{"run":{"id":805,"source_url":"https://artificialanalysis.ai/models","status":"success","started_at":"2026-07-09T03:38:34.917Z","completed_at":"2026-07-09T05:00:28.666Z","duration_ms":178,"http_status":200,"html_bytes":1330712,"html_sha256":"5de73ba18b65e526e6ca2d93490fab973117b09b151ddb26dd221e1e16d2b7cf","html_gzip_bytes":147201,"raw_html_encoding":"gzip-base64-chunks","parser_version":"aa-next-rsc-cost-time-per-task-v3","model_count":28,"result_count":28,"error":null},"options":{"mode":"combined","calc":"raw","sort":"score","costWeight":10,"costFloor":0.01,"costPower":1,"frontierOnly":false,"frontierMetric":"cost","limit":100},"effectiveSortBy":"score","topQualityModel":{"modelKey":"claude-fable-5","sourceId":"cd55210d-358e-4df1-ba9c-9acb5f186cc9","slug":"claude-fable-5","name":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","shortName":"Claude Fable 5 (with fallback)","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2026-06-09","cutoffDate":null,"totalCost":5630.523205656231,"inputCost":1454.391435381231,"outputCost":4176.131770275,"reasoningCost":3668.502629025,"answerCost":507.62914125,"costPerTask":2.7498239008825984,"inputCostPerTask":1.1990165514847535,"outputCostPerTask":1.5508073493978443,"reasoningCostPerTask":1.1842275226716166,"answerCostPerTask":0.36657982672622763,"timePerTask":295.92909967759107,"intelligence":59.8606463217303,"coding":76.4911915660979,"agentic":52.8147079037801,"mmmu":null,"priceInput1m":10,"priceOutput1m":50,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"cd55210d-358e-4df1-ba9c-9acb5f186cc9\",\"slug\":\"claude-fable-5\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)\",\"short_name\":\"Claude Fable 5 (with fallback)\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2026-06-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":59.8606463217303,\"coding_index\":76.4911915660979,\"agentic_index\":52.8147079037801,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":5630.523205656231,\"input\":1454.391435381231,\"nonCacheInput\":171.796669695,\"cacheRead\":742.8574728702189,\"cacheWrite\":539.7372928160122,\"output\":4176.131770275,\"reasoning\":3668.502629025,\"answer\":507.62914125},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":2.7498239008825984,\"input\":1.1990165514847535,\"nonCacheInput\":0.09511416853774562,\"cacheRead\":0.6273828830939632,\"cacheWrite\":0.47651949985304487,\"output\":1.5508073493978443,\"reasoning\":1.1842275226716166,\"answer\":0.36657982672622763},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":1.2909983580530273},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.27643911337785104},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.5600661386773599},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.024086402378472222},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.12590305647358666},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.014055648271780305},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.35130120724999997},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.009103232650520833},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.09787074375}]},\"intelligence_index_time_per_task\":295.92909967759107,\"price_1m_input_tokens\":10,\"price_1m_output_tokens\":50,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":63.05551526386944,"costForScoring":2.7498239008825984,"costPenalty":24.393048824398033,"pointsPerK":22930.746672043544,"costPerQuality":0.04360956990638116,"deltaTop":0,"costVsTop":1,"calculated":63.05551526386944,"frontier":true},"rows":[{"modelKey":"claude-fable-5","sourceId":"cd55210d-358e-4df1-ba9c-9acb5f186cc9","slug":"claude-fable-5","name":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","shortName":"Claude Fable 5 (with fallback)","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2026-06-09","cutoffDate":null,"totalCost":5630.523205656231,"inputCost":1454.391435381231,"outputCost":4176.131770275,"reasoningCost":3668.502629025,"answerCost":507.62914125,"costPerTask":2.7498239008825984,"inputCostPerTask":1.1990165514847535,"outputCostPerTask":1.5508073493978443,"reasoningCostPerTask":1.1842275226716166,"answerCostPerTask":0.36657982672622763,"timePerTask":295.92909967759107,"intelligence":59.8606463217303,"coding":76.4911915660979,"agentic":52.8147079037801,"mmmu":null,"priceInput1m":10,"priceOutput1m":50,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"cd55210d-358e-4df1-ba9c-9acb5f186cc9\",\"slug\":\"claude-fable-5\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)\",\"short_name\":\"Claude Fable 5 (with fallback)\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2026-06-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":59.8606463217303,\"coding_index\":76.4911915660979,\"agentic_index\":52.8147079037801,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":5630.523205656231,\"input\":1454.391435381231,\"nonCacheInput\":171.796669695,\"cacheRead\":742.8574728702189,\"cacheWrite\":539.7372928160122,\"output\":4176.131770275,\"reasoning\":3668.502629025,\"answer\":507.62914125},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":2.7498239008825984,\"input\":1.1990165514847535,\"nonCacheInput\":0.09511416853774562,\"cacheRead\":0.6273828830939632,\"cacheWrite\":0.47651949985304487,\"output\":1.5508073493978443,\"reasoning\":1.1842275226716166,\"answer\":0.36657982672622763},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":1.2909983580530273},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.27643911337785104},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.5600661386773599},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.024086402378472222},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.12590305647358666},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.014055648271780305},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.35130120724999997},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.009103232650520833},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.09787074375}]},\"intelligence_index_time_per_task\":295.92909967759107,\"price_1m_input_tokens\":10,\"price_1m_output_tokens\":50,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":63.05551526386944,"costForScoring":2.7498239008825984,"costPenalty":24.393048824398033,"pointsPerK":22930.746672043544,"costPerQuality":0.04360956990638116,"deltaTop":0,"costVsTop":1,"calculated":63.05551526386944,"frontier":true},{"modelKey":"claude-opus-4-8","sourceId":"992b7b84-5069-4c6a-9295-834252553d50","slug":"claude-opus-4-8","name":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","shortName":"Claude Opus 4.8 (max)","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2026-05-28","cutoffDate":null,"totalCost":3752.546240475629,"inputCost":834.1656904756285,"outputCost":2918.3805500000003,"reasoningCost":2626.2547250000002,"answerCost":292.125825,"costPerTask":1.7972215258754352,"inputCostPerTask":0.7744653411750283,"outputCostPerTask":1.022756184700407,"reasoningCostPerTask":0.8116206279506174,"answerCostPerTask":0.21113555674978962,"timePerTask":415.90369131506515,"intelligence":55.6920406995495,"coding":74.2535372451103,"agentic":47.1756219931271,"mmmu":null,"priceInput1m":5,"priceOutput1m":25,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"992b7b84-5069-4c6a-9295-834252553d50\",\"slug\":\"claude-opus-4-8\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)\",\"short_name\":\"Claude Opus 4.8 (max)\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2026-05-28\",\"knowledge_cutoff_date\":null,\"intelligence_index\":55.6920406995495,\"coding_index\":74.2535372451103,\"agentