8,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":38,"wins":19},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":13,"losses":22,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":29,"wins":5}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":9},"claude-fable-5":{"draws":8,"losses":24,"wins":4},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":14,"wins":7},"claude-opus-4-5":{"draws":18,"losses":33,"wins":7},"claude-opus-4-8":{"draws":8,"losses":18,"wins":6},"claude-opus-5":{"draws":8,"losses":53,"wins":7},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":13,"losses":13,"wins":10},"claude-sonnet-5-5":{"draws":7,"losses":22,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":18,"losses":10,"wins":24},"deepseek/deepseek-v4-pro":{"draws":5,"losses":13,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":18,"wins":3},"elorian/glimpse":{"draws":4,"losses":6,"wins":2},"fireworks/ember-1":{"draws":12,"losses":18,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":9},"gemini-4-argon":{"draws":0,"losses":13,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":23,"wins":12},"google/gemini-3.5-flash-lite":{"draws":22,"losses":21,"wins":21},"google/gemini-3.6-flash":{"draws":24,"losses":35,"wins":11},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":13,"wins":8},"gpt-5.4":{"draws":8,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":13,"losses":17,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":16,"losses":11,"wins":7},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"wins":8},"gpt-6-sol":{"draws":3,"losses":29,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":7},"inception/mercury-3":{"draws":5,"losses":7,"wins":4},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":19},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":11},"meta/muse-spark-1.2":{"draws":4,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":6},"meta/muse-spark-open":{"draws":3,"losses":10,"wins":5},"meta/muse-wonder":{"draws":2,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":11},"minimax/minimax-m3.1-flash":{"draws":5,"losses":2,"wins":3},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":10},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":6,"wins":3},"o3":{"draws":8,"losses":24,"wins":20},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":14,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":7,"wins":6},"stealth/ox-alpha":{"draws":35,"losses":60,"wins":31},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":18,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":20},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":10},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":17,"wins":7},"x-ai/grok-4.6":{"draws":15,"losses":20,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":23,"losses":12,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":30,"losses":24,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":5,"losses":26,"wins":5},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":4}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":9},"claude-fable-5":{"draws":8,"losses":24,"wins":4},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":3},"claude-opus-4-5":{"draws":21,"losses":28,"wins":9},"claude-opus-4-8":{"draws":5,"losses":23,"wins":4},"claude-opus-5":{"draws":6,"losses":45,"wins":7},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":13,"losses":16,"wins":7},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":17},"deepseek/deepseek-v4-pro":{"draws":15,"losses":11,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":12,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":12,"wins":0},"elorian/glimpse":{"draws":4,"losses":6,"wins":4},"fireworks/ember-1":{"draws":11,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":10},"gemini-4-argon":{"draws":4,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":7},"google/gemini-3.5-flash-lite":{"draws":25,"losses":23,"wins":16},"google/gemini-3.6-flash":{"draws":19,"losses":38,"wins":13},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":3},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":4,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":17,"wins":5},"gpt-5.4":{"draws":9,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":15,"wins":12},"gpt-5.5":{"draws":14,"losses":14,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":12},"gpt-5.6-sol":{"draws":5,"losses":25,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":16,"wins":6},"gpt-6-astra":{"draws":2,"losses":33,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":9},"gpt-6-sol":{"draws":3,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":10},"inception/mercury-3":{"draws":0,"losses":7,"wins":1},"inclusionai/ling-3.0-flash":{"draws":14,"losses":8,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":11,"wins":12},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":10},"meta/muse-spark-1.2":{"draws":8,"losses":19,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":6},"meta/muse-spark-open":{"draws":3,"losses":11,"wins":4},"meta/muse-wonder":{"draws":7,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":5},"minimax/minimax-m3.1-flash":{"draws":4,"losses":12,"wins":6},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":11,"wins":10},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":8,"wins":4},"o3":{"draws":10,"losses":20,"wins":22},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":9},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":20,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":10,"losses":19,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":7,"wins":4},"stealth/ox-alpha":{"draws":39,"losses":62,"wins":23},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":6},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":4},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":7},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":10},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":11},"unbiased/pareto-26.10":{"draws":0,"losses":4,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":8},"x-ai/grok-4.6":{"draws":18,"losses":13,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":23,"losses":13,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":21,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":26,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":20,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":6}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":21,"wins":7},"claude-fable-5":{"draws":11,"losses":32,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":29,"losses":34,"wins":15},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":14,"losses":63,"wins":5},"claude-opus-5-5":{"draws":1,"losses":50,"wins":1},"claude-sonnet-5":{"draws":20,"losses":25,"wins":3},"claude-sonnet-5-5":{"draws":14,"losses":32,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":19,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":16,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":3},"elorian/glimpse":{"draws":5,"losses":5,"wins":4},"fireworks/ember-1":{"draws":18,"losses":27,"wins":3},"gemini-3.1-pro-preview":{"draws":14,"losses":26,"wins":8},"gemini-4-argon":{"draws":0,"losses":24,"wins":0},"google/gemini-3.1-flash-lite":{"draws":16,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":17,"losses":31,"wins":12},"google/gemini-3.5-flash-lite":{"draws":30,"losses":37,"wins":17},"google/gemini-3.6-flash":{"draws":28,"losses":53,"wins":11},"google/gemini-3.8-flash":{"draws":11,"losses":34,"wins":3},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":12,"losses":16,"wins":14},"gpt-5.4":{"draws":17,"losses":27,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":20,"wins":15},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":17,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":18,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":17,"losses":23,"wins":8},"gpt-6-sol":{"draws":9,"losses":32,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":12},"inception/mercury-3":{"draws":5,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":19,"losses":5,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":19,"wins":19},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":31,"wins":9},"meta/muse-spark-open":{"draws":4,"losses":11,"wins":3},"meta/muse-wonder":{"draws":9,"losses":35,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":10,"wins":9},"minimax/minimax-m3.1-flash":{"draws":5,"losses":7,"wins":6},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":8,"wins":0},"o3":{"draws":16,"losses":34,"wins":16},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":7},"poolside/laguna-s-2.1":{"draws":24,"losses":14,"wins":8},"qwen/qwen3.7-max":{"draws":11,"losses":9,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":22,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":6},"stealth/ox-alpha":{"draws":42,"losses":82,"wins":33},"stealth/space-bunny-alpha":{"draws":16,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":14,"wins":26},"thinkingmachines/inkling-small":{"draws":17,"losses":15,"wins":16},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":32,"wins":5},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":28,"losses":20,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":12,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":40,"losses":36,"wins":20},"z-ai/glm-5.3":{"draws":11,"losses":30,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":31,"wins":6},"z-ai/glm-5.3-flashx":{"draws":14,"losses":30,"wins":4}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":2,"wins":17},"claude-fable-5":{"draws":4,"losses":21,"wins":7},"claude-fable-5-1":{"draws":0,"losses":21,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":10,"wins":11},"claude-opus-4-5":{"draws":9,"losses":12,"wins":23},"claude-opus-4-8":{"draws":3,"losses":11,"wins":8},"claude-opus-5":{"draws":7,"losses":33,"wins":14},"claude-opus-5-5":{"draws":2,"losses":27,"wins":3},"claude-sonnet-5":{"draws":8,"losses":5,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":10,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":14,"losses":8,"wins":26},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":8,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":15,"wins":2},"elorian/glimpse":{"draws":7,"losses":9,"wins":6},"fireworks/ember-1":{"draws":9,"losses":7,"wins":12},"gemini-3.1-pro-preview":{"draws":9,"losses":6,"wins":15},"gemini-4-argon":{"draws":4,"losses":36,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":6,"losses":14,"wins":18},"google/gemini-3.5-flash-lite":{"draws":12,"losses":4,"wins":34},"google/gemini-3.6-flash":{"draws":9,"losses":24,"wins":23},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":8},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":10},"gpt-4.1":{"draws":2,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":6,"wins":12},"gpt-5.4":{"draws":8,"losses":16,"wins":8},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":13},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":13},"gpt-5.5":{"draws":13,"losses":10,"wins":7},"gpt-5.6-luna":{"draws":4,"losses":6,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":15,"wins":8},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":12},"gpt-6-astra":{"draws":2,"losses":28,"wins":2},"gpt-6-luna":{"draws":9,"losses":10,"wins":15},"gpt-6-sol":{"draws":2,"losses":16,"wins":10},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":8},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":10},"inception/mercury-3":{"draws":10,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":20},"meta/muse-glimmer-30b":{"draws":8,"losses":4,"wins":16},"meta/muse-spark-1.2":{"draws":5,"losses":6,"wins":11},"meta/muse-spark-1.3":{"draws":1,"losses":15,"wins":10},"meta/muse-spark-open":{"draws":11,"losses":15,"wins":14},"meta/muse-wonder":{"draws":5,"losses":12,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":12},"minimax/minimax-m3.1-flash":{"draws":12,"losses":13,"wins":11},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":4,"losses":12,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":4,"wins":7},"o3":{"draws":4,"losses":22,"wins":26},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":21},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":1,"losses":8,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":11,"wins":9},"qwen/qwen3.8-27b":{"draws":4,"losses":6,"wins":10},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":9},"qwen/qwen3.8-max":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-max-0902":{"draws":8,"losses":8,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":14,"wins":13},"stealth/ox-alpha":{"draws":17,"losses":31,"wins":44},"stealth/space-bunny-alpha":{"draws":7,"losses":1,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":4,"losses":9,"wins":13},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":30},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":19,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":7,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":17,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":8},"z-ai/glm-5.2":{"draws":9,"losses":12,"wins":33},"z-ai/glm-5.3":{"draws":3,"losses":15,"wins":8},"z-ai/glm-5.3-flash":{"draws":4,"losses":13,"wins":14},"z-ai/glm-5.3-flashx":{"draws":2,"losses":13,"wins":9}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":8,"wins":4},"claude-fable-5":{"draws":0,"losses":13,"wins":1},"claude-fable-5-1":{"draws":1,"losses":23,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":10,"wins":2},"claude-opus-4-5":{"draws":0,"losses":15,"wins":7},"claude-opus-4-8":{"draws":2,"losses":11,"wins":1},"claude-opus-5":{"draws":5,"losses":21,"wins":4},"claude-opus-5-5":{"draws":1,"losses":15,"wins":0},"claude-sonnet-5":{"draws":3,"losses":7,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":13,"wins":8},"deepseek/deepseek-v4-pro":{"draws":8,"losses":7,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":10,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":6,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":17,"wins":7},"elorian/glimpse":{"draws":1,"losses":5,"wins":2},"fireworks/ember-1":{"draws":4,"losses":6,"wins":0},"gemini-3.1-pro-preview":{"draws":1,"losses":10,"wins":5},"gemini-4-argon":{"draws":1,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":17,"wins":5},"google/gemini-3.5-flash-lite":{"draws":5,"losses":14,"wins":7},"google/gemini-3.6-flash":{"draws":7,"losses":21,"wins":6},"google/gemini-3.8-flash":{"draws":3,"losses":20,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":7,"wins":1},"gpt-5.4":{"draws":0,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":9,"wins":5},"gpt-5.5":{"draws":2,"losses":20,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":12,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":11,"wins":4},"gpt-6-astra":{"draws":1,"losses":15,"wins":0},"gpt-6-luna":{"draws":1,"losses":12,"wins":5},"gpt-6-sol":{"draws":1,"losses":16,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":11,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":4,"wins":4},"inception/mercury-3":{"draws":0,"losses":14,"wins":4},"inclusionai/ling-3.0-flash":{"draws":3,"losses":6,"wins":5},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":11,"wins":8},"meta/muse-glimmer-30b":{"draws":5,"losses":12,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":12,"wins":0},"meta/muse-spark-1.3":{"draws":5,"losses":14,"wins":1},"meta/muse-spark-open":{"draws":4,"losses":19,"wins":5},"meta/muse-wonder":{"draws":3,"losses":10,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":4},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":10},"mistralai/mistral-large-4-0":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":8,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":9,"wins":3},"o3":{"draws":3,"losses":17,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":7,"wins":1},"poolside/laguna-s-2.1":{"draws":1,"losses":5,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":11,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":10,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":9,"wins":2},"qwen/qwen3.8-max":{"draws":3,"losses":14,"wins":1},"qwen/qwen3.8-max-0902":{"draws":3,"losses":8,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":14,"wins":6},"stealth/ox-alpha":{"draws":11,"losses":40,"wins":13},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":3},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":6},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":12,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":14,"wins":5},"thinkingmachines/inkling-small":{"draws":2,"losses":7,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":10,"wins":2},"x-ai/grok-4.6":{"draws":1,"losses":13,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":8,"losses":7,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":8,"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":2,"losses":20,"wins":4},"z-ai/glm-5.3":{"draws":2,"losses":14,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":11,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":8,"wins":2}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":12,"losses":35,"wins":1},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":34,"losses":28,"wins":16},"claude-opus-4-8":{"draws":17,"losses":24,"wins":3},"claude-opus-5":{"draws":10,"losses":68,"wins":4},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":19,"losses":17,"wins":12},"claude-sonnet-5-5":{"draws":12,"losses":29,"wins":7},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":21,"wins":22},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":16,"wins":4},"elorian/glimpse":{"draws":4,"losses":4,"wins":0},"fireworks/ember-1":{"draws":11,"losses":21,"wins":0},"gemini-3.1-pro-preview":{"draws":20,"losses":17,"wins":11},"gemini-4-argon":{"draws":3,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":23,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":38,"losses":26,"wins":20},"google/gemini-3.6-flash":{"draws":33,"losses":42,"wins":17},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":15,"wins":8},"gpt-5.4":{"draws":18,"losses":26,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":15,"losses":12,"wins":21},"gpt-5.5":{"draws":15,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":18,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":35,"wins":7},"gpt-5.6-terra":{"draws":20,"losses":18,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":21,"wins":12},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":21,"losses":2,"wins":11},"inception/mercury-3":{"draws":8,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":23,"losses":4,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":9,"wins":21},"meta/muse-glimmer-30b":{"draws":22,"losses":5,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":29,"wins":9},"meta/muse-spark-open":{"draws":5,"losses":11,"wins":4},"meta/muse-wonder":{"draws":17,"losses":28,"wins":3},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":12},"minimax/minimax-m3.1-flash":{"draws":9,"losses":5,"wins":6},"mistralai/mistral-large-4-0":{"draws":11,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":17,"wins":10},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":10,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":4,"wins":3},"o3":{"draws":20,"losses":26,"wins":20},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":26,"losses":10,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":21,"wins":6},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":16,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":18,"losses":18,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":24,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":11,"wins":6},"stealth/ox-alpha":{"draws":52,"losses":85,"wins":21},"stealth/space-bunny-alpha":{"draws":16,"losses":10,"wins":12},"stepfun/step-3.7-flash":{"draws":10,"losses":9,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":20,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":24,"losses":20,"wins":20},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":18},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":25,"wins":7},"x-ai/grok-4.7":{"draws":6,"losses":33,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":15,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":41,"losses":32,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":32,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":29,"wins":8},"z-ai/glm-5.3-flashx":{"draws":15,"losses":25,"wins":8}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":18,"wins":12},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":26,"wins":7},"claude-opus-4-5":{"draws":25,"losses":44,"wins":9},"claude-opus-4-8":{"draws":12,"losses":29,"wins":3},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":17,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":10,"wins":4},"deepseek/deepseek-v4-flash":{"draws":28,"losses":26,"wins":18},"deepseek/deepseek-v4-pro":{"draws":14,"losses":24,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":23,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":24,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":27,"wins":2},"elorian/glimpse":{"draws":5,"losses":12,"wins":5},"fireworks/ember-1":{"draws":19,"losses":28,"wins":1},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":4},"gemini-4-argon":{"draws":1,"losses":13,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":10,"wins":12},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":33,"losses":30,"wins":21},"google/gemini-3.6-flash":{"draws":32,"losses":54,"wins":6},"google/gemini-3.8-flash":{"draws":10,"losses":37,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":19,"losses":18,"wins":5},"gpt-5.4":{"draws":14,"losses":29,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":17,"wins":16},"gpt-5.5":{"draws":18,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":21,"wins":8},"gpt-5.6-sol":{"draws":7,"losses":39,"wins":2},"gpt-5.6-terra":{"draws":21,"losses":22,"wins":3},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":8,"losses":36,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":12,"wins":7},"inception/mercury-3":{"draws":10,"losses":14,"wins":4},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":23,"wins":13},"meta/muse-glimmer-30b":{"draws":22,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":28,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":35,"wins":4},"meta/muse-spark-open":{"draws":2,"losses":12,"wins":0},"meta/muse-wonder":{"draws":8,"losses":38,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"minimax/minimax-m3.1-flash":{"draws":10,"losses":7,"wins":3},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":23,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":14,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":9,"wins":0},"o3":{"draws":12,"losses":47,"wins":7},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":18,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":27,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-max-0902":{"draws":15,"losses":30,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":6,"wins":2},"stealth/ox-alpha":{"draws":39,"losses":106,"wins":13},"stealth/space-bunny-alpha":{"draws":15,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":11,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":25,"losses":24,"wins":15},"thinkingmachines/inkling-small":{"draws":19,"losses":16,"wins":13},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":32,"wins":1},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":1},"x-ai/grok-4.7":{"draws":4,"losses":35,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":21,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":38,"losses":40,"wins":18},"z-ai/glm-5.3":{"draws":10,"losses":35,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":29,"wins":4},"z-ai/glm-5.3-flashx":{"draws":10,"losses":34,"wins":4}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":12},"claude-fable-5":{"draws":4,"losses":4,"wins":20},"claude-fable-5-1":{"draws":2,"losses":15,"wins":9},"claude-haiku-5-5":{"draws":3,"losses":1,"wins":14},"claude-opus-4-5":{"draws":3,"losses":3,"wins":38},"claude-opus-4-8":{"draws":1,"losses":7,"wins":10},"claude-opus-5":{"draws":5,"losses":19,"wins":8},"claude-opus-5-5":{"draws":1,"losses":18,"wins":9},"claude-sonnet-5":{"draws":1,"losses":0,"wins":15},"claude-sonnet-5-5":{"draws":4,"losses":9,"wins":15},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":39},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":5,"wins":37},"elorian/glimpse":{"draws":2,"losses":4,"wins":20},"fireworks/ember-1":{"draws":1,"losses":0,"wins":11},"gemini-3.1-pro-preview":{"draws":2,"losses":2,"wins":18},"gemini-4-argon":{"draws":4,"losses":20,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":34},"google/gemini-3.5-flash-lite":{"draws":3,"losses":4,"wins":35},"google/gemini-3.6-flash":{"draws":2,"losses":5,"wins":35},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":14},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":13},"gpt-4.1":{"draws":1,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":5,"wins":15},"gpt-5.4":{"draws":2,"losses":1,"wins":13},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":16},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":13},"gpt-5.5":{"draws":1,"losses":2,"wins":17},"gpt-5.6-luna":{"draws":7,"losses":1,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":13},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":14},"gpt-6-astra":{"draws":5,"losses":12,"wins":3},"gpt-6-luna":{"draws":0,"losses":2,"wins":22},"gpt-6-sol":{"draws":3,"losses":12,"wins":15},"gpt-6.1-sol":{"draws":0,"losses":17,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":21},"inception/mercury-3":{"draws":3,"losses":3,"wins":26},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":17},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":19},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":21},"meta/muse-spark-1.2":{"draws":3,"losses":1,"wins":20},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":16},"meta/muse-spark-open":{"draws":6,"losses":7,"wins":31},"meta/muse-wonder":{"draws":1,"losses":0,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":14},"minimax/minimax-m3.1-flash":{"draws":2,"losses":3,"wins":35},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":1,"losses":1,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":18},"o3":{"draws":0,"losses":1,"wins":17},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":22},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":27},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":14},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":1,"wins":14},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":12},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":9},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":19},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":6,"wins":35},"stealth/ox-alpha":{"draws":6,"losses":6,"wins":52},"stealth/space-bunny-alpha":{"draws":0,"losses":2,"wins":16},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":14},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":2,"losses":7,"wins":17},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":23},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":22},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":4},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":19},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":20},"x-ai/grok-4.7":{"draws":4,"losses":2,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":10},"z-ai/glm-5.2":{"draws":4,"losses":3,"wins":31},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":9},"z-ai/glm-5.3-flash":{"draws":2,"losses":7,"wins":19},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":15}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":14,"wins":4},"claude-fable-5":{"draws":4,"losses":26,"wins":0},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":25,"wins":0},"claude-opus-4-5":{"draws":13,"losses":35,"wins":2},"claude-opus-4-8":{"draws":3,"losses":26,"wins":1},"claude-opus-5":{"draws":3,"losses":42,"wins":1},"claude-opus-5-5":{"draws":0,"losses":30,"wins":0},"claude-sonnet-5":{"draws":6,"losses":21,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":23,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":28,"wins":7},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":20,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":10,"wins":0},"elorian/glimpse":{"draws":2,"losses":5,"wins":1},"fireworks/ember-1":{"draws":8,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":7,"losses":20,"wins":3},"gemini-4-argon":{"draws":0,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":31,"wins":1},"google/gemini-3.5-flash-lite":{"draws":9,"losses":38,"wins":5},"google/gemini-3.6-flash":{"draws":12,"losses":44,"wins":2},"google/gemini-3.8-flash":{"draws":4,"losses":26,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":4},"gpt-4.1":{"draws":2,"losses":8,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":21,"wins":0},"gpt-5.4":{"draws":4,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":13,"wins":1},"gpt-5.4-nano":{"draws":7,"losses":22,"wins":7},"gpt-5.5":{"draws":6,"losses":19,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":20,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":22,"wins":1},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":7,"losses":19,"wins":4},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":5},"inception/mercury-3":{"draws":6,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":11,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":25,"wins":3},"meta/muse-glimmer-30b":{"draws":8,"losses":12,"wins":4},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":0},"meta/muse-spark-open":{"draws":2,"losses":13,"wins":1},"meta/muse-wonder":{"draws":3,"losses":26,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":4},"minimax/minimax-m3.1-flash":{"draws":4,"losses":14,"wins":2},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":11,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":20,"wins":2},"o3":{"draws":2,"losses":44,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":16,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":17,"wins":3},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":14,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":21,"wins":0},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":14,"wins":1},"qwen/qwen3.8-max":{"draws":8,"losses":22,"wins":0},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":9,"wins":0},"stealth/ox-alpha":{"draws":12,"losses":64,"wins":8},"stealth/space-bunny-alpha":{"draws":4,"losses":18,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":19,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":0},"thinkingmachines/inkling":{"draws":12,"losses":20,"wins":8},"thinkingmachines/inkling-small":{"draws":10,"losses":15,"wins":5},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":7,"wins":3},"x-ai/grok-4.5":{"draws":5,"losses":24,"wins":1},"x-ai/grok-4.6":{"draws":3,"losses":26,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":8,"wins":0},"xiaomi/mimo-v2.5":{"draws":15,"losses":27,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":16,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":17,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":42,"wins":6},"z-ai/glm-5.3":{"draws":4,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":2},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":30,"wins":25},"claude-fable-5":{"draws":16,"losses":62,"wins":6},"claude-fable-5-1":{"draws":3,"losses":91,"wins":0},"claude-haiku-5-5":{"draws":18,"losses":45,"wins":19},"claude-opus-4-5":{"draws":39,"losses":72,"wins":27},"claude-opus-4-8":{"draws":21,"losses":51,"wins":8},"claude-opus-5":{"draws":17,"losses":115,"wins":8},"claude-opus-5-5":{"draws":4,"losses":88,"wins":0},"claude-sonnet-5":{"draws":29,"losses":33,"wins":22},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":35,"losses":42,"wins":49},"deepseek/deepseek-v4-pro":{"draws":22,"losses":34,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":35,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":43,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":30,"wins":5},"elorian/glimpse":{"draws":4,"losses":10,"wins":12},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":24,"losses":38,"wins":22},"gemini-4-argon":{"draws":1,"losses":43,"wins":2},"google/gemini-3.1-flash-lite":{"draws":18,"losses":10,"wins":34},"google/gemini-3.5-flash":{"draws":17,"losses":48,"wins":15},"google/gemini-3.5-flash-lite":{"draws":45,"losses":63,"wins":42},"google/gemini-3.6-flash":{"draws":46,"losses":82,"wins":34},"google/gemini-3.8-flash":{"draws":22,"losses":55,"wins":7},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":20},"gpt-4.1":{"draws":10,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":21,"losses":33,"wins":20},"gpt-5.4":{"draws":13,"losses":55,"wins":14},"gpt-5.4-mini":{"draws":22,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":17,"losses":33,"wins":38},"gpt-5.5":{"draws":28,"losses":39,"wins":11},"gpt-5.6-luna":{"draws":25,"losses":32,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":70,"wins":7},"gpt-5.6-terra":{"draws":29,"losses":38,"wins":13},"gpt-6-astra":{"draws":3,"losses":79,"wins":2},"gpt-6-luna":{"draws":29,"losses":34,"wins":21},"gpt-6-sol":{"draws":14,"losses":64,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":79,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":13,"wins":23},"inception/mercury-3":{"draws":9,"losses":22,"wins":7},"inclusionai/ling-3.0-flash":{"draws":24,"losses":9,"wins":27},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":24,"wins":46},"meta/muse-glimmer-30b":{"draws":30,"losses":17,"wins":27},"meta/muse-spark-1.2":{"draws":17,"losses":49,"wins":14},"meta/muse-spark-1.3":{"draws":17,"losses":55,"wins":12},"meta/muse-spark-open":{"draws":6,"losses":14,"wins":2},"meta/muse-wonder":{"draws":10,"losses":69,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":18,"wins":18},"minimax/minimax-m3.1-flash":{"draws":9,"losses":21,"wins":12},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":18,"losses":10,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":30,"losses":33,"wins":17},"nex-agi/nex-n2-pro":{"draws":13,"losses":11,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":21,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":11,"wins":7},"o3":{"draws":23,"losses":57,"wins":46},"openai/gpt-oss-120b":{"draws":24,"losses":25,"wins":23},"poolside/laguna-s-2.1":{"draws":29,"losses":22,"wins":27},"qwen/qwen3.7-max":{"draws":16,"losses":23,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":8},"qwen/qwen3.8-27b":{"draws":10,"losses":35,"wins":15},"qwen/qwen3.8-flash":{"draws":21,"losses":22,"wins":13},"qwen/qwen3.8-max":{"draws":28,"losses":35,"wins":21},"qwen/qwen3.8-max-0902":{"draws":25,"losses":46,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":19,"wins":7},"stealth/ox-alpha":{"draws":54,"losses":163,"wins":43},"stealth/space-bunny-alpha":{"draws":23,"losses":27,"wins":18},"stepfun/step-3.7-flash":{"draws":13,"losses":17,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":20,"wins":10},"tencent/hy4-preview":{"draws":26,"losses":47,"wins":9},"thinkingmachines/inkling":{"draws":26,"losses":37,"wins":49},"thinkingmachines/inkling-small":{"draws":30,"losses":21,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":55,"wins":13},"x-ai/grok-4.6":{"draws":23,"losses":55,"wins":6},"x-ai/grok-4.7":{"draws":7,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":12},"xiaomi/mimo-v2.5":{"draws":48,"losses":37,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":18,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":35,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":59,"losses":70,"wins":39},"z-ai/glm-5.3":{"draws":13,"losses":62,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":57,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":56,"wins":12}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":30},"claude-fable-5":{"draws":18,"losses":60,"wins":12},"claude-fable-5-1":{"draws":6,"losses":93,"wins":1},"claude-haiku-5-5":{"draws":18,"losses":53,"wins":17},"claude-opus-4-5":{"draws":48,"losses":53,"wins":47},"claude-opus-4-8":{"draws":25,"losses":50,"wins":11},"claude-opus-5":{"draws":20,"losses":121,"wins":11},"claude-opus-5-5":{"draws":4,"losses":93,"wins":1},"claude-sonnet-5":{"draws":26,"losses":44,"wins":20},"claude-sonnet-5-5":{"draws":18,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":43,"losses":40,"wins":53},"deepseek/deepseek-v4-pro":{"draws":23,"losses":33,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":37,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":46,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":33,"wins":5},"elorian/glimpse":{"draws":5,"losses":12,"wins":9},"fireworks/ember-1":{"draws":30,"losses":36,"wins":24},"gemini-3.1-pro-preview":{"draws":33,"losses":32,"wins":25},"gemini-4-argon":{"draws":1,"losses":45,"wins":2},"google/gemini-3.1-flash-lite":{"draws":18,"losses":9,"wins":37},"google/gemini-3.5-flash":{"draws":29,"losses":53,"wins":32},"google/gemini-3.5-flash-lite":{"draws":45,"losses":36,"wins":47},"google/gemini-3.6-flash":{"draws":51,"losses":77,"wins":44},"google/gemini-3.8-flash":{"draws":19,"losses":63,"wins":8},"google/gemma-4-31b-it":{"draws":20,"losses":9,"wins":25},"gpt-4.1":{"draws":9,"losses":6,"wins":15},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":23,"losses":32,"wins":23},"gpt-5.4":{"draws":21,"losses":51,"wins":14},"gpt-5.4-mini":{"draws":19,"losses":18,"wins":23},"gpt-5.4-nano":{"draws":19,"losses":34,"wins":41},"gpt-5.5":{"draws":33,"losses":37,"wins":12},"gpt-5.6-luna":{"draws":28,"losses":28,"wins":34},"gpt-5.6-sol":{"draws":10,"losses":69,"wins":11},"gpt-5.6-terra":{"draws":26,"losses":34,"wins":26},"gpt-6-astra":{"draws":5,"losses":85,"wins":0},"gpt-6-luna":{"draws":31,"losses":35,"wins":24},"gpt-6-sol":{"draws":14,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":83,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":28},"inception/mercury-3":{"draws":11,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":24,"losses":7,"wins":33},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":23,"wins":51},"meta/muse-glimmer-30b":{"draws":35,"losses":14,"wins":29},"meta/muse-spark-1.2":{"draws":22,"losses":42,"wins":22},"meta/muse-spark-1.3":{"draws":23,"losses":52,"wins":15},"meta/muse-spark-open":{"draws":12,"losses":24,"wins":9},"meta/muse-wonder":{"draws":18,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":17,"wins":20},"minimax/minimax-m3.1-flash":{"draws":13,"losses":12,"wins":13},"mistralai/mistral-large-4-0":{"draws":20,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":19,"losses":9,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":12,"wins":8},"moonshotai/kimi-k3":{"draws":28,"losses":39,"wins":19},"nex-agi/nex-n2-pro":{"draws":10,"losses":13,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":18,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":11,"wins":1},"o3":{"draws":23,"losses":54,"wins":51},"openai/gpt-oss-120b":{"draws":24,"losses":23,"wins":31},"poolside/laguna-s-2.1":{"draws":26,"losses":27,"wins":31},"qwen/qwen3.7-max":{"draws":17,"losses":20,"wins":17},"qwen/qwen3.7-plus":{"draws":13,"losses":15,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":41,"wins":19},"qwen/qwen3.8-27b":{"draws":13,"losses":31,"wins":20},"qwen/qwen3.8-flash":{"draws":17,"losses":24,"wins":19},"qwen/qwen3.8-max":{"draws":28,"losses":39,"wins":23},"qwen/qwen3.8-max-0902":{"draws":27,"losses":47,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":14,"wins":14},"stealth/ox-alpha":{"draws":63,"losses":147,"wins":66},"stealth/space-bunny-alpha":{"draws":25,"losses":19,"wins":28},"stepfun/step-3.7-flash":{"draws":19,"losses":11,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":19,"wins":10},"tencent/hy4-preview":{"draws":24,"losses":43,"wins":19},"thinkingmachines/inkling":{"draws":37,"losses":31,"wins":50},"thinkingmachines/inkling-small":{"draws":31,"losses":20,"wins":39},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":12},"x-ai/grok-4.5":{"draws":23,"losses":47,"wins":20},"x-ai/grok-4.6":{"draws":17,"losses":58,"wins":15},"x-ai/grok-4.7":{"draws":9,"losses":59,"wins":12},"x-ai/grok-build-0.1":{"draws":14,"losses":5,"wins":11},"xiaomi/mimo-v2.5":{"draws":44,"losses":37,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":35,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":65,"losses":57,"wins":58},"z-ai/glm-5.3":{"draws":13,"losses":66,"wins":7},"z-ai/glm-5.3-flash":{"draws":18,"losses":52,"wins":20},"z-ai/glm-5.3-flashx":{"draws":26,"losses":43,"wins":21}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":26,"wins":32},"claude-fable-5":{"draws":23,"losses":63,"wins":10},"claude-fable-5-1":{"draws":10,"losses":97,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":47,"wins":17},"claude-opus-4-5":{"draws":54,"losses":63,"wins":39},"claude-opus-4-8":{"draws":25,"losses":41,"wins":22},"claude-opus-5":{"draws":22,"losses":127,"wins":15},"claude-opus-5-5":{"draws":4,"losses":99,"wins":1},"claude-sonnet-5":{"draws":31,"losses":43,"wins":22},"claude-sonnet-5-5":{"draws":19,"losses":60,"wins":17},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":49,"losses":36,"wins":59},"deepseek/deepseek-v4-pro":{"draws":29,"losses":39,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":40,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":40,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":44,"wins":12},"elorian/glimpse":{"draws":3,"losses":12,"wins":3},"fireworks/ember-1":{"draws":35,"losses":44,"wins":17},"gemini-3.1-pro-preview":{"draws":33,"losses":36,"wins":27},"gemini-4-argon":{"draws":5,"losses":34,"wins":1},"google/gemini-3.1-flash-lite":{"draws":25,"losses":10,"wins":29},"google/gemini-3.5-flash":{"draws":33,"losses":65,"wins":22},"google/gemini-3.5-flash-lite":{"draws":62,"losses":50,"wins":56},"google/gemini-3.6-flash":{"draws":39,"losses":86,"wins":27},"google/gemini-3.8-flash":{"draws":24,"losses":59,"wins":13},"google/gemma-4-31b-it":{"draws":23,"losses":11,"wins":22},"gpt-4.1":{"draws":12,"losses":10,"wins":10},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":3},"gpt-5":{"draws":26,"losses":40,"wins":18},"gpt-5.4":{"draws":24,"losses":48,"wins":20},"gpt-5.4-mini":{"draws":23,"losses":17,"wins":24},"gpt-5.4-nano":{"draws":24,"losses":36,"wins":36},"gpt-5.5":{"draws":37,"losses":37,"wins":14},"gpt-5.6-luna":{"draws":37,"losses":27,"wins":32},"gpt-5.6-sol":{"draws":14,"losses":73,"wins":9},"gpt-5.6-terra":{"draws":37,"losses":36,"wins":19},"gpt-6-astra":{"draws":8,"losses":88,"wins":0},"gpt-6-luna":{"draws":34,"losses":31,"wins":31},"gpt-6-sol":{"draws":13,"losses":76,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":90,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":5,"wins":30},"inception/mercury-3":{"draws":9,"losses":14,"wins":11},"inclusionai/ling-3.0-flash":{"draws":36,"losses":11,"wins":21},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":27,"wins":46},"meta/muse-glimmer-30b":{"draws":41,"losses":16,"wins":27},"meta/muse-spark-1.2":{"draws":21,"losses":53,"wins":18},"meta/muse-spark-1.3":{"draws":25,"losses":54,"wins":17},"meta/muse-spark-open":{"draws":13,"losses":30,"wins":13},"meta/muse-wonder":{"draws":16,"losses":68,"wins":12},"minimax/minimax-m3":{"draws":16,"losses":11,"wins":25},"minimax/minimax-m3.1-flash":{"draws":14,"losses":22,"wins":16},"mistralai/mistral-large-4-0":{"draws":18,"losses":25,"wins":17},"mistralai/mistral-medium-3-5":{"draws":29,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":6},"moonshotai/kimi-k3":{"draws":30,"losses":43,"wins":19},"nex-agi/nex-n2-pro":{"draws":16,"losses":5,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":17,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":10,"wins":2},"o3":{"draws":25,"losses":75,"wins":32},"openai/gpt-oss-120b":{"draws":36,"losses":18,"wins":30},"poolside/laguna-s-2.1":{"draws":41,"losses":23,"wins":28},"qwen/qwen3.7-max":{"draws":19,"losses":21,"wins":16},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":44,"wins":20},"qwen/qwen3.8-27b":{"draws":18,"losses":33,"wins":17},"qwen/qwen3.8-flash":{"draws":29,"losses":20,"wins":15},"qwen/qwen3.8-max":{"draws":30,"losses":43,"wins":23},"qwen/qwen3.8-max-0902":{"draws":33,"losses":40,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":23,"wins":9},"stealth/ox-alpha":{"draws":86,"losses":158,"wins":72},"stealth/space-bunny-alpha":{"draws":25,"losses":26,"wins":25},"stepfun/step-3.7-flash":{"draws":19,"losses":19,"wins":30},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":18},"tencent/hy4-preview":{"draws":24,"losses":54,"wins":14},"thinkingmachines/inkling":{"draws":43,"losses":24,"wins":61},"thinkingmachines/inkling-small":{"draws":41,"losses":28,"wins":27},"unbiased/pareto-26.10":{"draws":3,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":31,"wins":1},"upstage/solar-mini4":{"draws":7,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":23,"losses":53,"wins":20},"x-ai/grok-4.6":{"draws":29,"losses":57,"wins":10},"x-ai/grok-4.7":{"draws":2,"losses":71,"wins":11},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":15},"xiaomi/mimo-v2.5":{"draws":61,"losses":32,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":16,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":34,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":38,"wins":13},"z-ai/glm-5.2":{"draws":72,"losses":78,"wins":42},"z-ai/glm-5.3":{"draws":20,"losses":67,"wins":5},"z-ai/glm-5.3-flash":{"draws":22,"losses":58,"wins":16},"z-ai/glm-5.3-flashx":{"draws":27,"losses":48,"wins":21}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":10,"wins":20},"claude-fable-5":{"draws":8,"losses":31,"wins":9},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":16,"wins":17},"claude-opus-4-5":{"draws":30,"losses":14,"wins":34},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":18,"losses":12,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":3},"elorian/glimpse":{"draws":7,"losses":8,"wins":7},"fireworks/ember-1":{"draws":13,"losses":18,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"gemini-4-argon":{"draws":0,"losses":21,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":24},"google/gemini-3.5-flash-lite":{"draws":19,"losses":8,"wins":57},"google/gemini-3.6-flash":{"draws":25,"losses":31,"wins":36},"google/gemini-3.8-flash":{"draws":9,"losses":15,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":12,"losses":17,"wins":17},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":6,"wins":32},"gpt-5.5":{"draws":15,"losses":13,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":6,"losses":27,"wins":15},"gpt-5.6-terra":{"draws":18,"losses":11,"wins":17},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":16,"losses":14,"wins":18},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":39,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":5,"losses":2,"wins":7},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":34},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":18,"wins":17},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":20},"meta/muse-spark-open":{"draws":6,"losses":6,"wins":4},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":10,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":13,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":3,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":2,"wins":9},"o3":{"draws":9,"losses":16,"wins":41},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":16},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":19},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":7,"wins":6},"stealth/ox-alpha":{"draws":37,"losses":66,"wins":55},"stealth/space-bunny-alpha":{"draws":14,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling":{"draws":17,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":24,"wins":14},"x-ai/grok-4.6":{"draws":15,"losses":21,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":29,"losses":2,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":32,"losses":25,"wins":39},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":18}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":7},"claude-fable-5":{"draws":7,"losses":28,"wins":1},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":22,"wins":3},"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":11,"losses":23,"wins":2},"claude-opus-5":{"draws":8,"losses":47,"wins":3},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":5,"losses":23,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":24,"losses":22,"wins":8},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":16,"wins":0},"elorian/glimpse":{"draws":6,"losses":2,"wins":0},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":4},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":10,"wins":11},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":5},"google/gemini-3.5-flash-lite":{"draws":26,"losses":27,"wins":11},"google/gemini-3.6-flash":{"draws":23,"losses":40,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":15,"wins":1},"gpt-5.4":{"draws":11,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":11,"wins":4},"gpt-5.4-nano":{"draws":9,"losses":23,"wins":6},"gpt-5.5":{"draws":11,"losses":20,"wins":1},"gpt-5.6-luna":{"draws":14,"losses":16,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":0},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":4,"losses":32,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":8},"inception/mercury-3":{"draws":3,"losses":3,"wins":0},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":20,"wins":10},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":2},"meta/muse-spark-1.3":{"draws":11,"losses":23,"wins":2},"meta/muse-spark-open":{"draws":5,"losses":10,"wins":1},"meta/muse-wonder":{"draws":7,"losses":27,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"minimax/minimax-m3.1-flash":{"draws":8,"losses":10,"wins":2},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":1},"o3":{"draws":11,"losses":37,"wins":4},"openai/gpt-oss-120b":{"draws":14,"losses":16,"wins":2},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":22,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":1},"qwen/qwen3.8-max":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":14,"wins":1},"stealth/ox-alpha":{"draws":28,"losses":69,"wins":5},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":2},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":19,"wins":10},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":8},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":26,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":27,"losses":22,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":0},"z-ai/glm-5.2":{"draws":26,"losses":39,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":3},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":32,"losses":29,"wins":17},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":17,"wins":14},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":16,"wins":34},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":20,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":17,"wins":2},"elorian/glimpse":{"draws":4,"losses":11,"wins":3},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"gemini-4-argon":{"draws":2,"losses":18,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":28,"losses":27,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":47,"wins":20},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":15,"wins":16},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":20},"gpt-5.5":{"draws":10,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":8,"wins":11},"inception/mercury-3":{"draws":4,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":9,"wins":25},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":15,"losses":23,"wins":8},"meta/muse-spark-1.3":{"draws":16,"losses":28,"wins":4},"meta/muse-spark-open":{"draws":3,"losses":16,"wins":8},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":15},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":21,"wins":12},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":7},"o3":{"draws":13,"losses":26,"wins":27},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":13,"wins":17},"qwen/qwen3.7-max":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":12,"wins":9},"stealth/ox-alpha":{"draws":43,"losses":79,"wins":36},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":24,"wins":9},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":27},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":18},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":28,"wins":9},"x-ai/grok-4.6":{"draws":19,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":17,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":35,"losses":38,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":28,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":5,"wins":0},"elorian/glimpse":{"draws":2,"losses":2,"wins":0},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"gemini-4-argon":{"draws":0,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inception/mercury-3":{"draws":6,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-spark-open":{"draws":4,"losses":2,"wins":0},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"minimax/minimax-m3.1-flash":{"draws":2,"losses":4,"wins":0},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":0},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":33,"losses":34,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":14,"wins":10},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":18,"wins":10},"claude-opus-4-5":{"draws":16,"losses":25,"wins":17},"claude-opus-4-8":{"draws":8,"losses":17,"wins":7},"claude-opus-5":{"draws":6,"losses":58,"wins":4},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":8,"losses":24,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":19,"wins":20},"deepseek/deepseek-v4-pro":{"draws":4,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":13,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":13,"wins":4},"elorian/glimpse":{"draws":1,"losses":5,"wins":2},"fireworks/ember-1":{"draws":10,"losses":20,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":10},"gemini-4-argon":{"draws":0,"losses":9,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":7,"losses":23,"wins":14},"google/gemini-3.5-flash-lite":{"draws":13,"losses":16,"wins":31},"google/gemini-3.6-flash":{"draws":14,"losses":31,"wins":23},"google/gemini-3.8-flash":{"draws":6,"losses":19,"wins":11},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":3,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":11,"wins":9},"gpt-5.4":{"draws":3,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":8,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":14,"wins":18},"gpt-5.5":{"draws":11,"losses":19,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":19,"wins":9},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":12},"gpt-6-sol":{"draws":4,"losses":28,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"inception/mercury-2.5-preview":{"draws":8,"losses":5,"wins":9},"inception/mercury-3":{"draws":3,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":8,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":5,"losses":26,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":3,"losses":12,"wins":3},"meta/muse-wonder":{"draws":7,"losses":23,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":12},"minimax/minimax-m3.1-flash":{"draws":2,"losses":8,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":18,"wins":11},"nex-agi/nex-n2-pro":{"draws":1,"losses":8,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":6,"wins":3},"o3":{"draws":6,"losses":21,"wins":23},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":12,"losses":11,"wins":17},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":10},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":1,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":8,"losses":18,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":6,"wins":5},"stealth/ox-alpha":{"draws":22,"losses":70,"wins":32},"stealth/space-bunny-alpha":{"draws":6,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":16,"wins":11},"thinkingmachines/inkling":{"draws":9,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":9,"wins":15},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":25,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":11,"losses":12,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":17,"losses":27,"wins":28},"z-ai/glm-5.3":{"draws":4,"losses":25,"wins":5},"z-ai/glm-5.3-flash":{"draws":3,"losses":22,"wins":11},"z-ai/glm-5.3-flashx":{"draws":7,"losses":20,"wins":9}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":18},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":21,"wins":13},"claude-opus-4-5":{"draws":27,"losses":28,"wins":23},"claude-opus-4-8":{"draws":13,"losses":17,"wins":14},"claude-opus-5":{"draws":15,"losses":61,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":15,"wins":34},"deepseek/deepseek-v4-pro":{"draws":9,"losses":19,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":15,"wins":5},"elorian/glimpse":{"draws":2,"losses":7,"wins":3},"fireworks/ember-1":{"draws":19,"losses":15,"wins":14},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":18},"gemini-4-argon":{"draws":0,"losses":21,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":23,"wins":26},"google/gemini-3.5-flash-lite":{"draws":23,"losses":20,"wins":41},"google/gemini-3.6-flash":{"draws":19,"losses":43,"wins":30},"google/gemini-3.8-flash":{"draws":11,"losses":29,"wins":8},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":16,"wins":17},"gpt-5.4":{"draws":7,"losses":22,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":17},"gpt-5.4-nano":{"draws":7,"losses":17,"wins":24},"gpt-5.5":{"draws":16,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":20,"losses":12,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":12},"gpt-5.6-terra":{"draws":16,"losses":20,"wins":10},"gpt-6-astra":{"draws":1,"losses":43,"wins":4},"gpt-6-luna":{"draws":20,"losses":14,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inception/mercury-3":{"draws":3,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":10,"losses":14,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":24,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":29,"wins":12},"meta/muse-spark-open":{"draws":6,"losses":14,"wins":8},"meta/muse-wonder":{"draws":9,"losses":29,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"minimax/minimax-m3.1-flash":{"draws":4,"losses":7,"wins":11},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":4,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":4,"wins":5},"o3":{"draws":9,"losses":29,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":12,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":21},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":9,"losses":12,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":18,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":13,"wins":6},"stealth/ox-alpha":{"draws":38,"losses":80,"wins":40},"stealth/space-bunny-alpha":{"draws":13,"losses":9,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":11,"wins":34},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":28,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":21,"losses":12,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":28,"losses":29,"wins":39},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":26,"wins":16},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":18,"wins":5},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":30,"wins":2},"claude-opus-4-5":{"draws":36,"losses":35,"wins":7},"claude-opus-4-8":{"draws":11,"losses":30,"wins":3},"claude-opus-5":{"draws":21,"losses":58,"wins":3},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":21,"losses":19,"wins":8},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":8,"wins":5},"deepseek/deepseek-v4-flash":{"draws":32,"losses":27,"wins":13},"deepseek/deepseek-v4-pro":{"draws":16,"losses":21,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":23,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":21,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":16,"wins":2},"elorian/glimpse":{"draws":5,"losses":2,"wins":3},"fireworks/ember-1":{"draws":22,"losses":23,"wins":3},"gemini-3.1-pro-preview":{"draws":21,"losses":20,"wins":7},"gemini-4-argon":{"draws":4,"losses":16,"wins":0},"google/gemini-3.1-flash-lite":{"draws":14,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":24,"losses":32,"wins":4},"google/gemini-3.5-flash-lite":{"draws":30,"losses":38,"wins":16},"google/gemini-3.6-flash":{"draws":34,"losses":53,"wins":5},"google/gemini-3.8-flash":{"draws":15,"losses":32,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":18,"losses":21,"wins":3},"gpt-5.4":{"draws":18,"losses":28,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":16,"losses":24,"wins":8},"gpt-5.5":{"draws":18,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":21,"losses":20,"wins":5},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":22,"losses":23,"wins":3},"gpt-6-sol":{"draws":6,"losses":40,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":18,"losses":9,"wins":7},"inception/mercury-3":{"draws":8,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":21,"losses":9,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":21,"wins":8},"meta/muse-glimmer-30b":{"draws":24,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":16,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":10,"losses":37,"wins":1},"meta/muse-spark-open":{"draws":4,"losses":17,"wins":1},"meta/muse-wonder":{"draws":14,"losses":32,"wins":2},"minimax/minimax-m3":{"draws":9,"losses":13,"wins":4},"minimax/minimax-m3.1-flash":{"draws":13,"losses":14,"wins":1},"mistralai/mistral-large-4-0":{"draws":16,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":25,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":9,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":14,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":8,"wins":0},"o3":{"draws":16,"losses":43,"wins":7},"openai/gpt-oss-120b":{"draws":21,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":25,"losses":16,"wins":5},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":26,"losses":16,"wins":6},"qwen/qwen3.8-max-0902":{"draws":24,"losses":23,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":11,"wins":2},"stealth/ox-alpha":{"draws":59,"losses":87,"wins":12},"stealth/space-bunny-alpha":{"draws":16,"losses":22,"wins":0},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":3},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":0},"thinkingmachines/inkling":{"draws":25,"losses":26,"wins":13},"thinkingmachines/inkling-small":{"draws":26,"losses":15,"wins":7},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":17,"losses":28,"wins":3},"x-ai/grok-4.6":{"draws":19,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":27,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":21,"wins":1},"z-ai/glm-5.2":{"draws":50,"losses":41,"wins":5},"z-ai/glm-5.3":{"draws":15,"losses":30,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":28,"wins":5},"z-ai/glm-5.3-flashx":{"draws":16,"losses":31,"wins":1}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":28,"wins":22},"claude-fable-5":{"draws":11,"losses":58,"wins":3},"claude-fable-5-1":{"draws":1,"losses":75,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":38,"wins":15},"claude-opus-4-5":{"draws":32,"losses":63,"wins":23},"claude-opus-4-8":{"draws":14,"losses":42,"wins":12},"claude-opus-5":{"draws":11,"losses":106,"wins":3},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":23,"losses":33,"wins":16},"claude-sonnet-5-5":{"draws":12,"losses":53,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":7,"wins":16},"deepseek/deepseek-v4-flash":{"draws":28,"losses":43,"wins":43},"deepseek/deepseek-v4-pro":{"draws":11,"losses":30,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":35,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":28,"wins":2},"elorian/glimpse":{"draws":7,"losses":17,"wins":2},"fireworks/ember-1":{"draws":19,"losses":43,"wins":10},"gemini-3.1-pro-preview":{"draws":22,"losses":35,"wins":15},"gemini-4-argon":{"draws":0,"losses":40,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":13,"wins":25},"google/gemini-3.5-flash":{"draws":20,"losses":54,"wins":16},"google/gemini-3.5-flash-lite":{"draws":33,"losses":49,"wins":42},"google/gemini-3.6-flash":{"draws":28,"losses":83,"wins":25},"google/gemini-3.8-flash":{"draws":18,"losses":45,"wins":9},"google/gemma-4-31b-it":{"draws":15,"losses":10,"wins":17},"gpt-4.1":{"draws":7,"losses":9,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":11,"losses":37,"wins":16},"gpt-5.4":{"draws":10,"losses":45,"wins":13},"gpt-5.4-mini":{"draws":17,"losses":15,"wins":16},"gpt-5.4-nano":{"draws":14,"losses":24,"wins":22},"gpt-5.5":{"draws":18,"losses":32,"wins":14},"gpt-5.6-luna":{"draws":22,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":5,"losses":61,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":37,"wins":14},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":16,"losses":42,"wins":14},"gpt-6-sol":{"draws":8,"losses":56,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":65,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":9,"wins":23},"inception/mercury-3":{"draws":7,"losses":10,"wins":7},"inclusionai/ling-3.0-flash":{"draws":17,"losses":8,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":27,"wins":33},"meta/muse-glimmer-30b":{"draws":18,"losses":19,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":37,"wins":19},"meta/muse-spark-1.3":{"draws":12,"losses":52,"wins":8},"meta/muse-spark-open":{"draws":2,"losses":17,"wins":1},"meta/muse-wonder":{"draws":5,"losses":55,"wins":12},"minimax/minimax-m3":{"draws":10,"losses":12,"wins":20},"minimax/minimax-m3.1-flash":{"draws":2,"losses":17,"wins":13},"mistralai/mistral-large-4-0":{"draws":8,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":9,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":7,"wins":6},"moonshotai/kimi-k3":{"draws":18,"losses":37,"wins":13},"nex-agi/nex-n2-pro":{"draws":10,"losses":14,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":20,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":12,"wins":8},"o3":{"draws":12,"losses":58,"wins":38},"openai/gpt-oss-120b":{"draws":24,"losses":24,"wins":16},"poolside/laguna-s-2.1":{"draws":30,"losses":26,"wins":20},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":40,"wins":13},"qwen/qwen3.8-27b":{"draws":15,"losses":24,"wins":13},"qwen/qwen3.8-flash":{"draws":14,"losses":24,"wins":10},"qwen/qwen3.8-max":{"draws":15,"losses":37,"wins":20},"qwen/qwen3.8-max-0902":{"draws":22,"losses":35,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":16,"wins":2},"stealth/ox-alpha":{"draws":49,"losses":123,"wins":50},"stealth/space-bunny-alpha":{"draws":13,"losses":27,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":21,"wins":7},"tencent/hy4-preview":{"draws":14,"losses":46,"wins":8},"thinkingmachines/inkling":{"draws":25,"losses":40,"wins":29},"thinkingmachines/inkling-small":{"draws":26,"losses":21,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":23,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":47,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":46,"wins":12},"x-ai/grok-4.7":{"draws":10,"losses":54,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":39,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":25,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":42,"losses":66,"wins":36},"z-ai/glm-5.3":{"draws":13,"losses":48,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":46,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":40,"wins":14}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":12},"claude-fable-5":{"draws":12,"losses":23,"wins":7},"claude-fable-5-1":{"draws":2,"losses":43,"wins":3},"claude-haiku-5-5":{"draws":17,"losses":17,"wins":6},"claude-opus-4-5":{"draws":36,"losses":21,"wins":11},"claude-opus-4-8":{"draws":18,"losses":16,"wins":4},"claude-opus-5":{"draws":14,"losses":65,"wins":1},"claude-opus-5-5":{"draws":7,"losses":39,"wins":0},"claude-sonnet-5":{"draws":22,"losses":10,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":32,"losses":8,"wins":22},"deepseek/deepseek-v4-pro":{"draws":19,"losses":13,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":14,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":10,"wins":4},"elorian/glimpse":{"draws":2,"losses":2,"wins":8},"fireworks/ember-1":{"draws":17,"losses":17,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":11},"gemini-4-argon":{"draws":3,"losses":15,"wins":0},"google/gemini-3.1-flash-lite":{"draws":13,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":21,"losses":20,"wins":11},"google/gemini-3.5-flash-lite":{"draws":38,"losses":13,"wins":21},"google/gemini-3.6-flash":{"draws":28,"losses":38,"wins":14},"google/gemini-3.8-flash":{"draws":19,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":8},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":19,"losses":12,"wins":7},"gpt-5.4":{"draws":12,"losses":18,"wins":10},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":15},"gpt-5.5":{"draws":15,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":23,"losses":11,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":16,"losses":15,"wins":11},"gpt-6-sol":{"draws":10,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":9},"inception/mercury-3":{"draws":6,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":21,"losses":2,"wins":5},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":15},"meta/muse-glimmer-30b":{"draws":20,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":9,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":14,"wins":4},"meta/muse-wonder":{"draws":17,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":7},"minimax/minimax-m3.1-flash":{"draws":11,"losses":5,"wins":2},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":8},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":3,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":2},"o3":{"draws":16,"losses":18,"wins":20},"openai/gpt-oss-120b":{"draws":20,"losses":6,"wins":12},"poolside/laguna-s-2.1":{"draws":24,"losses":9,"wins":9},"qwen/qwen3.7-max":{"draws":14,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":8},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":15,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":17,"losses":15,"wins":10},"qwen/qwen3.8-max-0902":{"draws":19,"losses":18,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":7,"wins":3},"stealth/ox-alpha":{"draws":47,"losses":68,"wins":27},"stealth/space-bunny-alpha":{"draws":18,"losses":7,"wins":9},"stepfun/step-3.7-flash":{"draws":13,"losses":5,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":4},"thinkingmachines/inkling":{"draws":26,"losses":7,"wins":25},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":14},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":15,"losses":25,"wins":2},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":34,"losses":7,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":4,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":5},"z-ai/glm-5.2":{"draws":37,"losses":23,"wins":24},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":20,"wins":9},"z-ai/glm-5.3-flashx":{"draws":18,"losses":18,"wins":6}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":24,"wins":8},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":32,"wins":2},"claude-opus-4-5":{"draws":26,"losses":45,"wins":7},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":9,"losses":69,"wins":4},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":12,"losses":30,"wins":6},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":8,"wins":7},"deepseek/deepseek-v4-flash":{"draws":29,"losses":30,"wins":13},"deepseek/deepseek-v4-pro":{"draws":14,"losses":26,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":22,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":28,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":27,"wins":0},"elorian/glimpse":{"draws":2,"losses":10,"wins":2},"fireworks/ember-1":{"draws":15,"losses":27,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":26,"wins":10},"gemini-4-argon":{"draws":3,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":16,"wins":9},"google/gemini-3.5-flash":{"draws":11,"losses":43,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":43,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":62,"wins":5},"google/gemini-3.8-flash":{"draws":6,"losses":39,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":15,"wins":3},"gpt-4.1":{"draws":4,"losses":11,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":27,"wins":4},"gpt-5.4":{"draws":13,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":11,"losses":17,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":27,"wins":8},"gpt-5.5":{"draws":13,"losses":28,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":15,"wins":4},"gpt-5.6-sol":{"draws":4,"losses":40,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":24,"wins":7},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":7},"gpt-6-sol":{"draws":9,"losses":37,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":13,"wins":5},"inception/mercury-3":{"draws":4,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":17,"losses":13,"wins":4},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":29,"wins":6},"meta/muse-glimmer-30b":{"draws":17,"losses":22,"wins":3},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":34,"wins":2},"meta/muse-spark-open":{"draws":9,"losses":19,"wins":4},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":13,"wins":5},"minimax/minimax-m3.1-flash":{"draws":5,"losses":14,"wins":5},"mistralai/mistral-large-4-0":{"draws":8,"losses":19,"wins":3},"mistralai/mistral-medium-3-5":{"draws":10,"losses":10,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":26,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":24,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":5,"wins":1},"o3":{"draws":8,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":26,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":31,"wins":0},"qwen/qwen3.8-27b":{"draws":11,"losses":20,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":29,"wins":7},"qwen/qwen3.8-max-0902":{"draws":14,"losses":31,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":4,"wins":3},"stealth/ox-alpha":{"draws":49,"losses":100,"wins":9},"stealth/space-bunny-alpha":{"draws":15,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":16,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":18,"wins":0},"tencent/hy4-preview":{"draws":12,"losses":30,"wins":4},"thinkingmachines/inkling":{"draws":22,"losses":26,"wins":16},"thinkingmachines/inkling-small":{"draws":18,"losses":23,"wins":7},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":32,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":36,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":7,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":35,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":18,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":25,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":53,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":34,"wins":2}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":4,"wins":28},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":4,"losses":22,"wins":20},"claude-opus-4-5":{"draws":21,"losses":13,"wins":44},"claude-opus-4-8":{"draws":9,"losses":21,"wins":14},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":14,"losses":9,"wins":25},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":14,"losses":11,"wins":47},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":16,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":21,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":16,"wins":6},"elorian/glimpse":{"draws":5,"losses":5,"wins":2},"fireworks/ember-1":{"draws":11,"losses":18,"wins":19},"gemini-3.1-pro-preview":{"draws":10,"losses":13,"wins":25},"gemini-4-argon":{"draws":4,"losses":21,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":18,"wins":32},"google/gemini-3.5-flash-lite":{"draws":21,"losses":10,"wins":53},"google/gemini-3.6-flash":{"draws":20,"losses":33,"wins":39},"google/gemini-3.8-flash":{"draws":10,"losses":23,"wins":15},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":4,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":12,"wins":21},"gpt-5.4":{"draws":11,"losses":21,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"gpt-5.5":{"draws":10,"losses":22,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":24},"gpt-5.6-sol":{"draws":2,"losses":19,"wins":11},"gpt-5.6-terra":{"draws":13,"losses":14,"wins":19},"gpt-6-astra":{"draws":3,"losses":42,"wins":3},"gpt-6-luna":{"draws":10,"losses":13,"wins":25},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":41,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":21},"inception/mercury-3":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":37},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":7,"losses":23,"wins":18},"meta/muse-spark-open":{"draws":5,"losses":7,"wins":8},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":6,"losses":5,"wins":11},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":20},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":8},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":11,"losses":4,"wins":31},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":7,"wins":19},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":33,"losses":62,"wins":63},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":22},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":41},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":30},"unbiased/pareto-26.10":{"draws":0,"losses":11,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":22,"wins":18},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":21,"losses":26,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":21}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":8,"wins":17},"claude-fable-5":{"draws":12,"losses":29,"wins":1},"claude-fable-5-1":{"draws":4,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":5},"claude-opus-4-5":{"draws":30,"losses":28,"wins":10},"claude-opus-4-8":{"draws":16,"losses":19,"wins":3},"claude-opus-5":{"draws":11,"losses":51,"wins":8},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":20,"losses":16,"wins":6},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":24,"losses":12,"wins":28},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":16,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":17,"wins":0},"elorian/glimpse":{"draws":0,"losses":8,"wins":2},"fireworks/ember-1":{"draws":16,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":18,"losses":17,"wins":7},"gemini-4-argon":{"draws":3,"losses":15,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":12},"google/gemini-3.5-flash":{"draws":23,"losses":23,"wins":6},"google/gemini-3.5-flash-lite":{"draws":28,"losses":23,"wins":21},"google/gemini-3.6-flash":{"draws":30,"losses":38,"wins":12},"google/gemini-3.8-flash":{"draws":14,"losses":24,"wins":4},"google/gemma-4-31b-it":{"draws":15,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":17,"wins":6},"gpt-5.4":{"draws":12,"losses":19,"wins":9},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":15},"gpt-5.5":{"draws":21,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":16,"wins":10},"gpt-5.6-sol":{"draws":12,"losses":25,"wins":5},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":8},"gpt-6-astra":{"draws":5,"losses":36,"wins":1},"gpt-6-luna":{"draws":17,"losses":18,"wins":7},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":12},"inception/mercury-3":{"draws":9,"losses":8,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":12,"wins":14},"meta/muse-glimmer-30b":{"draws":18,"losses":4,"wins":14},"meta/muse-spark-1.2":{"draws":16,"losses":15,"wins":9},"meta/muse-spark-1.3":{"draws":13,"losses":20,"wins":9},"meta/muse-spark-open":{"draws":12,"losses":10,"wins":0},"meta/muse-wonder":{"draws":10,"losses":26,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":5,"wins":7},"minimax/minimax-m3.1-flash":{"draws":5,"losses":6,"wins":7},"mistralai/mistral-large-4-0":{"draws":16,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":6,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":2},"o3":{"draws":14,"losses":24,"wins":16},"openai/gpt-oss-120b":{"draws":18,"losses":1,"wins":17},"poolside/laguna-s-2.1":{"draws":26,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":17,"wins":6},"qwen/qwen3.8-27b":{"draws":15,"losses":12,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":21,"losses":11,"wins":10},"qwen/qwen3.8-max-0902":{"draws":19,"losses":16,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":4,"wins":3},"stealth/ox-alpha":{"draws":53,"losses":67,"wins":20},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":3},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":5,"wins":4},"tencent/hy4-preview":{"draws":16,"losses":18,"wins":6},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":20},"thinkingmachines/inkling-small":{"draws":19,"losses":8,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":13,"losses":26,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":31,"losses":9,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":44,"losses":20,"wins":20},"z-ai/glm-5.3":{"draws":13,"losses":23,"wins":4},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":13,"losses":24,"wins":5}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":35},"claude-fable-5":{"draws":5,"losses":9,"wins":34},"claude-fable-5-1":{"draws":5,"losses":25,"wins":24},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":38},"claude-opus-4-5":{"draws":8,"losses":7,"wins":63},"claude-opus-4-8":{"draws":5,"losses":7,"wins":32},"claude-opus-5":{"draws":11,"losses":24,"wins":47},"claude-opus-5-5":{"draws":8,"losses":27,"wins":17},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":5,"losses":11,"wins":32},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":2,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":3,"wins":20},"elorian/glimpse":{"draws":1,"losses":2,"wins":7},"fireworks/ember-1":{"draws":9,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":1,"wins":42},"gemini-4-argon":{"draws":4,"losses":9,"wins":13},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":8,"losses":1,"wins":51},"google/gemini-3.5-flash-lite":{"draws":9,"losses":1,"wins":74},"google/gemini-3.6-flash":{"draws":14,"losses":6,"wins":72},"google/gemini-3.8-flash":{"draws":8,"losses":5,"wins":35},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":0,"wins":37},"gpt-5.4":{"draws":5,"losses":7,"wins":34},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":28},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":45},"gpt-5.5":{"draws":3,"losses":3,"wins":38},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":7,"losses":2,"wins":39},"gpt-5.6-terra":{"draws":10,"losses":2,"wins":34},"gpt-6-astra":{"draws":4,"losses":17,"wins":11},"gpt-6-luna":{"draws":8,"losses":4,"wins":36},"gpt-6-sol":{"draws":3,"losses":15,"wins":30},"gpt-6.1-sol":{"draws":6,"losses":23,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":2,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":45},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":39},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":39},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":34},"meta/muse-spark-open":{"draws":3,"losses":0,"wins":21},"meta/muse-wonder":{"draws":8,"losses":7,"wins":33},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":6,"losses":0,"wins":20},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":36},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":18},"o3":{"draws":3,"losses":0,"wins":63},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":34},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":40},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":9,"losses":1,"wins":22},"qwen/qwen3.8-max":{"draws":7,"losses":2,"wins":39},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":37},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":14},"stealth/ox-alpha":{"draws":20,"losses":8,"wins":130},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":33},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":1,"wins":38},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":56},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":1,"losses":4,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":7,"wins":9},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":35},"x-ai/grok-4.6":{"draws":7,"losses":7,"wins":34},"x-ai/grok-4.7":{"draws":6,"losses":9,"wins":27},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":26},"z-ai/glm-5.2":{"draws":13,"losses":7,"wins":76},"z-ai/glm-5.3":{"draws":10,"losses":4,"wins":32},"z-ai/glm-5.3-flash":{"draws":7,"losses":5,"wins":36},"z-ai/glm-5.3-flashx":{"draws":10,"losses":3,"wins":35}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":12,"wins":16},"claude-fable-5":{"draws":12,"losses":31,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":20,"wins":9},"claude-opus-4-5":{"draws":30,"losses":25,"wins":23},"claude-opus-4-8":{"draws":17,"losses":22,"wins":5},"claude-opus-5":{"draws":17,"losses":60,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":12,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":24,"losses":19,"wins":29},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":21,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":17,"wins":5},"elorian/glimpse":{"draws":2,"losses":4,"wins":4},"fireworks/ember-1":{"draws":16,"losses":22,"wins":10},"gemini-3.1-pro-preview":{"draws":18,"losses":21,"wins":9},"gemini-4-argon":{"draws":2,"losses":18,"wins":0},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":22,"losses":23,"wins":15},"google/gemini-3.5-flash-lite":{"draws":40,"losses":15,"wins":29},"google/gemini-3.6-flash":{"draws":37,"losses":40,"wins":15},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":3,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":13,"wins":12},"gpt-5.4":{"draws":17,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":18,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":21,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":18,"losses":13,"wins":15},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":10,"losses":10,"wins":12},"gpt-6-sol":{"draws":8,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inception/mercury-3":{"draws":7,"losses":4,"wins":5},"inclusionai/ling-3.0-flash":{"draws":20,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":12,"wins":20},"meta/muse-glimmer-30b":{"draws":21,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":5},"meta/muse-spark-open":{"draws":6,"losses":6,"wins":10},"meta/muse-wonder":{"draws":15,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"minimax/minimax-m3.1-flash":{"draws":7,"losses":3,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":5,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":8},"o3":{"draws":17,"losses":24,"wins":25},"openai/gpt-oss-120b":{"draws":20,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":23,"losses":9,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":21,"wins":12},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":10,"wins":4},"stealth/ox-alpha":{"draws":44,"losses":75,"wins":39},"stealth/space-bunny-alpha":{"draws":19,"losses":5,"wins":14},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":19,"wins":24},"thinkingmachines/inkling-small":{"draws":21,"losses":12,"wins":15},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":35,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":35,"losses":6,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":38,"losses":23,"wins":35},"z-ai/glm-5.3":{"draws":8,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":11}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":8,"losses":20,"wins":20},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":9,"losses":14,"wins":23},"claude-opus-4-5":{"draws":15,"losses":10,"wins":53},"claude-opus-4-8":{"draws":7,"losses":16,"wins":21},"claude-opus-5":{"draws":11,"losses":59,"wins":12},"claude-opus-5-5":{"draws":2,"losses":42,"wins":8},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":8,"wins":6},"elorian/glimpse":{"draws":4,"losses":5,"wins":5},"fireworks/ember-1":{"draws":11,"losses":12,"wins":25},"gemini-3.1-pro-preview":{"draws":9,"losses":13,"wins":26},"gemini-4-argon":{"draws":3,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":11,"losses":15,"wins":34},"google/gemini-3.5-flash-lite":{"draws":12,"losses":9,"wins":63},"google/gemini-3.6-flash":{"draws":17,"losses":26,"wins":49},"google/gemini-3.8-flash":{"draws":9,"losses":18,"wins":21},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":23},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":7,"losses":8,"wins":27},"gpt-5.4":{"draws":5,"losses":9,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":5,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":22,"wins":21},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":29},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":6,"wins":33},"gpt-6-sol":{"draws":5,"losses":19,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inception/mercury-3":{"draws":8,"losses":3,"wins":11},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":42},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":31},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":27},"meta/muse-spark-1.3":{"draws":10,"losses":10,"wins":28},"meta/muse-spark-open":{"draws":2,"losses":5,"wins":15},"meta/muse-wonder":{"draws":12,"losses":21,"wins":15},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":5},"o3":{"draws":4,"losses":4,"wins":58},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":10,"losses":3,"wins":33},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":15,"wins":21},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":24},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":2,"wins":16},"stealth/ox-alpha":{"draws":25,"losses":33,"wins":100},"stealth/space-bunny-alpha":{"draws":9,"losses":4,"wins":25},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":27},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":1,"wins":17},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":13,"wins":23},"x-ai/grok-4.6":{"draws":12,"losses":16,"wins":20},"x-ai/grok-4.7":{"draws":4,"losses":25,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":22,"losses":15,"wins":59},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":7,"losses":21,"wins":20}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":32},"claude-fable-5":{"draws":4,"losses":18,"wins":26},"claude-fable-5-1":{"draws":4,"losses":36,"wins":14},"claude-haiku-5-5":{"draws":8,"losses":4,"wins":34},"claude-opus-4-5":{"draws":18,"losses":9,"wins":51},"claude-opus-4-8":{"draws":4,"losses":9,"wins":31},"claude-opus-5":{"draws":13,"losses":36,"wins":33},"claude-opus-5-5":{"draws":10,"losses":25,"wins":17},"claude-sonnet-5":{"draws":5,"losses":7,"wins":36},"claude-sonnet-5-5":{"draws":1,"losses":17,"wins":30},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":8,"losses":3,"wins":61},"deepseek/deepseek-v4-pro":{"draws":7,"losses":4,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":4,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":7,"wins":18},"elorian/glimpse":{"draws":2,"losses":2,"wins":6},"fireworks/ember-1":{"draws":9,"losses":7,"wins":32},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":39},"gemini-4-argon":{"draws":2,"losses":15,"wins":9},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":45},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":69},"google/gemini-3.8-flash":{"draws":14,"losses":7,"wins":27},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":3,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":4,"wins":33},"gpt-5.4":{"draws":4,"losses":10,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":40},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":38},"gpt-5.6-sol":{"draws":8,"losses":10,"wins":30},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":37},"gpt-6-astra":{"draws":5,"losses":35,"wins":8},"gpt-6-luna":{"draws":10,"losses":4,"wins":34},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inception/mercury-3":{"draws":2,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":31},"meta/muse-spark-1.3":{"draws":7,"losses":9,"wins":32},"meta/muse-spark-open":{"draws":5,"losses":3,"wins":14},"meta/muse-wonder":{"draws":8,"losses":14,"wins":26},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":7,"losses":1,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":34},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":10},"o3":{"draws":2,"losses":7,"wins":57},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":36},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":37},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":10,"wins":31},"qwen/qwen3.8-27b":{"draws":7,"losses":1,"wins":26},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":23},"qwen/qwen3.8-max":{"draws":6,"losses":4,"wins":38},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":1,"wins":18},"stealth/ox-alpha":{"draws":27,"losses":17,"wins":114},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":50},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"draws":3,"losses":9,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":10,"losses":8,"wins":30},"x-ai/grok-4.6":{"draws":11,"losses":5,"wins":32},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":15,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":11,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":4,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":15,"wins":24},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":34},"z-ai/glm-5.3-flashx":{"draws":13,"losses":8,"wins":27}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":10},"claude-fable-5":{"draws":8,"losses":17,"wins":5},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":3},"claude-opus-4-5":{"draws":23,"losses":20,"wins":5},"claude-opus-4-8":{"draws":11,"losses":8,"wins":7},"claude-opus-5":{"draws":13,"losses":35,"wins":2},"claude-opus-5-5":{"draws":4,"losses":26,"wins":0},"claude-sonnet-5":{"draws":12,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":8,"losses":15,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":13,"wins":13},"deepseek/deepseek-v4-pro":{"draws":11,"losses":9,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":12,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":6,"wins":2},"elorian/glimpse":{"draws":4,"losses":2,"wins":0},"fireworks/ember-1":{"draws":13,"losses":12,"wins":5},"gemini-3.1-pro-preview":{"draws":9,"losses":8,"wins":13},"gemini-4-argon":{"draws":2,"losses":22,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":10},"google/gemini-3.5-flash-lite":{"draws":19,"losses":13,"wins":22},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":8},"google/gemini-3.8-flash":{"draws":11,"losses":18,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":5},"gpt-5.4":{"draws":14,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":7},"gpt-5.5":{"draws":13,"losses":9,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":23,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":10,"wins":5},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":4},"gpt-6-sol":{"draws":7,"losses":22,"wins":1},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":4},"inception/mercury-3":{"draws":6,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":9},"meta/muse-spark-1.2":{"draws":11,"losses":11,"wins":6},"meta/muse-spark-1.3":{"draws":7,"losses":19,"wins":4},"meta/muse-spark-open":{"draws":3,"losses":7,"wins":2},"meta/muse-wonder":{"draws":10,"losses":17,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":5},"minimax/minimax-m3.1-flash":{"draws":8,"losses":9,"wins":5},"mistralai/mistral-large-4-0":{"draws":6,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":5,"wins":1},"o3":{"draws":7,"losses":17,"wins":10},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":1},"qwen/qwen3.8-27b":{"draws":9,"losses":12,"wins":1},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":4},"qwen/qwen3.8-max-0902":{"draws":12,"losses":16,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":35,"losses":54,"wins":19},"stealth/space-bunny-alpha":{"draws":8,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":12,"wins":3},"thinkingmachines/inkling":{"draws":17,"losses":5,"wins":18},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":10},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":11,"losses":16,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":16,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":20,"losses":15,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":12,"wins":1},"z-ai/glm-5.2":{"draws":28,"losses":23,"wins":9},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":17,"wins":4},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":6,"wins":9},"claude-fable-5":{"draws":10,"losses":15,"wins":1},"claude-fable-5-1":{"draws":2,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":9,"wins":1},"claude-opus-4-5":{"draws":16,"losses":12,"wins":8},"claude-opus-4-8":{"draws":4,"losses":8,"wins":2},"claude-opus-5":{"draws":5,"losses":30,"wins":5},"claude-opus-5-5":{"draws":0,"losses":24,"wins":0},"claude-sonnet-5":{"draws":11,"losses":3,"wins":8},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":12,"losses":14,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":11,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":36,"wins":4},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":4,"losses":10,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":11,"wins":12},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":9,"losses":18,"wins":11},"google/gemini-3.5-flash-lite":{"draws":12,"losses":6,"wins":20},"google/gemini-3.6-flash":{"draws":15,"losses":24,"wins":5},"google/gemini-3.8-flash":{"draws":5,"losses":9,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":5,"wins":4},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":0,"losses":15,"wins":7},"gpt-5.4":{"draws":2,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":14},"gpt-5.5":{"draws":9,"losses":10,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":13,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":4},"gpt-6-astra":{"draws":1,"losses":21,"wins":0},"gpt-6-luna":{"draws":3,"losses":13,"wins":4},"gpt-6-sol":{"draws":5,"losses":22,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":16,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":4,"wins":4},"inception/mercury-3":{"draws":3,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":5,"wins":8},"meituan/longcat-2.0":{"draws":7,"losses":10,"wins":11},"meta/muse-glimmer-30b":{"draws":2,"losses":6,"wins":6},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":8},"meta/muse-spark-1.3":{"draws":5,"losses":16,"wins":1},"meta/muse-spark-open":{"draws":9,"losses":27,"wins":8},"meta/muse-wonder":{"draws":5,"losses":15,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":7},"minimax/minimax-m3.1-flash":{"draws":9,"losses":15,"wins":14},"mistralai/mistral-large-4-0":{"draws":8,"losses":11,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":9,"wins":6},"o3":{"draws":3,"losses":11,"wins":18},"openai/gpt-oss-120b":{"draws":4,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":5,"losses":7,"wins":6},"qwen/qwen3.7-max":{"draws":1,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":2},"qwen/qwen3.8-flash":{"draws":7,"losses":1,"wins":4},"qwen/qwen3.8-max":{"draws":9,"losses":12,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":14,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":18,"losses":46,"wins":18},"stealth/space-bunny-alpha":{"draws":1,"losses":7,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":4,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":4,"losses":11,"wins":5},"thinkingmachines/inkling-small":{"draws":8,"losses":1,"wins":9},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":14,"losses":14,"wins":6},"x-ai/grok-4.6":{"draws":5,"losses":13,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":21,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":16,"wins":17},"z-ai/glm-5.3":{"draws":9,"losses":16,"wins":1},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":5},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":4}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":27,"wins":10},"claude-fable-5":{"draws":14,"losses":49,"wins":3},"claude-fable-5-1":{"draws":5,"losses":67,"wins":0},"claude-haiku-5-5":{"draws":21,"losses":37,"wins":4},"claude-opus-4-5":{"draws":35,"losses":64,"wins":7},"claude-opus-4-8":{"draws":19,"losses":39,"wins":0},"claude-opus-5":{"draws":17,"losses":89,"wins":6},"claude-opus-5-5":{"draws":4,"losses":74,"wins":0},"claude-sonnet-5":{"draws":24,"losses":38,"wins":4},"claude-sonnet-5-5":{"draws":16,"losses":47,"wins":3},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":45,"losses":33,"wins":24},"deepseek/deepseek-v4-pro":{"draws":24,"losses":24,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":29,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":28,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":32,"wins":2},"elorian/glimpse":{"draws":1,"losses":10,"wins":3},"fireworks/ember-1":{"draws":32,"losses":34,"wins":0},"gemini-3.1-pro-preview":{"draws":29,"losses":32,"wins":5},"gemini-4-argon":{"draws":5,"losses":28,"wins":1},"google/gemini-3.1-flash-lite":{"draws":18,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":28,"losses":49,"wins":5},"google/gemini-3.5-flash-lite":{"draws":46,"losses":46,"wins":22},"google/gemini-3.6-flash":{"draws":46,"losses":68,"wins":10},"google/gemini-3.8-flash":{"draws":21,"losses":44,"wins":1},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":5},"gpt-4.1":{"draws":9,"losses":13,"wins":0},"gpt-4.1-nano":{"draws":4,"losses":5,"wins":1},"gpt-5":{"draws":21,"losses":19,"wins":18},"gpt-5.4":{"draws":20,"losses":36,"wins":8},"gpt-5.4-mini":{"draws":21,"losses":17,"wins":6},"gpt-5.4-nano":{"draws":22,"losses":34,"wins":12},"gpt-5.5":{"draws":31,"losses":26,"wins":3},"gpt-5.6-luna":{"draws":37,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":8,"losses":57,"wins":1},"gpt-5.6-terra":{"draws":26,"losses":37,"wins":3},"gpt-6-astra":{"draws":3,"losses":62,"wins":1},"gpt-6-luna":{"draws":26,"losses":33,"wins":7},"gpt-6-sol":{"draws":10,"losses":50,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":63,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":13,"wins":8},"inception/mercury-3":{"draws":2,"losses":11,"wins":5},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":25,"wins":8},"meta/muse-glimmer-30b":{"draws":36,"losses":12,"wins":8},"meta/muse-spark-1.2":{"draws":16,"losses":41,"wins":5},"meta/muse-spark-1.3":{"draws":15,"losses":46,"wins":5},"meta/muse-spark-open":{"draws":7,"losses":24,"wins":3},"meta/muse-wonder":{"draws":9,"losses":52,"wins":5},"minimax/minimax-m3":{"draws":13,"losses":17,"wins":4},"minimax/minimax-m3.1-flash":{"draws":6,"losses":19,"wins":3},"mistralai/mistral-large-4-0":{"draws":21,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":16,"losses":14,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":23,"losses":33,"wins":6},"nex-agi/nex-n2-pro":{"draws":15,"losses":8,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":17,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":3},"o3":{"draws":25,"losses":53,"wins":10},"openai/gpt-oss-120b":{"draws":29,"losses":25,"wins":2},"poolside/laguna-s-2.1":{"draws":38,"losses":21,"wins":9},"qwen/qwen3.7-max":{"draws":22,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":39,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":27,"wins":9},"qwen/qwen3.8-flash":{"draws":20,"losses":23,"wins":1},"qwen/qwen3.8-max":{"draws":27,"losses":32,"wins":7},"qwen/qwen3.8-max-0902":{"draws":29,"losses":34,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":21,"wins":1},"stealth/ox-alpha":{"draws":73,"losses":142,"wins":11},"stealth/space-bunny-alpha":{"draws":24,"losses":16,"wins":6},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":18,"wins":4},"tencent/hy4-preview":{"draws":29,"losses":33,"wins":2},"thinkingmachines/inkling":{"draws":31,"losses":36,"wins":17},"thinkingmachines/inkling-small":{"draws":37,"losses":18,"wins":11},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":20,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":48,"wins":3},"x-ai/grok-4.6":{"draws":24,"losses":39,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":49,"wins":3},"x-ai/grok-build-0.1":{"draws":11,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":45,"losses":35,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":23,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":34,"wins":3},"z-ai/glm-5.2":{"draws":79,"losses":43,"wins":10},"z-ai/glm-5.3":{"draws":17,"losses":42,"wins":3},"z-ai/glm-5.3-flash":{"draws":23,"losses":33,"wins":10},"z-ai/glm-5.3-flashx":{"draws":25,"losses":35,"wins":6}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":4,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":2,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":0},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":1},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":33,"wins":22},"claude-fable-5":{"draws":11,"losses":64,"wins":9},"claude-fable-5-1":{"draws":0,"losses":91,"wins":3},"claude-haiku-5-5":{"draws":18,"losses":52,"wins":10},"claude-opus-4-5":{"draws":38,"losses":80,"wins":18},"claude-opus-4-8":{"draws":16,"losses":50,"wins":10},"claude-opus-5":{"draws":14,"losses":117,"wins":9},"claude-opus-5-5":{"draws":5,"losses":85,"wins":2},"claude-sonnet-5":{"draws":26,"losses":40,"wins":18},"claude-sonnet-5-5":{"draws":12,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":20},"deepseek/deepseek-v4-flash":{"draws":33,"losses":51,"wins":44},"deepseek/deepseek-v4-pro":{"draws":17,"losses":47,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":35,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":44,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":33,"wins":3},"elorian/glimpse":{"draws":3,"losses":11,"wins":8},"fireworks/ember-1":{"draws":30,"losses":48,"wins":6},"gemini-3.1-pro-preview":{"draws":24,"losses":39,"wins":21},"gemini-4-argon":{"draws":2,"losses":35,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":14,"wins":31},"google/gemini-3.5-flash":{"draws":19,"losses":66,"wins":21},"google/gemini-3.5-flash-lite":{"draws":45,"losses":69,"wins":34},"google/gemini-3.6-flash":{"draws":36,"losses":101,"wins":25},"google/gemini-3.8-flash":{"draws":13,"losses":64,"wins":7},"google/gemma-4-31b-it":{"draws":20,"losses":11,"wins":17},"gpt-4.1":{"draws":8,"losses":15,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":16,"losses":39,"wins":21},"gpt-5.4":{"draws":21,"losses":53,"wins":8},"gpt-5.4-mini":{"draws":26,"losses":19,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":44,"wins":28},"gpt-5.5":{"draws":35,"losses":31,"wins":12},"gpt-5.6-luna":{"draws":26,"losses":32,"wins":26},"gpt-5.6-sol":{"draws":9,"losses":69,"wins":6},"gpt-5.6-terra":{"draws":25,"losses":39,"wins":16},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":24,"losses":44,"wins":16},"gpt-6-sol":{"draws":7,"losses":69,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":76,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":14,"wins":19},"inception/mercury-3":{"draws":11,"losses":15,"wins":8},"inclusionai/ling-3.0-flash":{"draws":27,"losses":13,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":25,"wins":18},"meta/muse-glimmer-30b":{"draws":34,"losses":23,"wins":17},"meta/muse-spark-1.2":{"draws":15,"losses":54,"wins":11},"meta/muse-spark-1.3":{"draws":15,"losses":57,"wins":12},"meta/muse-spark-open":{"draws":7,"losses":23,"wins":4},"meta/muse-wonder":{"draws":20,"losses":54,"wins":10},"minimax/minimax-m3":{"draws":11,"losses":18,"wins":17},"minimax/minimax-m3.1-flash":{"draws":6,"losses":22,"wins":12},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":19,"losses":14,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":15,"wins":2},"moonshotai/kimi-k3":{"draws":26,"losses":39,"wins":15},"nex-agi/nex-n2-pro":{"draws":11,"losses":13,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":23,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":2},"o3":{"draws":22,"losses":75,"wins":29},"openai/gpt-oss-120b":{"draws":24,"losses":25,"wins":25},"poolside/laguna-s-2.1":{"draws":34,"losses":32,"wins":18},"qwen/qwen3.7-max":{"draws":17,"losses":21,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":17,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":49,"wins":10},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":10},"qwen/qwen3.8-flash":{"draws":20,"losses":25,"wins":11},"qwen/qwen3.8-max":{"draws":27,"losses":38,"wins":19},"qwen/qwen3.8-max-0902":{"draws":21,"losses":49,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":24,"wins":8},"stealth/ox-alpha":{"draws":65,"losses":176,"wins":41},"stealth/space-bunny-alpha":{"draws":22,"losses":33,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":22,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":21,"wins":13},"tencent/hy4-preview":{"draws":19,"losses":51,"wins":12},"thinkingmachines/inkling":{"draws":29,"losses":43,"wins":42},"thinkingmachines/inkling-small":{"draws":33,"losses":25,"wins":26},"unbiased/pareto-26.10":{"draws":0,"losses":22,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":26,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":8,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":54,"wins":15},"x-ai/grok-4.6":{"draws":26,"losses":49,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":64,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":9},"xiaomi/mimo-v2.5":{"draws":37,"losses":43,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":27,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":30,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":37,"wins":5},"z-ai/glm-5.2":{"draws":56,"losses":74,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":63,"wins":5},"z-ai/glm-5.3-flash":{"draws":16,"losses":50,"wins":18},"z-ai/glm-5.3-flashx":{"draws":16,"losses":56,"wins":12}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":6},"claude-fable-5":{"draws":8,"losses":25,"wins":3},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":23,"wins":3},"claude-opus-4-5":{"draws":18,"losses":35,"wins":5},"claude-opus-4-8":{"draws":7,"losses":22,"wins":3},"claude-opus-5":{"draws":2,"losses":58,"wins":8},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":10,"losses":22,"wins":4},"claude-sonnet-5-5":{"draws":4,"losses":28,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":19,"losses":19,"wins":14},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":17,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":9,"wins":3},"elorian/glimpse":{"draws":2,"losses":5,"wins":3},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":20,"wins":3},"gemini-4-argon":{"draws":0,"losses":16,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":6},"google/gemini-3.5-flash-lite":{"draws":21,"losses":27,"wins":16},"google/gemini-3.6-flash":{"draws":19,"losses":43,"wins":8},"google/gemini-3.8-flash":{"draws":10,"losses":21,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":10,"losses":17,"wins":7},"gpt-5.4":{"draws":9,"losses":23,"wins":4},"gpt-5.4-mini":{"draws":11,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":15,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":13,"losses":12,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":31,"wins":1},"gpt-5.6-terra":{"draws":12,"losses":18,"wins":4},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":12,"losses":19,"wins":5},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":6},"inception/mercury-3":{"draws":2,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":17,"wins":11},"meta/muse-glimmer-30b":{"draws":11,"losses":10,"wins":3},"meta/muse-spark-1.2":{"draws":6,"losses":27,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":25,"wins":3},"meta/muse-spark-open":{"draws":6,"losses":9,"wins":3},"meta/muse-wonder":{"draws":6,"losses":26,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":11,"wins":5},"minimax/minimax-m3.1-flash":{"draws":6,"losses":6,"wins":4},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":21,"wins":5},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":7,"wins":1},"o3":{"draws":8,"losses":31,"wins":13},"openai/gpt-oss-120b":{"draws":10,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":15,"wins":7},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":6,"wins":5},"qwen/qwen3.8-max":{"draws":11,"losses":20,"wins":5},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":9,"wins":5},"stealth/ox-alpha":{"draws":28,"losses":83,"wins":15},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":13,"wins":2},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":2},"thinkingmachines/inkling":{"draws":16,"losses":19,"wins":17},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":11},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":3},"x-ai/grok-4.5":{"draws":8,"losses":24,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":0},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":23,"losses":17,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":4},"z-ai/glm-5.2":{"draws":32,"losses":27,"wins":13},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":6,"losses":27,"wins":3},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":5}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":30,"wins":6},"claude-opus-4-5":{"draws":23,"losses":32,"wins":23},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":7,"losses":65,"wins":10},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":19,"wins":14},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":21,"wins":30},"deepseek/deepseek-v4-pro":{"draws":9,"losses":21,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":22,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":26,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":18,"wins":5},"elorian/glimpse":{"draws":3,"losses":5,"wins":4},"fireworks/ember-1":{"draws":14,"losses":25,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":22,"wins":13},"gemini-4-argon":{"draws":3,"losses":12,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":14,"losses":30,"wins":16},"google/gemini-3.5-flash-lite":{"draws":25,"losses":24,"wins":35},"google/gemini-3.6-flash":{"draws":24,"losses":50,"wins":18},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":18,"wins":15},"gpt-5.4":{"draws":8,"losses":23,"wins":15},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":21,"wins":18},"gpt-5.5":{"draws":10,"losses":23,"wins":11},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":20,"wins":13},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inception/mercury-3":{"draws":6,"losses":12,"wins":4},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":18,"wins":22},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":17},"meta/muse-spark-1.2":{"draws":6,"losses":18,"wins":6},"meta/muse-spark-1.3":{"draws":11,"losses":27,"wins":10},"meta/muse-spark-open":{"draws":4,"losses":12,"wins":4},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"minimax/minimax-m3.1-flash":{"draws":6,"losses":14,"wins":10},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":22,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":0},"o3":{"draws":8,"losses":34,"wins":24},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":11,"losses":8,"wins":27},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":25,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":8,"wins":6},"stealth/ox-alpha":{"draws":37,"losses":86,"wins":35},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":15,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":7,"losses":26,"wins":13},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":30,"wins":7},"x-ai/grok-4.6":{"draws":10,"losses":35,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":30,"losses":32,"wins":34},"z-ai/glm-5.3":{"draws":9,"losses":28,"wins":9},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":10,"wins":17},"claude-fable-5":{"draws":11,"losses":34,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":29,"losses":30,"wins":19},"claude-opus-4-8":{"draws":12,"losses":27,"wins":5},"claude-opus-5":{"draws":11,"losses":64,"wins":7},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":19,"losses":17,"wins":12},"claude-sonnet-5-5":{"draws":10,"losses":31,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":17,"wins":32},"deepseek/deepseek-v4-pro":{"draws":10,"losses":23,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":24,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":26,"wins":6},"elorian/glimpse":{"draws":3,"losses":4,"wins":5},"fireworks/ember-1":{"draws":20,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":20,"wins":15},"gemini-4-argon":{"draws":0,"losses":23,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":17,"losses":27,"wins":16},"google/gemini-3.5-flash-lite":{"draws":26,"losses":22,"wins":36},"google/gemini-3.6-flash":{"draws":19,"losses":48,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":31,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":20,"wins":12},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":17,"losses":13,"wins":18},"gpt-5.5":{"draws":16,"losses":21,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":23,"wins":9},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":8,"losses":39,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":2,"wins":15},"inception/mercury-3":{"draws":6,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":12,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":13,"wins":22},"meta/muse-glimmer-30b":{"draws":22,"losses":9,"wins":11},"meta/muse-spark-1.2":{"draws":11,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":2},"meta/muse-spark-open":{"draws":4,"losses":13,"wins":3},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"minimax/minimax-m3.1-flash":{"draws":4,"losses":10,"wins":10},"mistralai/mistral-large-4-0":{"draws":12,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":23,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":5,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":1},"o3":{"draws":12,"losses":33,"wins":21},"openai/gpt-oss-120b":{"draws":17,"losses":6,"wins":19},"poolside/laguna-s-2.1":{"draws":18,"losses":17,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":20,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":19,"wins":8},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":19,"losses":24,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":9,"wins":3},"stealth/ox-alpha":{"draws":36,"losses":88,"wins":34},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":27,"wins":5},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":23,"losses":9,"wins":16},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":32,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":33,"losses":14,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":13,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":6},"z-ai/glm-5.2":{"draws":30,"losses":38,"wins":28},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":32,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":27,"wins":8}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":11},"claude-fable-5":{"draws":0,"losses":14,"wins":2},"claude-fable-5-1":{"draws":1,"losses":24,"wins":3},"claude-haiku-5-5":{"draws":6,"losses":8,"wins":12},"claude-opus-4-5":{"draws":15,"losses":9,"wins":12},"claude-opus-4-8":{"draws":6,"losses":5,"wins":5},"claude-opus-5":{"draws":6,"losses":30,"wins":10},"claude-opus-5-5":{"draws":2,"losses":20,"wins":0},"claude-sonnet-5":{"draws":8,"losses":3,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":9,"wins":6},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":24},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":4,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":9,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":30,"wins":7},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":10,"losses":3,"wins":13},"gemini-3.1-pro-preview":{"draws":3,"losses":5,"wins":2},"gemini-4-argon":{"draws":2,"losses":39,"wins":7},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":5,"losses":11,"wins":4},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":25},"google/gemini-3.6-flash":{"draws":10,"losses":28,"wins":14},"google/gemini-3.8-flash":{"draws":7,"losses":10,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":11},"gpt-4.1":{"draws":1,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":4,"wins":8},"gpt-5.4":{"draws":6,"losses":8,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":7},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":11},"gpt-5.5":{"draws":7,"losses":6,"wins":5},"gpt-5.6-luna":{"draws":10,"losses":1,"wins":11},"gpt-5.6-sol":{"draws":2,"losses":15,"wins":7},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":6},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":5,"losses":8,"wins":11},"gpt-6-sol":{"draws":1,"losses":18,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":17,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":2,"wins":8},"inception/mercury-3":{"draws":9,"losses":7,"wins":16},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":9},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":13},"meta/muse-glimmer-30b":{"draws":6,"losses":4,"wins":10},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":4},"meta/muse-spark-1.3":{"draws":3,"losses":10,"wins":9},"meta/muse-spark-open":{"draws":6,"losses":8,"wins":14},"meta/muse-wonder":{"draws":8,"losses":14,"wins":8},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":7},"minimax/minimax-m3.1-flash":{"draws":8,"losses":12,"wins":18},"mistralai/mistral-large-4-0":{"draws":1,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":7,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":5,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":2,"wins":15},"o3":{"draws":2,"losses":7,"wins":15},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":10,"losses":1,"wins":15},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":3,"wins":10},"qwen/qwen3.8-27b":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-flash":{"draws":5,"losses":5,"wins":10},"qwen/qwen3.8-max":{"draws":8,"losses":9,"wins":9},"qwen/qwen3.8-max-0902":{"draws":6,"losses":11,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":13,"losses":21,"wins":28},"stealth/space-bunny-alpha":{"draws":5,"losses":3,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":1,"losses":7,"wins":12},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":21},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":13},"x-ai/grok-4.6":{"draws":5,"losses":12,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":14,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":13,"losses":1,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":13,"losses":6,"wins":25},"z-ai/glm-5.3":{"draws":5,"losses":13,"wins":2},"z-ai/glm-5.3-flash":{"draws":3,"losses":11,"wins":10},"z-ai/glm-5.3-flashx":{"draws":2,"losses":10,"wins":10}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":23},"claude-fable-5":{"draws":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":4,"losses":39,"wins":11},"claude-haiku-5-5":{"draws":16,"losses":12,"wins":18},"claude-opus-4-5":{"draws":27,"losses":17,"wins":34},"claude-opus-4-8":{"draws":12,"losses":19,"wins":13},"claude-opus-5":{"draws":11,"losses":54,"wins":17},"claude-opus-5-5":{"draws":0,"losses":43,"wins":9},"claude-sonnet-5":{"draws":17,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":10,"wins":8},"elorian/glimpse":{"draws":4,"losses":9,"wins":1},"fireworks/ember-1":{"draws":18,"losses":10,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":11,"wins":26},"gemini-4-argon":{"draws":1,"losses":21,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":34},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":27,"losses":30,"wins":35},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":14},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":23},"gpt-5.4":{"draws":15,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":18,"losses":12,"wins":14},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":25,"wins":14},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":18,"losses":14,"wins":16},"gpt-6-sol":{"draws":6,"losses":32,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":37,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":21},"inception/mercury-3":{"draws":7,"losses":8,"wins":4},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":32},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":16},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-spark-open":{"draws":7,"losses":9,"wins":10},"meta/muse-wonder":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"minimax/minimax-m3.1-flash":{"draws":1,"losses":6,"wins":11},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":8,"wins":25},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":1,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":2},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":27},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":0,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":4,"wins":17},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":17,"losses":12,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":4,"wins":9},"stealth/ox-alpha":{"draws":43,"losses":60,"wins":55},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":13},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":25,"losses":7,"wins":32},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":11,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":15,"wins":18},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":24,"losses":7,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":24,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":11,"losses":21,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":18,"wins":16}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":20,"wins":8},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":0,"losses":39,"wins":1},"claude-haiku-5-5":{"draws":2,"losses":22,"wins":10},"claude-opus-4-5":{"draws":18,"losses":31,"wins":9},"claude-opus-4-8":{"draws":4,"losses":20,"wins":8},"claude-opus-5":{"draws":8,"losses":56,"wins":4},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":8,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":4,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":20,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":14,"wins":3},"elorian/glimpse":{"draws":3,"losses":5,"wins":4},"fireworks/ember-1":{"draws":7,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":15,"wins":15},"gemini-4-argon":{"draws":0,"losses":16,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":6,"losses":22,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":16,"wins":29},"google/gemini-3.6-flash":{"draws":9,"losses":44,"wins":15},"google/gemini-3.8-flash":{"draws":4,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":2,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":7,"losses":16,"wins":11},"gpt-5.4":{"draws":4,"losses":17,"wins":13},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":19},"gpt-5.5":{"draws":8,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":18,"wins":10},"gpt-6-astra":{"draws":0,"losses":34,"wins":2},"gpt-6-luna":{"draws":9,"losses":18,"wins":9},"gpt-6-sol":{"draws":2,"losses":29,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":32,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":11},"inception/mercury-3":{"draws":8,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":11,"wins":18},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":4,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":0,"losses":10,"wins":0},"meta/muse-wonder":{"draws":5,"losses":23,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":6},"minimax/minimax-m3.1-flash":{"draws":4,"losses":12,"wins":8},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":23,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":8},"o3":{"draws":6,"losses":28,"wins":16},"openai/gpt-oss-120b":{"draws":8,"losses":11,"wins":15},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":18},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":11},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":25,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":5,"wins":3},"stealth/ox-alpha":{"draws":29,"losses":65,"wins":30},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":16},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":25},"thinkingmachines/inkling-small":{"draws":8,"losses":7,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":28,"wins":3},"x-ai/grok-4.6":{"draws":7,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":10,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":17,"losses":25,"wins":30},"z-ai/glm-5.3":{"draws":5,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":10}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":6,"wins":7},"claude-fable-5":{"draws":9,"losses":9,"wins":2},"claude-fable-5-1":{"draws":3,"losses":23,"wins":2},"claude-haiku-5-5":{"draws":10,"losses":11,"wins":5},"claude-opus-4-5":{"draws":19,"losses":22,"wins":13},"claude-opus-4-8":{"draws":5,"losses":17,"wins":4},"claude-opus-5":{"draws":4,"losses":34,"wins":4},"claude-opus-5-5":{"draws":3,"losses":29,"wins":0},"claude-sonnet-5":{"draws":8,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":9,"losses":11,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":13,"losses":7,"wins":12},"deepseek/deepseek-v4-pro":{"draws":3,"losses":9,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":16,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":13,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":19,"wins":7},"elorian/glimpse":{"draws":8,"losses":10,"wins":4},"fireworks/ember-1":{"draws":3,"losses":12,"wins":3},"gemini-3.1-pro-preview":{"draws":11,"losses":10,"wins":5},"gemini-4-argon":{"draws":3,"losses":34,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":4},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":18},"google/gemini-3.6-flash":{"draws":14,"losses":28,"wins":8},"google/gemini-3.8-flash":{"draws":6,"losses":17,"wins":3},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":4},"gpt-4.1":{"draws":2,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":15,"wins":4},"gpt-5.4":{"draws":9,"losses":18,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":10},"gpt-5.5":{"draws":8,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":21,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":9,"wins":6},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":2,"losses":14,"wins":4},"gpt-6-sol":{"draws":7,"losses":21,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":15,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":7},"inception/mercury-3":{"draws":5,"losses":11,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":8,"losses":10,"wins":10},"meta/muse-glimmer-30b":{"draws":7,"losses":7,"wins":6},"meta/muse-spark-1.2":{"draws":4,"losses":16,"wins":2},"meta/muse-spark-1.3":{"draws":2,"losses":13,"wins":1},"meta/muse-spark-open":{"draws":10,"losses":21,"wins":5},"meta/muse-wonder":{"draws":3,"losses":14,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":2},"minimax/minimax-m3.1-flash":{"draws":3,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":5,"losses":7,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":10,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":3},"o3":{"draws":2,"losses":10,"wins":12},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":6},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":11,"wins":4},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-max":{"draws":9,"losses":13,"wins":6},"qwen/qwen3.8-max-0902":{"draws":6,"losses":17,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":17,"wins":10},"stealth/ox-alpha":{"draws":30,"losses":52,"wins":22},"stealth/space-bunny-alpha":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":10},"thinkingmachines/inkling":{"draws":8,"losses":20,"wins":16},"thinkingmachines/inkling-small":{"draws":8,"losses":11,"wins":3},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":7,"losses":11,"wins":8},"x-ai/grok-4.6":{"draws":7,"losses":13,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":12,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":10,"wins":2},"z-ai/glm-5.2":{"draws":18,"losses":25,"wins":11},"z-ai/glm-5.3":{"draws":1,"losses":15,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":4,"losses":16,"wins":4}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":10},"claude-fable-5":{"draws":10,"losses":24,"wins":8},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":7},"claude-opus-4-5":{"draws":24,"losses":31,"wins":13},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":11,"losses":62,"wins":7},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":14,"losses":20,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":24},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":17,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":20,"wins":2},"elorian/glimpse":{"draws":1,"losses":2,"wins":3},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":19,"wins":9},"gemini-4-argon":{"draws":1,"losses":11,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":15,"wins":22},"google/gemini-3.6-flash":{"draws":27,"losses":42,"wins":11},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":7},"gpt-4.1":{"draws":6,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":19,"losses":10,"wins":9},"gpt-5.4":{"draws":15,"losses":22,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":14,"wins":17},"gpt-5.5":{"draws":19,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":5},"gpt-5.6-terra":{"draws":21,"losses":10,"wins":9},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":6,"losses":31,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":8},"inception/mercury-3":{"draws":9,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":13},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":2,"losses":10,"wins":8},"meta/muse-wonder":{"draws":7,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":6},"minimax/minimax-m3.1-flash":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":16,"wins":11},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":5},"o3":{"draws":18,"losses":21,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":11,"wins":10},"poolside/laguna-s-2.1":{"draws":20,"losses":9,"wins":13},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":9,"losses":1,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":22,"wins":6},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":8},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":10,"wins":5},"stealth/ox-alpha":{"draws":48,"losses":67,"wins":27},"stealth/space-bunny-alpha":{"draws":15,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":19},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":14},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":11,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":11,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":7},"z-ai/glm-5.2":{"draws":42,"losses":19,"wins":23},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":15,"losses":18,"wins":9}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":8},"claude-fable-5":{"draws":6,"losses":34,"wins":2},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":23,"losses":43,"wins":2},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":10,"losses":58,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":13,"losses":27,"wins":2},"claude-sonnet-5-5":{"draws":7,"losses":32,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":28,"losses":25,"wins":9},"deepseek/deepseek-v4-pro":{"draws":9,"losses":25,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":23,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":19,"wins":2},"elorian/glimpse":{"draws":2,"losses":9,"wins":1},"fireworks/ember-1":{"draws":13,"losses":28,"wins":1},"gemini-3.1-pro-preview":{"draws":14,"losses":25,"wins":3},"gemini-4-argon":{"draws":2,"losses":20,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":12},"google/gemini-3.5-flash":{"draws":14,"losses":32,"wins":6},"google/gemini-3.5-flash-lite":{"draws":22,"losses":37,"wins":15},"google/gemini-3.6-flash":{"draws":29,"losses":46,"wins":5},"google/gemini-3.8-flash":{"draws":8,"losses":32,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":11,"wins":2},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":10,"losses":18,"wins":8},"gpt-5.4":{"draws":9,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":11,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":27,"wins":5},"gpt-5.5":{"draws":12,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":35,"wins":3},"gpt-5.6-terra":{"draws":12,"losses":25,"wins":3},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":25,"wins":2},"gpt-6-sol":{"draws":3,"losses":38,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":10,"wins":5},"inception/mercury-3":{"draws":2,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":15,"losses":7,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":18,"wins":10},"meta/muse-glimmer-30b":{"draws":17,"losses":14,"wins":5},"meta/muse-spark-1.2":{"draws":9,"losses":28,"wins":3},"meta/muse-spark-1.3":{"draws":7,"losses":34,"wins":1},"meta/muse-spark-open":{"draws":5,"losses":15,"wins":2},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":5},"minimax/minimax-m3.1-flash":{"draws":5,"losses":13,"wins":4},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":28,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":15,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":0},"o3":{"draws":11,"losses":38,"wins":5},"openai/gpt-oss-120b":{"draws":15,"losses":18,"wins":3},"poolside/laguna-s-2.1":{"draws":19,"losses":17,"wins":6},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":30,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":19,"wins":1},"qwen/qwen3.8-flash":{"draws":10,"losses":16,"wins":2},"qwen/qwen3.8-max":{"draws":11,"losses":27,"wins":4},"qwen/qwen3.8-max-0902":{"draws":15,"losses":25,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":11,"wins":3},"stealth/ox-alpha":{"draws":34,"losses":93,"wins":13},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":12,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":3},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":2},"thinkingmachines/inkling":{"draws":21,"losses":27,"wins":8},"thinkingmachines/inkling-small":{"draws":20,"losses":13,"wins":9},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":30,"wins":3},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":2},"z-ai/glm-5.2":{"draws":36,"losses":41,"wins":7},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":24,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":31,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":5,"losses":29,"wins":14},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":30,"losses":16,"wins":32},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":12,"losses":55,"wins":15},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":14,"losses":11,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":21,"wins":17},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":22,"losses":13,"wins":37},"deepseek/deepseek-v4-pro":{"draws":8,"losses":17,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":11,"wins":7},"elorian/glimpse":{"draws":5,"losses":5,"wins":2},"fireworks/ember-1":{"draws":13,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"gemini-4-argon":{"draws":0,"losses":14,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":17,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":17,"wins":41},"google/gemini-3.6-flash":{"draws":28,"losses":33,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":26,"wins":11},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":5,"losses":26,"wins":15},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":28},"gpt-5.5":{"draws":10,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":15,"wins":19},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":28},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":20,"wins":16},"meta/muse-spark-1.3":{"draws":8,"losses":24,"wins":16},"meta/muse-spark-open":{"draws":8,"losses":10,"wins":4},"meta/muse-wonder":{"draws":8,"losses":29,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"minimax/minimax-m3.1-flash":{"draws":11,"losses":7,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":11,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":5,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":1,"wins":5},"o3":{"draws":10,"losses":27,"wins":29},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":23},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":17,"wins":20},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":10,"losses":19,"wins":19},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":5,"wins":15},"stealth/ox-alpha":{"draws":40,"losses":66,"wins":52},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":22,"losses":13,"wins":29},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":19,"wins":16},"x-ai/grok-4.6":{"draws":6,"losses":27,"wins":15},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":28,"losses":9,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":19,"wins":40},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":11,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":25,"wins":10}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":8},"claude-fable-5":{"draws":11,"losses":30,"wins":1},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":7},"claude-opus-4-5":{"draws":24,"losses":32,"wins":12},"claude-opus-4-8":{"draws":13,"losses":21,"wins":4},"claude-opus-5":{"draws":3,"losses":62,"wins":5},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":18,"losses":16,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":20,"losses":26,"wins":16},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":17,"wins":3},"elorian/glimpse":{"draws":6,"losses":4,"wins":4},"fireworks/ember-1":{"draws":17,"losses":18,"wins":7},"gemini-3.1-pro-preview":{"draws":16,"losses":20,"wins":6},"gemini-4-argon":{"draws":3,"losses":16,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":19,"losses":21,"wins":12},"google/gemini-3.5-flash-lite":{"draws":27,"losses":20,"wins":27},"google/gemini-3.6-flash":{"draws":23,"losses":42,"wins":15},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":6},"google/gemma-4-31b-it":{"draws":13,"losses":6,"wins":7},"gpt-4.1":{"draws":5,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":13,"losses":11,"wins":12},"gpt-5.4":{"draws":14,"losses":16,"wins":10},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":11},"gpt-5.5":{"draws":17,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":20,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":15,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":23,"wins":6},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":6,"wins":8},"inception/mercury-3":{"draws":2,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":5},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":17,"wins":15},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":11},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":11,"losses":25,"wins":6},"meta/muse-spark-open":{"draws":5,"losses":15,"wins":4},"meta/muse-wonder":{"draws":12,"losses":27,"wins":3},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":7},"minimax/minimax-m3.1-flash":{"draws":14,"losses":8,"wins":8},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":12,"losses":10,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":3},"o3":{"draws":9,"losses":30,"wins":17},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":14},"poolside/laguna-s-2.1":{"draws":19,"losses":11,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":4},"qwen/qwen3.8-max":{"draws":17,"losses":23,"wins":2},"qwen/qwen3.8-max-0902":{"draws":17,"losses":18,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":13,"wins":3},"stealth/ox-alpha":{"draws":47,"losses":76,"wins":19},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":17,"wins":17},"thinkingmachines/inkling-small":{"draws":20,"losses":12,"wins":10},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":11,"losses":26,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":24,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":28,"losses":17,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":42,"losses":30,"wins":12},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":23,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":4}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":2},"claude-fable-5":{"draws":2,"losses":9,"wins":3},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":5,"wins":1},"claude-opus-4-5":{"draws":5,"losses":7,"wins":2},"claude-opus-4-8":{"draws":1,"losses":12,"wins":1},"claude-opus-5":{"draws":3,"losses":23,"wins":0},"claude-opus-5-5":{"draws":3,"losses":11,"wins":0},"claude-sonnet-5":{"draws":5,"losses":8,"wins":3},"claude-sonnet-5-5":{"draws":3,"losses":8,"wins":1},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":7},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":9,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":18,"wins":1},"elorian/glimpse":{"draws":3,"losses":7,"wins":2},"fireworks/ember-1":{"draws":0,"losses":7,"wins":1},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":2},"gemini-4-argon":{"draws":0,"losses":24,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":8,"losses":7,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":2},"google/gemini-3.8-flash":{"draws":2,"losses":9,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":4,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":4,"wins":3},"gpt-5.4":{"draws":3,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":5},"gpt-5.5":{"draws":2,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":7,"losses":4,"wins":3},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":6,"losses":5,"wins":1},"gpt-6-sol":{"draws":0,"losses":14,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":9,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inception/mercury-3":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":1},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":3,"wins":3},"meta/muse-glimmer-30b":{"draws":0,"losses":4,"wins":4},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":2},"meta/muse-spark-1.3":{"draws":3,"losses":9,"wins":2},"meta/muse-spark-open":{"draws":4,"losses":13,"wins":3},"meta/muse-wonder":{"draws":4,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":1},"minimax/minimax-m3.1-flash":{"draws":6,"losses":7,"wins":3},"mistralai/mistral-large-4-0":{"draws":6,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":2},"o3":{"draws":3,"losses":9,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":6,"wins":1},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":1},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.8-max-0902":{"draws":7,"losses":5,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":13,"wins":5},"stealth/ox-alpha":{"draws":15,"losses":27,"wins":6},"stealth/space-bunny-alpha":{"draws":2,"losses":6,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":6},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":9,"wins":1},"thinkingmachines/inkling":{"draws":3,"losses":6,"wins":5},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":2},"unbiased/pareto-26.10":{"draws":0,"losses":4,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":4,"wins":1},"x-ai/grok-4.6":{"draws":2,"losses":5,"wins":1},"x-ai/grok-4.7":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":3,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":6,"wins":5},"z-ai/glm-5.3":{"draws":0,"losses":9,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":3},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":13,"wins":14},"claude-fable-5":{"draws":8,"losses":28,"wins":6},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":12},"claude-opus-4-5":{"draws":19,"losses":38,"wins":11},"claude-opus-4-8":{"draws":6,"losses":22,"wins":10},"claude-opus-5":{"draws":9,"losses":58,"wins":3},"claude-opus-5-5":{"draws":2,"losses":43,"wins":1},"claude-sonnet-5":{"draws":11,"losses":18,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":13,"losses":30,"wins":19},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":24,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":23,"wins":2},"elorian/glimpse":{"draws":3,"losses":6,"wins":3},"fireworks/ember-1":{"draws":12,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":11},"gemini-4-argon":{"draws":1,"losses":19,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":11,"wins":12},"google/gemini-3.5-flash":{"draws":14,"losses":28,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":23,"wins":25},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":15},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":8},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":13,"losses":16,"wins":9},"gpt-5.4":{"draws":15,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":5,"losses":21,"wins":16},"gpt-5.5":{"draws":17,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":12},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":12,"wins":7},"inception/mercury-3":{"draws":1,"losses":8,"wins":5},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":23,"wins":10},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":10,"losses":20,"wins":10},"meta/muse-spark-1.3":{"draws":6,"losses":32,"wins":4},"meta/muse-spark-open":{"draws":5,"losses":8,"wins":3},"meta/muse-wonder":{"draws":9,"losses":30,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":7},"minimax/minimax-m3.1-flash":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":23,"wins":9},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":7,"wins":4},"o3":{"draws":12,"losses":32,"wins":20},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":11},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":25,"wins":5},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":10,"wins":6},"stealth/ox-alpha":{"draws":30,"losses":86,"wins":26},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":25,"wins":6},"thinkingmachines/inkling":{"draws":17,"losses":19,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":14,"wins":13},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":6,"wins":3},"x-ai/grok-4.5":{"draws":9,"losses":30,"wins":3},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":33,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":22,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":21,"wins":3},"z-ai/glm-5.2":{"draws":26,"losses":30,"wins":28},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":4},"z-ai/glm-5.3-flash":{"draws":5,"losses":26,"wins":11},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":7}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":1},"claude-fable-5":{"draws":2,"losses":10,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":2,"wins":2},"claude-opus-4-5":{"draws":6,"losses":3,"wins":1},"claude-opus-4-8":{"draws":1,"losses":4,"wins":1},"claude-opus-5":{"draws":3,"losses":8,"wins":1},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":5,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":0},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":12,"wins":0},"elorian/glimpse":{"draws":4,"losses":5,"wins":3},"fireworks/ember-1":{"draws":2,"losses":6,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":2},"gemini-4-argon":{"draws":0,"losses":16,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":4,"wins":2},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":3},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":6,"wins":1},"gpt-5.5":{"draws":0,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":2},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":3,"losses":8,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"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":3,"wins":1},"inception/mercury-3":{"draws":2,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":2},"meta/muse-glimmer-30b":{"draws":0,"losses":3,"wins":1},"meta/muse-spark-1.2":{"draws":2,"losses":8,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":5,"wins":0},"meta/muse-spark-open":{"draws":3,"losses":15,"wins":0},"meta/muse-wonder":{"draws":0,"losses":5,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":2},"minimax/minimax-m3.1-flash":{"draws":6,"losses":5,"wins":3},"mistralai/mistral-large-4-0":{"draws":2,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":4,"wins":0},"o3":{"draws":2,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":5},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":10,"wins":1},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":6,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":12,"wins":3},"stealth/ox-alpha":{"draws":10,"losses":11,"wins":3},"stealth/space-bunny-alpha":{"draws":2,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":4,"wins":4},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":6},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":5,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":5,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":5,"wins":2},"z-ai/glm-5.3":{"draws":2,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":8,"wins":2}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":11,"wins":14},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":19,"wins":10},"claude-opus-4-5":{"draws":18,"losses":38,"wins":22},"claude-opus-4-8":{"draws":14,"losses":22,"wins":8},"claude-opus-5":{"draws":13,"losses":65,"wins":4},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":14},"claude-sonnet-5-5":{"draws":8,"losses":31,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":14,"wins":33},"deepseek/deepseek-v4-pro":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":16,"wins":6},"elorian/glimpse":{"draws":3,"losses":3,"wins":4},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":16},"gemini-4-argon":{"draws":0,"losses":24,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":19,"losses":25,"wins":16},"google/gemini-3.5-flash-lite":{"draws":28,"losses":20,"wins":36},"google/gemini-3.6-flash":{"draws":25,"losses":44,"wins":23},"google/gemini-3.8-flash":{"draws":16,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":11,"wins":13},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":20,"wins":16},"gpt-5.5":{"draws":13,"losses":20,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":18,"losses":13,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":2,"losses":44,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":15},"inception/mercury-3":{"draws":4,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":27},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":27,"wins":6},"meta/muse-spark-1.3":{"draws":12,"losses":29,"wins":7},"meta/muse-spark-open":{"draws":7,"losses":10,"wins":7},"meta/muse-wonder":{"draws":7,"losses":36,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":2,"losses":4,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":13},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":9,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":2},"o3":{"draws":10,"losses":22,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":26,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":15,"wins":5},"stealth/ox-alpha":{"draws":44,"losses":82,"wins":32},"stealth/space-bunny-alpha":{"draws":13,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":20,"losses":14,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":20},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":11},"x-ai/grok-4.6":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":25,"losses":20,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":27,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":27,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":8},"z-ai/glm-5.3-flash":{"draws":14,"losses":25,"wins":9},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":14,"wins":8},"claude-fable-5":{"draws":7,"losses":26,"wins":3},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":21,"wins":5},"claude-opus-4-5":{"draws":19,"losses":34,"wins":5},"claude-opus-4-8":{"draws":9,"losses":22,"wins":1},"claude-opus-5":{"draws":7,"losses":57,"wins":4},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":4},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":20},"deepseek/deepseek-v4-pro":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":16,"wins":4},"elorian/glimpse":{"draws":3,"losses":8,"wins":3},"fireworks/ember-1":{"draws":14,"losses":20,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":6},"gemini-4-argon":{"draws":0,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":7},"google/gemini-3.5-flash-lite":{"draws":17,"losses":25,"wins":18},"google/gemini-3.6-flash":{"draws":20,"losses":39,"wins":9},"google/gemini-3.8-flash":{"draws":7,"losses":27,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":2,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":16,"wins":7},"gpt-5.4":{"draws":7,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":13},"gpt-5.5":{"draws":11,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":34,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":21,"wins":3},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":12,"losses":17,"wins":7},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":7,"wins":7},"inception/mercury-3":{"draws":6,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":15,"wins":10},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":11},"meta/muse-spark-1.2":{"draws":7,"losses":28,"wins":1},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":4},"meta/muse-spark-open":{"draws":1,"losses":13,"wins":0},"meta/muse-wonder":{"draws":4,"losses":28,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":8},"minimax/minimax-m3.1-flash":{"draws":2,"losses":8,"wins":4},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":3,"wins":3},"o3":{"draws":7,"losses":36,"wins":7},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":17,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":19,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-max-0902":{"draws":12,"losses":20,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":11,"wins":1},"stealth/ox-alpha":{"draws":34,"losses":80,"wins":10},"stealth/space-bunny-alpha":{"draws":6,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":25,"wins":14},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":5},"x-ai/grok-4.6":{"draws":9,"losses":26,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":19,"losses":19,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":32,"losses":28,"wins":12},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":17,"wins":25},"claude-fable-5":{"draws":10,"losses":48,"wins":14},"claude-fable-5-1":{"draws":0,"losses":79,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":30,"wins":23},"claude-opus-4-5":{"draws":35,"losses":55,"wins":26},"claude-opus-4-8":{"draws":14,"losses":38,"wins":12},"claude-opus-5":{"draws":8,"losses":111,"wins":7},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":19,"losses":33,"wins":20},"claude-sonnet-5-5":{"draws":10,"losses":47,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":11,"wins":14},"deepseek/deepseek-v4-flash":{"draws":33,"losses":31,"wins":48},"deepseek/deepseek-v4-pro":{"draws":13,"losses":27,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":28,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":32,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":29,"wins":3},"elorian/glimpse":{"draws":1,"losses":12,"wins":7},"fireworks/ember-1":{"draws":22,"losses":37,"wins":13},"gemini-3.1-pro-preview":{"draws":20,"losses":31,"wins":21},"gemini-4-argon":{"draws":1,"losses":30,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":9,"wins":28},"google/gemini-3.5-flash":{"draws":16,"losses":52,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":34,"wins":63},"google/gemini-3.6-flash":{"draws":34,"losses":68,"wins":36},"google/gemini-3.8-flash":{"draws":12,"losses":49,"wins":11},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":17},"gpt-4.1":{"draws":5,"losses":12,"wins":7},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":17,"losses":23,"wins":28},"gpt-5.4":{"draws":17,"losses":44,"wins":9},"gpt-5.4-mini":{"draws":18,"losses":15,"wins":15},"gpt-5.4-nano":{"draws":16,"losses":28,"wins":34},"gpt-5.5":{"draws":25,"losses":30,"wins":13},"gpt-5.6-luna":{"draws":21,"losses":23,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":57,"wins":7},"gpt-5.6-terra":{"draws":23,"losses":33,"wins":12},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":20,"losses":25,"wins":27},"gpt-6-sol":{"draws":10,"losses":54,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":67,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":12,"wins":18},"inception/mercury-3":{"draws":10,"losses":13,"wins":5},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":21,"wins":34},"meta/muse-glimmer-30b":{"draws":23,"losses":19,"wins":24},"meta/muse-spark-1.2":{"draws":11,"losses":43,"wins":16},"meta/muse-spark-1.3":{"draws":9,"losses":44,"wins":19},"meta/muse-spark-open":{"draws":7,"losses":25,"wins":4},"meta/muse-wonder":{"draws":10,"losses":57,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":16,"wins":13},"mistralai/mistral-large-4-0":{"draws":13,"losses":17,"wins":16},"mistralai/mistral-medium-3-5":{"draws":13,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":19,"losses":31,"wins":20},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":14,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":15,"wins":8},"o3":{"draws":17,"losses":54,"wins":39},"openai/gpt-oss-120b":{"draws":19,"losses":14,"wins":33},"poolside/laguna-s-2.1":{"draws":22,"losses":13,"wins":19},"qwen/qwen3.7-max":{"draws":14,"losses":18,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":42,"wins":10},"qwen/qwen3.8-27b":{"draws":12,"losses":22,"wins":16},"qwen/qwen3.8-flash":{"draws":17,"losses":17,"wins":14},"qwen/qwen3.8-max":{"draws":22,"losses":27,"wins":23},"qwen/qwen3.8-max-0902":{"draws":19,"losses":35,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":13,"wins":3},"stealth/ox-alpha":{"draws":55,"losses":133,"wins":60},"stealth/space-bunny-alpha":{"draws":13,"losses":22,"wins":21},"stepfun/step-3.7-flash":{"draws":15,"losses":15,"wins":26},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":14},"tencent/hy4-preview":{"draws":20,"losses":35,"wins":15},"thinkingmachines/inkling":{"draws":22,"losses":29,"wins":49},"thinkingmachines/inkling-small":{"draws":26,"losses":10,"wins":36},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":14,"losses":45,"wins":13},"x-ai/grok-4.6":{"draws":20,"losses":42,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":30,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":16,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":33,"wins":13},"z-ai/glm-5.2":{"draws":52,"losses":48,"wins":44},"z-ai/glm-5.3":{"draws":7,"losses":52,"wins":9},"z-ai/glm-5.3-flash":{"draws":15,"losses":39,"wins":18},"z-ai/glm-5.3-flashx":{"draws":13,"losses":44,"wins":15}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":17,"wins":10},"claude-fable-5":{"draws":8,"losses":29,"wins":5},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":19,"wins":8},"claude-opus-4-5":{"draws":21,"losses":34,"wins":13},"claude-opus-4-8":{"draws":11,"losses":18,"wins":9},"claude-opus-5":{"draws":8,"losses":59,"wins":3},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":15,"losses":20,"wins":7},"claude-sonnet-5-5":{"draws":13,"losses":18,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":21,"losses":19,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":23,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":15,"wins":6},"elorian/glimpse":{"draws":2,"losses":4,"wins":6},"fireworks/ember-1":{"draws":13,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":13},"gemini-4-argon":{"draws":0,"losses":24,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":16,"losses":22,"wins":34},"google/gemini-3.6-flash":{"draws":22,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":14,"losses":19,"wins":9},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":15,"losses":14,"wins":9},"gpt-5.4":{"draws":11,"losses":20,"wins":9},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":16},"gpt-5.5":{"draws":14,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":22,"wins":5},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":11,"losses":16,"wins":15},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":10},"inception/mercury-3":{"draws":3,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":20},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":25,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":8},"meta/muse-spark-open":{"draws":4,"losses":16,"wins":2},"meta/muse-wonder":{"draws":5,"losses":28,"wins":9},"minimax/minimax-m3":{"draws":10,"losses":2,"wins":12},"minimax/minimax-m3.1-flash":{"draws":1,"losses":12,"wins":9},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":9,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":5,"wins":2},"o3":{"draws":10,"losses":34,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":17,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.8-max":{"draws":18,"losses":17,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":4,"wins":7},"stealth/ox-alpha":{"draws":33,"losses":80,"wins":27},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":17,"losses":11,"wins":28},"thinkingmachines/inkling-small":{"draws":14,"losses":9,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":23,"wins":8},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":14,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":6,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":30,"losses":27,"wins":27},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":7},"claude-fable-5":{"draws":7,"losses":26,"wins":3},"claude-fable-5-1":{"draws":5,"losses":35,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":28,"wins":1},"claude-opus-4-5":{"draws":25,"losses":28,"wins":7},"claude-opus-4-8":{"draws":8,"losses":24,"wins":4},"claude-opus-5":{"draws":6,"losses":45,"wins":7},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":11,"losses":20,"wins":5},"claude-sonnet-5-5":{"draws":8,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":17,"losses":25,"wins":12},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":16,"wins":3},"elorian/glimpse":{"draws":4,"losses":4,"wins":4},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":22,"wins":2},"gemini-4-argon":{"draws":0,"losses":22,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":30,"wins":5},"google/gemini-3.5-flash-lite":{"draws":18,"losses":36,"wins":10},"google/gemini-3.6-flash":{"draws":23,"losses":44,"wins":3},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":6},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":20,"wins":2},"gpt-5.4":{"draws":6,"losses":27,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":22,"wins":8},"gpt-5.5":{"draws":11,"losses":19,"wins":2},"gpt-5.6-luna":{"draws":14,"losses":16,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":21,"wins":2},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":14,"losses":20,"wins":2},"gpt-6-sol":{"draws":7,"losses":28,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":9,"wins":7},"inception/mercury-3":{"draws":8,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":9,"losses":12,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":22,"wins":8},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":27,"wins":4},"meta/muse-spark-open":{"draws":2,"losses":11,"wins":1},"meta/muse-wonder":{"draws":4,"losses":30,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":5},"minimax/minimax-m3.1-flash":{"draws":6,"losses":14,"wins":2},"mistralai/mistral-large-4-0":{"draws":4,"losses":17,"wins":1},"mistralai/mistral-medium-3-5":{"draws":9,"losses":9,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":16,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":0},"o3":{"draws":6,"losses":41,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":17,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":19,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":12,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":2},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":4,"wins":3},"stealth/ox-alpha":{"draws":23,"losses":72,"wins":7},"stealth/space-bunny-alpha":{"draws":8,"losses":19,"wins":3},"stepfun/step-3.7-flash":{"draws":5,"losses":15,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":5},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":9},"thinkingmachines/inkling-small":{"draws":15,"losses":18,"wins":3},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":7,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":24,"losses":29,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":16,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":42,"wins":8},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":2},"z-ai/glm-5.3-flashx":{"draws":7,"losses":28,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":20},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":14},"claude-opus-4-5":{"draws":27,"losses":25,"wins":26},"claude-opus-4-8":{"draws":14,"losses":18,"wins":12},"claude-opus-5":{"draws":8,"losses":62,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":15,"losses":10,"wins":23},"claude-sonnet-5-5":{"draws":8,"losses":22,"wins":18},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":13,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":22,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":17,"wins":7},"elorian/glimpse":{"draws":1,"losses":10,"wins":3},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":2,"losses":13,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":18,"losses":19,"wins":23},"google/gemini-3.5-flash-lite":{"draws":28,"losses":16,"wins":40},"google/gemini-3.6-flash":{"draws":22,"losses":44,"wins":26},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":13,"wins":19},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":25},"gpt-5.5":{"draws":12,"losses":18,"wins":14},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":32,"wins":8},"gpt-5.6-terra":{"draws":14,"losses":11,"wins":21},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":5,"losses":3,"wins":6},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":30},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":22},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":18},"meta/muse-spark-open":{"draws":5,"losses":14,"wins":5},"meta/muse-wonder":{"draws":10,"losses":24,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":18},"minimax/minimax-m3.1-flash":{"draws":4,"losses":6,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":18,"wins":18},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":7},"o3":{"draws":12,"losses":18,"wins":36},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":24},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":7},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":25,"wins":12},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":6,"wins":14},"stealth/ox-alpha":{"draws":37,"losses":67,"wins":54},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":13},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":11},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":29},"unbiased/pareto-26.10":{"draws":2,"losses":4,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":22,"wins":16},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":6,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":30,"losses":26,"wins":40},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":7},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":25,"wins":11}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":8},"claude-fable-5":{"draws":5,"losses":17,"wins":2},"claude-fable-5-1":{"draws":1,"losses":25,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":2},"claude-opus-4-5":{"draws":17,"losses":19,"wins":2},"claude-opus-4-8":{"draws":5,"losses":12,"wins":3},"claude-opus-5":{"draws":8,"losses":28,"wins":2},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":6,"losses":13,"wins":5},"claude-sonnet-5-5":{"draws":8,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":9,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":10,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":6,"wins":1},"elorian/glimpse":{"draws":2,"losses":3,"wins":3},"fireworks/ember-1":{"draws":12,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":7},"gemini-4-argon":{"draws":1,"losses":15,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":20,"wins":4},"google/gemini-3.5-flash-lite":{"draws":10,"losses":18,"wins":12},"google/gemini-3.6-flash":{"draws":14,"losses":26,"wins":6},"google/gemini-3.8-flash":{"draws":7,"losses":17,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":8,"wins":5},"gpt-5.4":{"draws":7,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":4},"gpt-5.5":{"draws":8,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":9,"losses":11,"wins":4},"gpt-6-sol":{"draws":7,"losses":16,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":21,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":8},"inception/mercury-3":{"draws":7,"losses":4,"wins":1},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":8},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":15,"wins":1},"meta/muse-spark-open":{"draws":3,"losses":9,"wins":0},"meta/muse-wonder":{"draws":6,"losses":14,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":5,"wins":3},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":3},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":2,"wins":1},"o3":{"draws":4,"losses":19,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":1},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":18,"losses":54,"wins":16},"stealth/space-bunny-alpha":{"draws":7,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":15,"wins":2},"thinkingmachines/inkling":{"draws":14,"losses":14,"wins":4},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":5},"unbiased/pareto-26.10":{"draws":1,"losses":3,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":15,"losses":14,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":20,"losses":22,"wins":6},"z-ai/glm-5.3":{"draws":8,"losses":13,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":2}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":8,"losses":38,"wins":2},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":31,"wins":2},"claude-opus-4-5":{"draws":31,"losses":40,"wins":7},"claude-opus-4-8":{"draws":12,"losses":30,"wins":2},"claude-opus-5":{"draws":12,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":18,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":23,"losses":24,"wins":25},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":24,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":26,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":26,"wins":3},"elorian/glimpse":{"draws":4,"losses":8,"wins":4},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"gemini-4-argon":{"draws":1,"losses":11,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":16,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":28,"losses":26,"wins":30},"google/gemini-3.6-flash":{"draws":33,"losses":53,"wins":6},"google/gemini-3.8-flash":{"draws":10,"losses":37,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":26,"wins":9},"gpt-5.4":{"draws":10,"losses":27,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":18,"wins":17},"gpt-5.5":{"draws":18,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":22,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":25,"wins":10},"gpt-6-astra":{"draws":6,"losses":42,"wins":0},"gpt-6-luna":{"draws":14,"losses":25,"wins":9},"gpt-6-sol":{"draws":2,"losses":41,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":6,"wins":12},"inception/mercury-3":{"draws":4,"losses":13,"wins":3},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":15,"wins":17},"meta/muse-glimmer-30b":{"draws":21,"losses":12,"wins":9},"meta/muse-spark-1.2":{"draws":12,"losses":27,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":32,"wins":6},"meta/muse-spark-open":{"draws":5,"losses":14,"wins":3},"meta/muse-wonder":{"draws":11,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":4},"minimax/minimax-m3.1-flash":{"draws":6,"losses":6,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":18,"wins":1},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":11,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":1},"o3":{"draws":15,"losses":35,"wins":16},"openai/gpt-oss-120b":{"draws":12,"losses":17,"wins":13},"poolside/laguna-s-2.1":{"draws":20,"losses":17,"wins":9},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":11,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":28,"wins":4},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-max-0902":{"draws":16,"losses":24,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":15,"wins":5},"stealth/ox-alpha":{"draws":45,"losses":87,"wins":26},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":30,"wins":5},"thinkingmachines/inkling":{"draws":23,"losses":18,"wins":23},"thinkingmachines/inkling-small":{"draws":21,"losses":12,"wins":15},"unbiased/pareto-26.10":{"draws":2,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":27,"wins":10},"x-ai/grok-4.6":{"draws":17,"losses":28,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":37,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":30,"losses":27,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":37,"losses":43,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":28,"wins":6},"z-ai/glm-5.3-flashx":{"draws":19,"losses":26,"wins":3}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":11,"losses":22,"wins":15},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":26,"losses":31,"wins":21},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":19,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":32,"losses":11,"wins":29},"deepseek/deepseek-v4-pro":{"draws":13,"losses":12,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":21,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":17,"wins":9},"elorian/glimpse":{"draws":2,"losses":3,"wins":7},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":15,"losses":16,"wins":17},"gemini-4-argon":{"draws":2,"losses":12,"wins":2},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":24,"losses":16,"wins":20},"google/gemini-3.5-flash-lite":{"draws":32,"losses":21,"wins":31},"google/gemini-3.6-flash":{"draws":24,"losses":36,"wins":32},"google/gemini-3.8-flash":{"draws":10,"losses":20,"wins":18},"google/gemma-4-31b-it":{"draws":14,"losses":4,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":15,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":15,"losses":17,"wins":12},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":31,"wins":9},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":13,"losses":19,"wins":16},"gpt-6-sol":{"draws":5,"losses":29,"wins":14},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":5,"wins":14},"inception/mercury-3":{"draws":5,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":24,"losses":8,"wins":20},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":12,"losses":18,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":20,"wins":16},"meta/muse-spark-open":{"draws":8,"losses":13,"wins":9},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"minimax/minimax-m3.1-flash":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":2,"wins":6},"o3":{"draws":16,"losses":20,"wins":30},"openai/gpt-oss-120b":{"draws":17,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":17,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":2,"wins":8},"stealth/ox-alpha":{"draws":49,"losses":67,"wins":42},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":14,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":16},"x-ai/grok-4.6":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":25,"losses":18,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":35,"losses":24,"wins":37},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":9,"losses":23,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":5,"wins":19},"claude-fable-5":{"draws":12,"losses":29,"wins":7},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":29,"losses":26,"wins":23},"claude-opus-4-8":{"draws":16,"losses":13,"wins":15},"claude-opus-5":{"draws":11,"losses":68,"wins":3},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":17,"losses":14,"wins":17},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":26,"losses":10,"wins":36},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":19,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":11,"wins":8},"elorian/glimpse":{"draws":8,"losses":4,"wins":2},"fireworks/ember-1":{"draws":18,"losses":12,"wins":18},"gemini-3.1-pro-preview":{"draws":15,"losses":15,"wins":18},"gemini-4-argon":{"draws":0,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":21,"losses":15,"wins":24},"google/gemini-3.5-flash-lite":{"draws":32,"losses":10,"wins":42},"google/gemini-3.6-flash":{"draws":37,"losses":30,"wins":25},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":11},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":8,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":11,"wins":16},"gpt-5.4":{"draws":12,"losses":21,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":23},"gpt-5.5":{"draws":22,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":22,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":12},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":19,"losses":15,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":6,"wins":11},"inception/mercury-3":{"draws":11,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":30},"meta/muse-glimmer-30b":{"draws":18,"losses":3,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":6,"losses":9,"wins":11},"meta/muse-wonder":{"draws":13,"losses":29,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":15},"minimax/minimax-m3.1-flash":{"draws":4,"losses":4,"wins":14},"mistralai/mistral-large-4-0":{"draws":13,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":9,"wins":21},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":2,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":5},"o3":{"draws":16,"losses":21,"wins":29},"openai/gpt-oss-120b":{"draws":16,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":9,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":7,"losses":15,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":6,"wins":9},"stealth/ox-alpha":{"draws":44,"losses":61,"wins":53},"stealth/space-bunny-alpha":{"draws":13,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":21,"losses":2,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":33,"losses":9,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":16,"wins":36},"z-ai/glm-5.3":{"draws":15,"losses":25,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":17},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":5},"claude-fable-5":{"draws":5,"losses":9,"wins":8},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":9,"wins":2},"claude-opus-4-5":{"draws":10,"losses":5,"wins":13},"claude-opus-4-8":{"draws":3,"losses":5,"wins":6},"claude-opus-5":{"draws":7,"losses":27,"wins":6},"claude-opus-5-5":{"draws":4,"losses":16,"wins":2},"claude-sonnet-5":{"draws":9,"losses":6,"wins":5},"claude-sonnet-5-5":{"draws":3,"losses":8,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":19},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":4,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":8,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":6},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":9,"losses":7,"wins":8},"gemini-3.1-pro-preview":{"draws":2,"losses":3,"wins":3},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":8},"google/gemini-3.5-flash":{"draws":10,"losses":13,"wins":7},"google/gemini-3.5-flash-lite":{"draws":18,"losses":10,"wins":14},"google/gemini-3.6-flash":{"draws":8,"losses":17,"wins":13},"google/gemini-3.8-flash":{"draws":6,"losses":8,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":5},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":7,"wins":4},"gpt-5.4":{"draws":5,"losses":4,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":9},"gpt-5.5":{"draws":4,"losses":12,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":4,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":3},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":4,"losses":5,"wins":7},"gpt-6-sol":{"draws":3,"losses":13,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":21,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":7},"inception/mercury-3":{"draws":10,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":6},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":6},"meta/muse-spark-1.2":{"draws":8,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":15,"wins":7},"meta/muse-spark-open":{"draws":9,"losses":14,"wins":15},"meta/muse-wonder":{"draws":5,"losses":10,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":7},"minimax/minimax-m3.1-flash":{"draws":12,"losses":10,"wins":14},"mistralai/mistral-large-4-0":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":5},"o3":{"draws":6,"losses":15,"wins":11},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":10},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":16,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":6,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-max-0902":{"draws":8,"losses":6,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":8,"wins":10},"stealth/ox-alpha":{"draws":26,"losses":29,"wins":23},"stealth/space-bunny-alpha":{"draws":6,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":12},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":6},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":7,"wins":11},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":8},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":2},"x-ai/grok-4.6":{"draws":6,"losses":11,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":17,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":17,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":6},"z-ai/glm-5.2":{"draws":20,"losses":15,"wins":15},"z-ai/glm-5.3":{"draws":2,"losses":12,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":5},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":7}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":35,"wins":67},"claude-fable-5":{"draws":34,"losses":109,"wins":25},"claude-fable-5-1":{"draws":5,"losses":189,"wins":2},"claude-haiku-5-5":{"draws":48,"losses":71,"wins":33},"claude-opus-4-5":{"draws":101,"losses":88,"wins":75},"claude-opus-4-8":{"draws":34,"losses":70,"wins":32},"claude-opus-5":{"draws":45,"losses":225,"wins":24},"claude-opus-5-5":{"draws":18,"losses":157,"wins":1},"claude-sonnet-5":{"draws":54,"losses":59,"wins":55},"claude-sonnet-5-5":{"draws":37,"losses":90,"wins":41},"cohere/north-mini-code":{"draws":14,"losses":12,"wins":34},"deepseek/deepseek-v4-flash":{"draws":98,"losses":58,"wins":90},"deepseek/deepseek-v4-pro":{"draws":60,"losses":53,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":54,"losses":66,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":77,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":67,"wins":27},"elorian/glimpse":{"draws":18,"losses":15,"wins":13},"fireworks/ember-1":{"draws":62,"losses":75,"wins":31},"gemini-3.1-pro-preview":{"draws":53,"losses":61,"wins":54},"gemini-4-argon":{"draws":8,"losses":65,"wins":5},"google/gemini-3.1-flash-lite":{"draws":26,"losses":8,"wins":58},"google/gemini-3.5-flash":{"draws":51,"losses":99,"wins":52},"google/gemini-3.5-flash-lite":{"draws":95,"losses":77,"wins":120},"google/gemini-3.6-flash":{"draws":88,"losses":160,"wins":78},"google/gemini-3.8-flash":{"draws":47,"losses":93,"wins":28},"google/gemma-4-31b-it":{"draws":35,"losses":15,"wins":40},"gpt-4.1":{"draws":23,"losses":18,"wins":15},"gpt-4.1-nano":{"draws":16,"losses":2,"wins":10},"gpt-5":{"draws":57,"losses":52,"wins":41},"gpt-5.4":{"draws":62,"losses":73,"wins":27},"gpt-5.4-mini":{"draws":50,"losses":31,"wins":31},"gpt-5.4-nano":{"draws":46,"losses":47,"wins":53},"gpt-5.5":{"draws":63,"losses":59,"wins":34},"gpt-5.6-luna":{"draws":72,"losses":47,"wins":49},"gpt-5.6-sol":{"draws":32,"losses":113,"wins":23},"gpt-5.6-terra":{"draws":72,"losses":49,"wins":41},"gpt-6-astra":{"draws":11,"losses":156,"wins":1},"gpt-6-luna":{"draws":54,"losses":69,"wins":45},"gpt-6-sol":{"draws":20,"losses":134,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":152,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":50,"losses":11,"wins":47},"inception/mercury-3":{"draws":17,"losses":19,"wins":10},"inclusionai/ling-3.0-flash":{"draws":59,"losses":13,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":67,"losses":34,"wins":77},"meta/muse-glimmer-30b":{"draws":62,"losses":26,"wins":62},"meta/muse-spark-1.2":{"draws":52,"losses":64,"wins":46},"meta/muse-spark-1.3":{"draws":36,"losses":102,"wins":30},"meta/muse-spark-open":{"draws":14,"losses":36,"wins":14},"meta/muse-wonder":{"draws":44,"losses":101,"wins":23},"minimax/minimax-m3":{"draws":26,"losses":18,"wins":40},"minimax/minimax-m3.1-flash":{"draws":34,"losses":25,"wins":39},"mistralai/mistral-large-4-0":{"draws":50,"losses":34,"wins":22},"mistralai/mistral-medium-3-5":{"draws":41,"losses":14,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":12,"wins":11},"moonshotai/kimi-k3":{"draws":53,"losses":63,"wins":46},"nex-agi/nex-n2-pro":{"draws":35,"losses":10,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":22,"wins":53},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":9,"wins":14},"o3":{"draws":50,"losses":90,"wins":68},"openai/gpt-oss-120b":{"draws":66,"losses":27,"wins":57},"poolside/laguna-s-2.1":{"draws":76,"losses":37,"wins":57},"qwen/qwen3.7-max":{"draws":35,"losses":25,"wins":30},"qwen/qwen3.7-plus":{"draws":24,"losses":13,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":59,"losses":70,"wins":39},"qwen/qwen3.8-27b":{"draws":43,"losses":44,"wins":33},"qwen/qwen3.8-flash":{"draws":52,"losses":40,"wins":20},"qwen/qwen3.8-max":{"draws":55,"losses":75,"wins":38},"qwen/qwen3.8-max-0902":{"draws":57,"losses":71,"wins":40},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":32,"wins":19},"stealth/ox-alpha":{"draws":142,"losses":297,"wins":163},"stealth/space-bunny-alpha":{"draws":55,"losses":37,"wins":38},"stepfun/step-3.7-flash":{"draws":36,"losses":22,"wins":60},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":34,"losses":22,"wins":28},"tencent/hy4-preview":{"draws":51,"losses":80,"wins":31},"thinkingmachines/inkling":{"draws":88,"losses":52,"wins":96},"thinkingmachines/inkling-small":{"draws":76,"losses":26,"wins":66},"unbiased/pareto-26.10":{"draws":2,"losses":31,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":56,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":6,"wins":23},"x-ai/grok-4.5":{"draws":48,"losses":74,"wins":46},"x-ai/grok-4.6":{"draws":65,"losses":73,"wins":30},"x-ai/grok-4.7":{"draws":19,"losses":106,"wins":15},"x-ai/grok-build-0.1":{"draws":22,"losses":11,"wins":23},"xiaomi/mimo-v2.5":{"draws":89,"losses":46,"wins":87},"xiaomi/mimo-v2.5-pro":{"draws":34,"losses":27,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":53,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":64,"wins":22},"z-ai/glm-5.2":{"draws":140,"losses":93,"wins":103},"z-ai/glm-5.3":{"draws":34,"losses":107,"wins":21},"z-ai/glm-5.3-flash":{"draws":34,"losses":93,"wins":41},"z-ai/glm-5.3-flashx":{"draws":43,"losses":94,"wins":31}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":13,"losses":19,"wins":4},"claude-fable-5-1":{"draws":2,"losses":39,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":4},"claude-opus-4-5":{"draws":19,"losses":29,"wins":10},"claude-opus-4-8":{"draws":11,"losses":15,"wins":6},"claude-opus-5":{"draws":11,"losses":54,"wins":3},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":24,"losses":13,"wins":15},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":16,"wins":2},"elorian/glimpse":{"draws":4,"losses":3,"wins":1},"fireworks/ember-1":{"draws":14,"losses":18,"wins":4},"gemini-3.1-pro-preview":{"draws":15,"losses":15,"wins":6},"gemini-4-argon":{"draws":1,"losses":15,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":18,"losses":18,"wins":8},"google/gemini-3.5-flash-lite":{"draws":26,"losses":16,"wins":20},"google/gemini-3.6-flash":{"draws":19,"losses":42,"wins":7},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":5},"gpt-4.1":{"draws":5,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":12,"wins":7},"gpt-5.4":{"draws":17,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":12},"gpt-5.5":{"draws":20,"losses":13,"wins":1},"gpt-5.6-luna":{"draws":19,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":9},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":6},"gpt-6-sol":{"draws":6,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":8},"inception/mercury-3":{"draws":2,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":2},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":15},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":2},"meta/muse-spark-open":{"draws":5,"losses":6,"wins":3},"meta/muse-wonder":{"draws":9,"losses":23,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"minimax/minimax-m3.1-flash":{"draws":3,"losses":3,"wins":4},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":1,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":0,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":3},"o3":{"draws":12,"losses":25,"wins":7},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":11},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":5},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":8,"wins":1},"stealth/ox-alpha":{"draws":46,"losses":67,"wins":13},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":6},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":13,"wins":15},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":8},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":19,"wins":3},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":6}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":11},"claude-fable-5":{"draws":11,"losses":24,"wins":1},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":22,"wins":4},"claude-opus-4-5":{"draws":18,"losses":25,"wins":15},"claude-opus-4-8":{"draws":11,"losses":18,"wins":3},"claude-opus-5":{"draws":11,"losses":43,"wins":4},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":14,"losses":9,"wins":13},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":17,"losses":12,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":12,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":8,"wins":4},"elorian/glimpse":{"draws":4,"losses":3,"wins":3},"fireworks/ember-1":{"draws":14,"losses":15,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":11,"wins":8},"gemini-4-argon":{"draws":0,"losses":15,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":23,"losses":37,"wins":10},"google/gemini-3.8-flash":{"draws":12,"losses":19,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":8},"gpt-4.1":{"draws":6,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":11,"wins":9},"gpt-5.4":{"draws":12,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":9},"gpt-5.5":{"draws":14,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":9},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":8},"gpt-6-astra":{"draws":6,"losses":30,"wins":0},"gpt-6-luna":{"draws":13,"losses":16,"wins":7},"gpt-6-sol":{"draws":9,"losses":24,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":33,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":14},"inception/mercury-3":{"draws":7,"losses":5,"wins":0},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":18},"meta/muse-glimmer-30b":{"draws":13,"losses":11,"wins":6},"meta/muse-spark-1.2":{"draws":14,"losses":10,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":4},"meta/muse-spark-open":{"draws":8,"losses":13,"wins":1},"meta/muse-wonder":{"draws":10,"losses":20,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":6},"minimax/minimax-m3.1-flash":{"draws":3,"losses":7,"wins":6},"mistralai/mistral-large-4-0":{"draws":10,"losses":8,"wins":4},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":5,"wins":1},"o3":{"draws":11,"losses":20,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":23,"wins":2},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":6,"wins":5},"stealth/ox-alpha":{"draws":32,"losses":68,"wins":24},"stealth/space-bunny-alpha":{"draws":13,"losses":9,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":8},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":21},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":12},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":19,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":21,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":24,"losses":12,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":19},"z-ai/glm-5.3":{"draws":10,"losses":23,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":18,"wins":10},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":3}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":4,"wins":0},"elorian/glimpse":{"draws":0,"losses":2,"wins":0},"fireworks/ember-1":{"draws":3,"losses":3,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inception/mercury-3":{"draws":0,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":0},"meta/muse-wonder":{"draws":2,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":1},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":8,"losses":8,"wins":0},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":2,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":2,"wins":2},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":5,"losses":0,"wins":1},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":14,"wins":9},"claude-fable-5":{"draws":9,"losses":21,"wins":6},"claude-fable-5-1":{"draws":5,"losses":32,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":13,"wins":7},"claude-opus-4-5":{"draws":23,"losses":23,"wins":12},"claude-opus-4-8":{"draws":10,"losses":16,"wins":6},"claude-opus-5":{"draws":13,"losses":50,"wins":9},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":19,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":17},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":10,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":13,"wins":4},"elorian/glimpse":{"draws":5,"losses":5,"wins":0},"fireworks/ember-1":{"draws":15,"losses":15,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":8},"gemini-4-argon":{"draws":0,"losses":22,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":10,"wins":24},"google/gemini-3.6-flash":{"draws":25,"losses":28,"wins":15},"google/gemini-3.8-flash":{"draws":17,"losses":16,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":11,"losses":10,"wins":11},"gpt-5.4":{"draws":17,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":7,"wins":16},"gpt-5.5":{"draws":16,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":6},"gpt-6-astra":{"draws":7,"losses":29,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"wins":8},"gpt-6-sol":{"draws":10,"losses":24,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":5},"inception/mercury-3":{"draws":8,"losses":5,"wins":1},"inclusionai/ling-3.0-flash":{"draws":14,"losses":1,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":6},"meta/muse-spark-open":{"draws":7,"losses":4,"wins":5},"meta/muse-wonder":{"draws":9,"losses":21,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":8},"minimax/minimax-m3.1-flash":{"draws":7,"losses":5,"wins":8},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":6,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":3,"wins":3},"o3":{"draws":12,"losses":18,"wins":12},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":17,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":18,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":8,"wins":1},"stealth/ox-alpha":{"draws":36,"losses":67,"wins":21},"stealth/space-bunny-alpha":{"draws":14,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":17,"wins":17},"thinkingmachines/inkling-small":{"draws":19,"losses":5,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":14,"losses":18,"wins":4},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":2},"x-ai/grok-4.7":{"draws":9,"losses":23,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":12,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":31,"losses":23,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":23,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":7,"wins":21},"claude-fable-5":{"draws":11,"losses":34,"wins":3},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":21,"wins":15},"claude-opus-4-5":{"draws":28,"losses":32,"wins":18},"claude-opus-4-8":{"draws":12,"losses":22,"wins":10},"claude-opus-5":{"draws":11,"losses":62,"wins":9},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":22,"losses":18,"wins":32},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":17,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":25,"wins":3},"elorian/glimpse":{"draws":4,"losses":6,"wins":4},"fireworks/ember-1":{"draws":20,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"gemini-4-argon":{"draws":0,"losses":22,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":15,"losses":26,"wins":19},"google/gemini-3.5-flash-lite":{"draws":24,"losses":26,"wins":34},"google/gemini-3.6-flash":{"draws":26,"losses":42,"wins":24},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":10},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":10},"gpt-4.1":{"draws":7,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":17,"wins":13},"gpt-5.4":{"draws":14,"losses":24,"wins":8},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":21},"gpt-5.5":{"draws":20,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":18,"losses":17,"wins":13},"gpt-6-sol":{"draws":9,"losses":36,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inception/mercury-3":{"draws":8,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":26},"meta/muse-glimmer-30b":{"draws":20,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":25,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":26,"wins":11},"meta/muse-spark-open":{"draws":4,"losses":13,"wins":1},"meta/muse-wonder":{"draws":12,"losses":31,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":16,"losses":17,"wins":13},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":7,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":3,"wins":1},"o3":{"draws":11,"losses":33,"wins":22},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":16,"losses":11,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":20,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":13,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":18,"losses":15,"wins":15},"qwen/qwen3.8-max-0902":{"draws":16,"losses":22,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":5,"wins":6},"stealth/ox-alpha":{"draws":35,"losses":76,"wins":47},"stealth/space-bunny-alpha":{"draws":14,"losses":14,"wins":10},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":15,"wins":31},"thinkingmachines/inkling-small":{"draws":20,"losses":8,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":17,"losses":24,"wins":7},"x-ai/grok-4.6":{"draws":17,"losses":25,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":12,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":33,"losses":28,"wins":35},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":13},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":22,"wins":19},"claude-fable-5":{"draws":17,"losses":48,"wins":7},"claude-fable-5-1":{"draws":5,"losses":77,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":43,"wins":12},"claude-opus-4-5":{"draws":40,"losses":52,"wins":24},"claude-opus-4-8":{"draws":18,"losses":37,"wins":9},"claude-opus-5":{"draws":17,"losses":99,"wins":14},"claude-opus-5-5":{"draws":6,"losses":70,"wins":0},"claude-sonnet-5":{"draws":24,"losses":34,"wins":14},"claude-sonnet-5-5":{"draws":15,"losses":42,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":10},"deepseek/deepseek-v4-flash":{"draws":37,"losses":37,"wins":30},"deepseek/deepseek-v4-pro":{"draws":19,"losses":33,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":23,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":31,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":35,"wins":2},"elorian/glimpse":{"draws":11,"losses":11,"wins":4},"fireworks/ember-1":{"draws":24,"losses":35,"wins":13},"gemini-3.1-pro-preview":{"draws":20,"losses":31,"wins":21},"gemini-4-argon":{"draws":0,"losses":25,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":17,"wins":19},"google/gemini-3.5-flash":{"draws":22,"losses":50,"wins":18},"google/gemini-3.5-flash-lite":{"draws":31,"losses":52,"wins":45},"google/gemini-3.6-flash":{"draws":45,"losses":75,"wins":20},"google/gemini-3.8-flash":{"draws":13,"losses":49,"wins":10},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":10},"gpt-4.1":{"draws":5,"losses":10,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":34,"wins":16},"gpt-5.4":{"draws":19,"losses":40,"wins":11},"gpt-5.4-mini":{"draws":17,"losses":16,"wins":15},"gpt-5.4-nano":{"draws":12,"losses":31,"wins":25},"gpt-5.5":{"draws":18,"losses":38,"wins":12},"gpt-5.6-luna":{"draws":24,"losses":30,"wins":18},"gpt-5.6-sol":{"draws":12,"losses":53,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":30,"wins":16},"gpt-6-astra":{"draws":3,"losses":68,"wins":1},"gpt-6-luna":{"draws":23,"losses":31,"wins":18},"gpt-6-sol":{"draws":13,"losses":56,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":65,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":14,"wins":15},"inception/mercury-3":{"draws":6,"losses":5,"wins":1},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":21,"losses":24,"wins":31},"meta/muse-glimmer-30b":{"draws":25,"losses":18,"wins":23},"meta/muse-spark-1.2":{"draws":19,"losses":31,"wins":20},"meta/muse-spark-1.3":{"draws":15,"losses":49,"wins":8},"meta/muse-spark-open":{"draws":10,"losses":23,"wins":7},"meta/muse-wonder":{"draws":12,"losses":47,"wins":13},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":15},"minimax/minimax-m3.1-flash":{"draws":12,"losses":15,"wins":16},"mistralai/mistral-large-4-0":{"draws":16,"losses":20,"wins":10},"mistralai/mistral-medium-3-5":{"draws":14,"losses":11,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":10,"wins":5},"moonshotai/kimi-k3":{"draws":22,"losses":31,"wins":17},"nex-agi/nex-n2-pro":{"draws":10,"losses":7,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":22,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":8},"o3":{"draws":12,"losses":62,"wins":22},"openai/gpt-oss-120b":{"draws":16,"losses":23,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":28,"wins":23},"qwen/qwen3.7-max":{"draws":15,"losses":19,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":33,"wins":16},"qwen/qwen3.8-27b":{"draws":12,"losses":26,"wins":14},"qwen/qwen3.8-flash":{"draws":14,"losses":24,"wins":10},"qwen/qwen3.8-max":{"draws":26,"losses":31,"wins":15},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":17,"wins":7},"stealth/ox-alpha":{"draws":58,"losses":142,"wins":50},"stealth/space-bunny-alpha":{"draws":19,"losses":22,"wins":17},"stepfun/step-3.7-flash":{"draws":12,"losses":28,"wins":10},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":17,"wins":11},"tencent/hy4-preview":{"draws":24,"losses":37,"wins":9},"thinkingmachines/inkling":{"draws":30,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":26,"losses":21,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":5},"x-ai/grok-4.5":{"draws":18,"losses":41,"wins":13},"x-ai/grok-4.6":{"draws":27,"losses":34,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":50,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":6},"xiaomi/mimo-v2.5":{"draws":35,"losses":44,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":23,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":26,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":29,"wins":5},"z-ai/glm-5.2":{"draws":52,"losses":55,"wins":37},"z-ai/glm-5.3":{"draws":15,"losses":44,"wins":9},"z-ai/glm-5.3-flash":{"draws":19,"losses":40,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":44,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":19,"wins":7},"claude-fable-5":{"draws":9,"losses":34,"wins":5},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":29,"wins":5},"claude-opus-4-5":{"draws":26,"losses":45,"wins":7},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":12,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":9,"wins":4},"deepseek/deepseek-v4-flash":{"draws":33,"losses":27,"wins":12},"deepseek/deepseek-v4-pro":{"draws":19,"losses":22,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":26,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":22,"wins":2},"elorian/glimpse":{"draws":3,"losses":6,"wins":1},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":26,"wins":6},"gemini-4-argon":{"draws":4,"losses":21,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":14,"wins":6},"google/gemini-3.5-flash":{"draws":18,"losses":35,"wins":7},"google/gemini-3.5-flash-lite":{"draws":26,"losses":35,"wins":23},"google/gemini-3.6-flash":{"draws":27,"losses":49,"wins":16},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":18,"wins":5},"gpt-5.4":{"draws":16,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":18,"losses":18,"wins":12},"gpt-5.5":{"draws":16,"losses":25,"wins":3},"gpt-5.6-luna":{"draws":22,"losses":19,"wins":7},"gpt-5.6-sol":{"draws":10,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":17,"losses":27,"wins":2},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":10},"gpt-6-sol":{"draws":4,"losses":44,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":8,"wins":9},"inception/mercury-3":{"draws":3,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":23,"wins":11},"meta/muse-glimmer-30b":{"draws":22,"losses":14,"wins":6},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":7},"meta/muse-spark-1.3":{"draws":14,"losses":31,"wins":3},"meta/muse-spark-open":{"draws":6,"losses":13,"wins":1},"meta/muse-wonder":{"draws":12,"losses":34,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"minimax/minimax-m3.1-flash":{"draws":13,"losses":11,"wins":0},"mistralai/mistral-large-4-0":{"draws":12,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":23,"wins":6},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":8,"wins":1},"o3":{"draws":13,"losses":40,"wins":13},"openai/gpt-oss-120b":{"draws":16,"losses":18,"wins":8},"poolside/laguna-s-2.1":{"draws":23,"losses":19,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":14,"wins":4},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":31,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":10,"wins":4},"stealth/ox-alpha":{"draws":45,"losses":90,"wins":23},"stealth/space-bunny-alpha":{"draws":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":14,"losses":27,"wins":5},"thinkingmachines/inkling":{"draws":28,"losses":27,"wins":9},"thinkingmachines/inkling-small":{"draws":14,"losses":12,"wins":6},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":3},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":28,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":19,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":38,"losses":44,"wins":14},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":31,"wins":7},"z-ai/glm-5.3-flashx":{"draws":13,"losses":29,"wins":6}},"unbiased/pareto-26.10":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":30},"claude-fable-5":{"draws":1,"losses":3,"wins":26},"claude-fable-5-1":{"draws":6,"losses":11,"wins":11},"claude-haiku-5-5":{"draws":2,"losses":4,"wins":26},"claude-opus-4-5":{"draws":6,"losses":0,"wins":50},"claude-opus-4-8":{"draws":3,"losses":3,"wins":24},"claude-opus-5":{"draws":7,"losses":16,"wins":31},"claude-opus-5-5":{"draws":2,"losses":17,"wins":11},"claude-sonnet-5":{"draws":3,"losses":0,"wins":27},"claude-sonnet-5-5":{"draws":3,"losses":5,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":50},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":1,"wins":39},"elorian/glimpse":{"draws":1,"losses":0,"wins":25},"fireworks/ember-1":{"draws":2,"losses":0,"wins":28},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":20},"gemini-4-argon":{"draws":4,"losses":13,"wins":31},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":0,"wins":25},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":46},"google/gemini-3.6-flash":{"draws":7,"losses":3,"wins":44},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":26},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":15},"gpt-4.1":{"draws":1,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":25},"gpt-5.4":{"draws":4,"losses":2,"wins":28},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":12},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":22},"gpt-5.5":{"draws":2,"losses":2,"wins":20},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":24},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":31},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":26},"gpt-6-astra":{"draws":5,"losses":11,"wins":8},"gpt-6-luna":{"draws":2,"losses":0,"wins":22},"gpt-6-sol":{"draws":3,"losses":3,"wins":34},"gpt-6.1-sol":{"draws":6,"losses":10,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":19},"inception/mercury-3":{"draws":2,"losses":1,"wins":27},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":39},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":24},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":30},"meta/muse-spark-1.3":{"draws":3,"losses":0,"wins":21},"meta/muse-spark-open":{"draws":2,"losses":2,"wins":40},"meta/muse-wonder":{"draws":6,"losses":6,"wins":28},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":14},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":38},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":18},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":1,"losses":0,"wins":31},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":13},"o3":{"draws":0,"losses":0,"wins":36},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":22},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":37},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":19},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":24},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":14},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":13},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":35},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":42},"stealth/ox-alpha":{"draws":7,"losses":3,"wins":84},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":27},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":17},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":28},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":41},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":31},"unbiased/pareto-26.10-preview":{"draws":0,"losses":7,"wins":7},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":3,"losses":0,"wins":27},"x-ai/grok-4.6":{"draws":6,"losses":1,"wins":25},"x-ai/grok-4.7":{"draws":4,"losses":6,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":0,"wins":15},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":56},"z-ai/glm-5.3":{"draws":4,"losses":2,"wins":18},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":21},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":22}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":22,"wins":29},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":76},"claude-opus-4-8":{"draws":2,"losses":1,"wins":41},"claude-opus-5":{"draws":3,"losses":29,"wins":50},"claude-opus-5-5":{"draws":1,"losses":26,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":6,"wins":24},"elorian/glimpse":{"draws":0,"losses":1,"wins":17},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"gemini-4-argon":{"draws":0,"losses":5,"wins":15},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":0,"losses":5,"wins":55},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":78},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":42},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":4,"wins":39},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":43},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":6,"losses":22,"wins":20},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":9,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":0,"losses":1,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":42},"meta/muse-spark-open":{"draws":0,"losses":2,"wins":20},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":30},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":11},"o3":{"draws":0,"losses":3,"wins":63},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":45},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":34},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":26},"stealth/ox-alpha":{"draws":10,"losses":7,"wins":141},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":24},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10":{"draws":0,"losses":7,"wins":7},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":41},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":88},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":5,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":8,"losses":1,"wins":1},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":7,"losses":5,"wins":0},"claude-opus-5-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":5,"losses":1,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":2,"wins":0},"elorian/glimpse":{"draws":4,"losses":0,"wins":0},"fireworks/ember-1":{"draws":5,"losses":1,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":0},"gemini-4-argon":{"draws":3,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.5":{"draws":5,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":0},"gpt-6-astra":{"draws":2,"losses":4,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-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":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":3},"meta/muse-spark-open":{"draws":2,"losses":2,"wins":2},"meta/muse-wonder":{"draws":3,"losses":3,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":0},"o3":{"draws":3,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":10,"losses":8,"wins":0},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":0,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":1,"wins":0},"z-ai/glm-5.3-flashx":{"draws":5,"losses":1,"wins":0}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":20},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":27,"losses":25,"wins":26},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":18,"losses":12,"wins":18},"claude-sonnet-5-5":{"draws":15,"losses":20,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":18,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":15,"wins":6},"elorian/glimpse":{"draws":2,"losses":7,"wins":5},"fireworks/ember-1":{"draws":16,"losses":13,"wins":19},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":5,"losses":15,"wins":6},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":21},"google/gemini-3.5-flash-lite":{"draws":30,"losses":15,"wins":39},"google/gemini-3.6-flash":{"draws":22,"losses":44,"wins":26},"google/gemini-3.8-flash":{"draws":12,"losses":20,"wins":16},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":16},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":18,"wins":16},"gpt-5.4":{"draws":9,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":27},"gpt-5.5":{"draws":11,"losses":22,"wins":11},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":19},"gpt-5.6-sol":{"draws":5,"losses":32,"wins":11},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":14},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":2,"wins":18},"inception/mercury-3":{"draws":12,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":13,"wins":25},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":17},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":16},"meta/muse-spark-open":{"draws":4,"losses":12,"wins":8},"meta/muse-wonder":{"draws":9,"losses":28,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"minimax/minimax-m3.1-flash":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":20,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":1,"wins":4},"o3":{"draws":7,"losses":28,"wins":31},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":15},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":7,"wins":1},"stealth/ox-alpha":{"draws":39,"losses":71,"wins":48},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":15,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":22,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":7,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":29,"wins":7},"z-ai/glm-5.3-flash":{"draws":6,"losses":29,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":7,"wins":17},"claude-fable-5":{"draws":15,"losses":28,"wins":5},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":13},"claude-opus-4-5":{"draws":27,"losses":23,"wins":28},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":16,"losses":61,"wins":5},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":20,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":13,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":26,"losses":14,"wins":32},"deepseek/deepseek-v4-pro":{"draws":15,"losses":12,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":1},"elorian/glimpse":{"draws":3,"losses":6,"wins":5},"fireworks/ember-1":{"draws":20,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":20,"losses":14,"wins":14},"gemini-4-argon":{"draws":2,"losses":25,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":18},"google/gemini-3.5-flash":{"draws":22,"losses":19,"wins":19},"google/gemini-3.5-flash-lite":{"draws":31,"losses":15,"wins":38},"google/gemini-3.6-flash":{"draws":34,"losses":36,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":24,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":15,"losses":13,"wins":14},"gpt-5.4":{"draws":15,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":11},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":21,"losses":11,"wins":16},"gpt-6-sol":{"draws":10,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":7,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":5,"wins":13},"inception/mercury-3":{"draws":6,"losses":5,"wins":5},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":14,"wins":16},"meta/muse-glimmer-30b":{"draws":22,"losses":3,"wins":17},"meta/muse-spark-1.2":{"draws":15,"losses":14,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":6,"losses":16,"wins":2},"meta/muse-wonder":{"draws":20,"losses":26,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":3,"wins":13},"minimax/minimax-m3.1-flash":{"draws":9,"losses":10,"wins":9},"mistralai/mistral-large-4-0":{"draws":13,"losses":7,"wins":10},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":10,"wins":18},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":4},"o3":{"draws":12,"losses":25,"wins":29},"openai/gpt-oss-120b":{"draws":20,"losses":6,"wins":16},"poolside/laguna-s-2.1":{"draws":23,"losses":10,"wins":13},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":20,"wins":10},"qwen/qwen3.8-27b":{"draws":13,"losses":13,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":21,"losses":18,"wins":9},"qwen/qwen3.8-max-0902":{"draws":21,"losses":13,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":6,"wins":6},"stealth/ox-alpha":{"draws":61,"losses":72,"wins":25},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":12,"wins":27},"thinkingmachines/inkling-small":{"draws":20,"losses":10,"wins":18},"unbiased/pareto-26.10":{"draws":4,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":15,"losses":25,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":1},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":31,"losses":14,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":36,"losses":26,"wins":34},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":14,"losses":29,"wins":5}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":15,"wins":18},"claude-fable-5":{"draws":5,"losses":27,"wins":10},"claude-fable-5-1":{"draws":3,"losses":37,"wins":6},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":18},"claude-opus-4-5":{"draws":13,"losses":26,"wins":31},"claude-opus-4-8":{"draws":11,"losses":18,"wins":13},"claude-opus-5":{"draws":9,"losses":44,"wins":17},"claude-opus-5-5":{"draws":5,"losses":36,"wins":5},"claude-sonnet-5":{"draws":9,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":12,"losses":18,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":38},"deepseek/deepseek-v4-pro":{"draws":5,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":15,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":19,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":12,"wins":5},"elorian/glimpse":{"draws":4,"losses":4,"wins":4},"fireworks/ember-1":{"draws":6,"losses":14,"wins":22},"gemini-3.1-pro-preview":{"draws":6,"losses":15,"wins":21},"gemini-4-argon":{"draws":5,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":27},"google/gemini-3.5-flash-lite":{"draws":14,"losses":20,"wins":40},"google/gemini-3.6-flash":{"draws":9,"losses":37,"wins":34},"google/gemini-3.8-flash":{"draws":9,"losses":16,"wins":17},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":16},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":15,"wins":15},"gpt-5.4":{"draws":9,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":17},"gpt-5.4-nano":{"draws":10,"losses":8,"wins":28},"gpt-5.5":{"draws":8,"losses":19,"wins":11},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":23},"gpt-5.6-sol":{"draws":5,"losses":26,"wins":11},"gpt-5.6-terra":{"draws":8,"losses":15,"wins":17},"gpt-6-astra":{"draws":3,"losses":34,"wins":5},"gpt-6-luna":{"draws":7,"losses":13,"wins":22},"gpt-6-sol":{"draws":9,"losses":25,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inception/mercury-3":{"draws":4,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":35},"meta/muse-glimmer-30b":{"draws":4,"losses":13,"wins":19},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":14},"meta/muse-spark-1.3":{"draws":6,"losses":19,"wins":17},"meta/muse-spark-open":{"draws":3,"losses":4,"wins":7},"meta/muse-wonder":{"draws":10,"losses":18,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":15},"minimax/minimax-m3.1-flash":{"draws":3,"losses":12,"wins":11},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":2},"o3":{"draws":8,"losses":24,"wins":30},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":25},"poolside/laguna-s-2.1":{"draws":9,"losses":10,"wins":19},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":11},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":10,"losses":16,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":1,"wins":16},"stealth/ox-alpha":{"draws":26,"losses":45,"wins":47},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":11,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":10,"losses":1,"wins":31},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":20,"wins":13},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":22,"losses":22,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":18,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":14},"z-ai/glm-5.3-flashx":{"draws":7,"losses":18,"wins":17}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":38,"wins":33},"claude-fable-5":{"draws":14,"losses":86,"wins":2},"claude-fable-5-1":{"draws":5,"losses":105,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":64,"wins":20},"claude-opus-4-5":{"draws":47,"losses":91,"wins":30},"claude-opus-4-8":{"draws":19,"losses":64,"wins":15},"claude-opus-5":{"draws":24,"losses":135,"wins":7},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":29,"losses":55,"wins":18},"claude-sonnet-5-5":{"draws":15,"losses":74,"wins":13},"cohere/north-mini-code":{"draws":8,"losses":13,"wins":19},"deepseek/deepseek-v4-flash":{"draws":41,"losses":58,"wins":55},"deepseek/deepseek-v4-pro":{"draws":28,"losses":50,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":47,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":57,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":47,"wins":8},"elorian/glimpse":{"draws":8,"losses":9,"wins":3},"fireworks/ember-1":{"draws":32,"losses":54,"wins":16},"gemini-3.1-pro-preview":{"draws":23,"losses":53,"wins":26},"gemini-4-argon":{"draws":2,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":21,"losses":21,"wins":36},"google/gemini-3.5-flash":{"draws":28,"losses":77,"wins":27},"google/gemini-3.5-flash-lite":{"draws":37,"losses":79,"wins":68},"google/gemini-3.6-flash":{"draws":44,"losses":123,"wins":31},"google/gemini-3.8-flash":{"draws":24,"losses":67,"wins":11},"google/gemma-4-31b-it":{"draws":19,"losses":16,"wins":25},"gpt-4.1":{"draws":9,"losses":16,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":21,"losses":48,"wins":21},"gpt-5.4":{"draws":21,"losses":71,"wins":8},"gpt-5.4-mini":{"draws":20,"losses":24,"wins":24},"gpt-5.4-nano":{"draws":18,"losses":54,"wins":40},"gpt-5.5":{"draws":38,"losses":45,"wins":11},"gpt-5.6-luna":{"draws":34,"losses":42,"wins":26},"gpt-5.6-sol":{"draws":11,"losses":82,"wins":9},"gpt-5.6-terra":{"draws":28,"losses":61,"wins":7},"gpt-6-astra":{"draws":7,"losses":94,"wins":1},"gpt-6-luna":{"draws":25,"losses":63,"wins":14},"gpt-6-sol":{"draws":14,"losses":78,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":90,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":11,"wins":36},"inception/mercury-3":{"draws":7,"losses":18,"wins":3},"inclusionai/ling-3.0-flash":{"draws":25,"losses":18,"wins":29},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":43,"wins":41},"meta/muse-glimmer-30b":{"draws":30,"losses":32,"wins":26},"meta/muse-spark-1.2":{"draws":22,"losses":57,"wins":17},"meta/muse-spark-1.3":{"draws":18,"losses":73,"wins":11},"meta/muse-spark-open":{"draws":12,"losses":41,"wins":5},"meta/muse-wonder":{"draws":10,"losses":83,"wins":9},"minimax/minimax-m3":{"draws":13,"losses":20,"wins":23},"minimax/minimax-m3.1-flash":{"draws":8,"losses":33,"wins":23},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":12},"mistralai/mistral-medium-3-5":{"draws":18,"losses":15,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":9},"moonshotai/kimi-k3":{"draws":26,"losses":55,"wins":15},"nex-agi/nex-n2-pro":{"draws":14,"losses":12,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":28,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":12,"wins":7},"o3":{"draws":22,"losses":99,"wins":39},"openai/gpt-oss-120b":{"draws":22,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":26,"losses":42,"wins":28},"qwen/qwen3.7-max":{"draws":20,"losses":24,"wins":18},"qwen/qwen3.7-plus":{"draws":12,"losses":21,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":56,"wins":15},"qwen/qwen3.8-27b":{"draws":12,"losses":45,"wins":19},"qwen/qwen3.8-flash":{"draws":20,"losses":31,"wins":17},"qwen/qwen3.8-max":{"draws":24,"losses":53,"wins":25},"qwen/qwen3.8-max-0902":{"draws":34,"losses":57,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":60,"losses":200,"wins":50},"stealth/space-bunny-alpha":{"draws":26,"losses":33,"wins":23},"stepfun/step-3.7-flash":{"draws":18,"losses":28,"wins":32},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":24,"wins":17},"tencent/hy4-preview":{"draws":27,"losses":65,"wins":8},"thinkingmachines/inkling":{"draws":30,"losses":43,"wins":65},"thinkingmachines/inkling-small":{"draws":33,"losses":27,"wins":42},"unbiased/pareto-26.10":{"draws":0,"losses":26,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":17,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":72,"wins":12},"x-ai/grok-4.6":{"draws":34,"losses":59,"wins":9},"x-ai/grok-4.7":{"draws":7,"losses":74,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":15,"wins":11},"xiaomi/mimo-v2.5":{"draws":38,"losses":44,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":32,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":44,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":6},"z-ai/glm-5.2":{"draws":64,"losses":91,"wins":49},"z-ai/glm-5.3":{"draws":12,"losses":81,"wins":3},"z-ai/glm-5.3-flash":{"draws":17,"losses":63,"wins":22},"z-ai/glm-5.3-flashx":{"draws":22,"losses":70,"wins":10}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":8},"claude-fable-5":{"draws":6,"losses":34,"wins":2},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":8},"claude-opus-4-5":{"draws":17,"losses":35,"wins":16},"claude-opus-4-8":{"draws":9,"losses":23,"wins":6},"claude-opus-5":{"draws":5,"losses":64,"wins":1},"claude-opus-5-5":{"draws":1,"losses":44,"wins":1},"claude-sonnet-5":{"draws":10,"losses":26,"wins":6},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":21,"losses":27,"wins":18},"deepseek/deepseek-v4-pro":{"draws":7,"losses":21,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":21,"wins":3},"elorian/glimpse":{"draws":1,"losses":5,"wins":6},"fireworks/ember-1":{"draws":15,"losses":21,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":20,"wins":10},"gemini-4-argon":{"draws":1,"losses":17,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":19,"losses":34,"wins":19},"google/gemini-3.6-flash":{"draws":17,"losses":51,"wins":12},"google/gemini-3.8-flash":{"draws":11,"losses":26,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":15,"wins":12},"gpt-5.4":{"draws":8,"losses":27,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":18,"wins":15},"gpt-5.5":{"draws":16,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":26,"wins":4},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":12,"losses":24,"wins":6},"gpt-6-sol":{"draws":1,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":10},"inception/mercury-3":{"draws":10,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":17},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":14},"meta/muse-spark-1.2":{"draws":8,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":34,"wins":3},"meta/muse-spark-open":{"draws":1,"losses":8,"wins":1},"meta/muse-wonder":{"draws":4,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":10},"minimax/minimax-m3.1-flash":{"draws":4,"losses":14,"wins":8},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":20,"wins":9},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":6,"wins":2},"o3":{"draws":11,"losses":38,"wins":13},"openai/gpt-oss-120b":{"draws":13,"losses":15,"wins":10},"poolside/laguna-s-2.1":{"draws":16,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":9},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":14,"wins":2},"stealth/ox-alpha":{"draws":33,"losses":84,"wins":23},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":14,"losses":14,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":8,"losses":29,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":24,"losses":18,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":32,"wins":20},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":1},"z-ai/glm-5.3-flash":{"draws":9,"losses":30,"wins":3},"z-ai/glm-5.3-flashx":{"draws":12,"losses":27,"wins":3}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":17},"claude-fable-5":{"draws":12,"losses":26,"wins":4},"claude-fable-5-1":{"draws":1,"losses":42,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":10},"claude-opus-4-5":{"draws":22,"losses":27,"wins":19},"claude-opus-4-8":{"draws":10,"losses":16,"wins":12},"claude-opus-5":{"draws":8,"losses":56,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":10,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":20,"losses":13,"wins":33},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":14,"wins":2},"elorian/glimpse":{"draws":1,"losses":1,"wins":6},"fireworks/ember-1":{"draws":13,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"gemini-4-argon":{"draws":1,"losses":14,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":22,"wins":19},"google/gemini-3.5-flash-lite":{"draws":13,"losses":14,"wins":45},"google/gemini-3.6-flash":{"draws":16,"losses":41,"wins":23},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":12},"gpt-4.1":{"draws":6,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":1},"gpt-5":{"draws":11,"losses":17,"wins":10},"gpt-5.4":{"draws":16,"losses":17,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":21},"gpt-5.5":{"draws":20,"losses":14,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":9},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":8},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":6},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":16},"inception/mercury-3":{"draws":3,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":24},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":5,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":31,"wins":6},"meta/muse-spark-open":{"draws":4,"losses":17,"wins":9},"meta/muse-wonder":{"draws":4,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"minimax/minimax-m3.1-flash":{"draws":9,"losses":13,"wins":8},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":0},"o3":{"draws":9,"losses":21,"wins":32},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":22},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":19},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":11},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":13,"wins":5},"stealth/ox-alpha":{"draws":35,"losses":70,"wins":35},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":6,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":20,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":26,"losses":4,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":30,"wins":27},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":7},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":10}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":5,"losses":33,"wins":10},"claude-fable-5-1":{"draws":5,"losses":46,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":21,"wins":12},"claude-opus-4-5":{"draws":28,"losses":24,"wins":26},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":10,"losses":60,"wins":12},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":13,"wins":10},"elorian/glimpse":{"draws":1,"losses":4,"wins":1},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":19},"gemini-4-argon":{"draws":0,"losses":29,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":46},"google/gemini-3.6-flash":{"draws":28,"losses":42,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":15},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":19},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":12,"losses":21,"wins":11},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":30,"wins":10},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":14},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":10,"losses":17,"wins":21},"gpt-6-sol":{"draws":10,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inception/mercury-3":{"draws":4,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":4,"wins":31},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":18,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-spark-open":{"draws":6,"losses":11,"wins":3},"meta/muse-wonder":{"draws":8,"losses":28,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":11,"losses":6,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":5,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":5,"wins":2},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":10,"losses":19,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":9,"wins":7},"stealth/ox-alpha":{"draws":43,"losses":68,"wins":47},"stealth/space-bunny-alpha":{"draws":15,"losses":12,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":28},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":29,"losses":5,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":13,"wins":2},"z-ai/glm-5.2":{"draws":40,"losses":22,"wins":34},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":20,"wins":18},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":14}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":51,"losses":43,"wins":38},"claude-fable-5":{"draws":29,"losses":96,"wins":19},"claude-fable-5-1":{"draws":8,"losses":152,"wins":2},"claude-haiku-5-5":{"draws":28,"losses":84,"wins":26},"claude-opus-4-5":{"draws":75,"losses":105,"wins":54},"claude-opus-4-8":{"draws":35,"losses":75,"wins":22},"claude-opus-5":{"draws":32,"losses":193,"wins":21},"claude-opus-5-5":{"draws":9,"losses":142,"wins":5},"claude-sonnet-5":{"draws":46,"losses":64,"wins":34},"claude-sonnet-5-5":{"draws":28,"losses":89,"wins":27},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":36},"deepseek/deepseek-v4-flash":{"draws":71,"losses":52,"wins":93},"deepseek/deepseek-v4-pro":{"draws":45,"losses":53,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":43,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":50,"losses":66,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":66,"wins":10},"elorian/glimpse":{"draws":13,"losses":20,"wins":13},"fireworks/ember-1":{"draws":48,"losses":69,"wins":27},"gemini-3.1-pro-preview":{"draws":43,"losses":64,"wins":37},"gemini-4-argon":{"draws":6,"losses":58,"wins":8},"google/gemini-3.1-flash-lite":{"draws":18,"losses":17,"wins":61},"google/gemini-3.5-flash":{"draws":41,"losses":88,"wins":51},"google/gemini-3.5-flash-lite":{"draws":75,"losses":88,"wins":89},"google/gemini-3.6-flash":{"draws":85,"losses":127,"wins":64},"google/gemini-3.8-flash":{"draws":38,"losses":80,"wins":26},"google/gemma-4-31b-it":{"draws":35,"losses":14,"wins":35},"gpt-4.1":{"draws":16,"losses":12,"wins":20},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":35,"losses":54,"wins":37},"gpt-5.4":{"draws":37,"losses":73,"wins":28},"gpt-5.4-mini":{"draws":43,"losses":21,"wins":32},"gpt-5.4-nano":{"draws":32,"losses":53,"wins":59},"gpt-5.5":{"draws":51,"losses":57,"wins":24},"gpt-5.6-luna":{"draws":50,"losses":40,"wins":54},"gpt-5.6-sol":{"draws":19,"losses":108,"wins":17},"gpt-5.6-terra":{"draws":52,"losses":50,"wins":36},"gpt-6-astra":{"draws":7,"losses":134,"wins":3},"gpt-6-luna":{"draws":53,"losses":57,"wins":34},"gpt-6-sol":{"draws":26,"losses":105,"wins":13},"gpt-6.1-sol":{"draws":12,"losses":128,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":43,"losses":10,"wins":49},"inception/mercury-3":{"draws":17,"losses":17,"wins":12},"inclusionai/ling-3.0-flash":{"draws":47,"losses":16,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":45,"losses":33,"wins":78},"meta/muse-glimmer-30b":{"draws":59,"losses":22,"wins":45},"meta/muse-spark-1.2":{"draws":32,"losses":67,"wins":39},"meta/muse-spark-1.3":{"draws":29,"losses":85,"wins":30},"meta/muse-spark-open":{"draws":15,"losses":46,"wins":13},"meta/muse-wonder":{"draws":30,"losses":95,"wins":19},"minimax/minimax-m3":{"draws":28,"losses":18,"wins":32},"minimax/minimax-m3.1-flash":{"draws":20,"losses":28,"wins":22},"mistralai/mistral-large-4-0":{"draws":29,"losses":43,"wins":18},"mistralai/mistral-medium-3-5":{"draws":41,"losses":8,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":43,"losses":61,"wins":34},"nex-agi/nex-n2-pro":{"draws":28,"losses":11,"wins":33},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":30,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":11,"wins":7},"o3":{"draws":34,"losses":94,"wins":70},"openai/gpt-oss-120b":{"draws":42,"losses":33,"wins":51},"poolside/laguna-s-2.1":{"draws":52,"losses":46,"wins":40},"qwen/qwen3.7-max":{"draws":25,"losses":35,"wins":24},"qwen/qwen3.7-plus":{"draws":20,"losses":17,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":56,"wins":30},"qwen/qwen3.8-27b":{"draws":35,"losses":39,"wins":28},"qwen/qwen3.8-flash":{"draws":39,"losses":30,"wins":27},"qwen/qwen3.8-max":{"draws":50,"losses":57,"wins":37},"qwen/qwen3.8-max-0902":{"draws":50,"losses":65,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":22,"wins":17},"stealth/ox-alpha":{"draws":122,"losses":253,"wins":99},"stealth/space-bunny-alpha":{"draws":40,"losses":37,"wins":37},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":46},"stepfun/step-5-preview":{"draws":4,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":28,"losses":23,"wins":27},"tencent/hy4-preview":{"draws":36,"losses":77,"wins":25},"thinkingmachines/inkling":{"draws":60,"losses":48,"wins":84},"thinkingmachines/inkling-small":{"draws":53,"losses":35,"wins":56},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":19},"x-ai/grok-4.5":{"draws":35,"losses":90,"wins":19},"x-ai/grok-4.6":{"draws":37,"losses":85,"wins":22},"x-ai/grok-4.7":{"draws":15,"losses":94,"wins":17},"x-ai/grok-build-0.1":{"draws":20,"losses":12,"wins":16},"xiaomi/mimo-v2.5":{"draws":75,"losses":58,"wins":89},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":32,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":53,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":56,"wins":18},"z-ai/glm-5.2":{"draws":85,"losses":85,"wins":70},"z-ai/glm-5.3":{"draws":33,"losses":93,"wins":12},"z-ai/glm-5.3-flash":{"draws":33,"losses":85,"wins":26},"z-ai/glm-5.3-flashx":{"draws":35,"losses":77,"wins":32}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":21},"claude-fable-5":{"draws":8,"losses":29,"wins":11},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":28,"losses":22,"wins":28},"claude-opus-4-8":{"draws":10,"losses":15,"wins":19},"claude-opus-5":{"draws":12,"losses":62,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":17,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":8,"wins":37},"deepseek/deepseek-v4-pro":{"draws":17,"losses":14,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":18,"wins":7},"elorian/glimpse":{"draws":5,"losses":4,"wins":5},"fireworks/ember-1":{"draws":18,"losses":14,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":16,"wins":21},"gemini-4-argon":{"draws":2,"losses":21,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":19,"losses":21,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":13,"wins":45},"google/gemini-3.6-flash":{"draws":24,"losses":33,"wins":35},"google/gemini-3.8-flash":{"draws":12,"losses":23,"wins":13},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":15,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":14,"wins":23},"gpt-5.5":{"draws":15,"losses":10,"wins":19},"gpt-5.6-luna":{"draws":16,"losses":13,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":16},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":11,"losses":19,"wins":18},"gpt-6-sol":{"draws":8,"losses":30,"wins":10},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inception/mercury-3":{"draws":8,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":7,"wins":29},"meta/muse-glimmer-30b":{"draws":10,"losses":10,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":18},"meta/muse-spark-open":{"draws":6,"losses":10,"wins":8},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":5,"losses":9,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":20,"losses":14,"wins":12},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":10,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":7},"o3":{"draws":10,"losses":26,"wins":30},"openai/gpt-oss-120b":{"draws":17,"losses":3,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":22},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":14,"wins":16},"qwen/qwen3.8-27b":{"draws":13,"losses":4,"wins":17},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":18,"losses":18,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":10,"wins":8},"stealth/ox-alpha":{"draws":46,"losses":68,"wins":44},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":20},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":15,"wins":18},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":27,"losses":3,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":38},"z-ai/glm-5.3":{"draws":5,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":14,"losses":18,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":21,"wins":13}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":8,"wins":21},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":11},"claude-opus-4-5":{"draws":24,"losses":25,"wins":29},"claude-opus-4-8":{"draws":6,"losses":23,"wins":15},"claude-opus-5":{"draws":17,"losses":55,"wins":10},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":13,"losses":19,"wins":16},"claude-sonnet-5-5":{"draws":10,"losses":23,"wins":15},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":30,"losses":15,"wins":27},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":14,"wins":4},"elorian/glimpse":{"draws":1,"losses":6,"wins":5},"fireworks/ember-1":{"draws":11,"losses":16,"wins":21},"gemini-3.1-pro-preview":{"draws":11,"losses":19,"wins":18},"gemini-4-argon":{"draws":3,"losses":13,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":10,"losses":25,"wins":25},"google/gemini-3.5-flash-lite":{"draws":25,"losses":23,"wins":36},"google/gemini-3.6-flash":{"draws":21,"losses":35,"wins":36},"google/gemini-3.8-flash":{"draws":7,"losses":26,"wins":15},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":13},"gpt-4.1":{"draws":2,"losses":7,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":12,"wins":20},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":15,"wins":22},"gpt-5.5":{"draws":12,"losses":18,"wins":14},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":13,"losses":26,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":13,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"gpt-6-sol":{"draws":7,"losses":29,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":19},"inception/mercury-3":{"draws":11,"losses":3,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":13,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":20,"wins":16},"meta/muse-spark-1.3":{"draws":9,"losses":22,"wins":17},"meta/muse-spark-open":{"draws":4,"losses":13,"wins":5},"meta/muse-wonder":{"draws":16,"losses":24,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"minimax/minimax-m3.1-flash":{"draws":6,"losses":13,"wins":9},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":16,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":6},"o3":{"draws":9,"losses":27,"wins":30},"openai/gpt-oss-120b":{"draws":12,"losses":10,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":11,"wins":19},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":16},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":11,"wins":9},"stealth/ox-alpha":{"draws":33,"losses":79,"wins":46},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":11},"thinkingmachines/inkling":{"draws":19,"losses":18,"wins":27},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":9,"losses":21,"wins":18},"x-ai/grok-4.6":{"draws":18,"losses":20,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":13,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":25,"wins":36},"z-ai/glm-5.3":{"draws":13,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":13,"losses":24,"wins":11}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":9,"losses":30,"wins":9},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":22,"wins":11},"claude-opus-4-5":{"draws":22,"losses":24,"wins":32},"claude-opus-4-8":{"draws":11,"losses":21,"wins":12},"claude-opus-5":{"draws":13,"losses":58,"wins":11},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":19,"losses":11,"wins":18},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":16,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":5},"elorian/glimpse":{"draws":1,"losses":6,"wins":5},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":18,"losses":12,"wins":18},"gemini-4-argon":{"draws":4,"losses":24,"wins":0},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":20,"losses":17,"wins":23},"google/gemini-3.5-flash-lite":{"draws":30,"losses":14,"wins":40},"google/gemini-3.6-flash":{"draws":30,"losses":34,"wins":28},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":15,"losses":11,"wins":16},"gpt-5.4":{"draws":17,"losses":17,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":12,"wins":24},"gpt-5.5":{"draws":19,"losses":15,"wins":10},"gpt-5.6-luna":{"draws":18,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":17},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":21},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inception/mercury-3":{"draws":6,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":2,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":9,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-spark-open":{"draws":2,"losses":9,"wins":9},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"minimax/minimax-m3.1-flash":{"draws":5,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":11,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":6},"o3":{"draws":12,"losses":14,"wins":40},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":9,"wins":14},"qwen/qwen3.8-flash":{"draws":13,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":7,"wins":6},"stealth/ox-alpha":{"draws":36,"losses":70,"wins":52},"stealth/space-bunny-alpha":{"draws":14,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":21,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":2,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":1,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":12,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":35,"losses":23,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":28,"wins":6},"z-ai/glm-5.3-flash":{"draws":12,"losses":26,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":10}}}}}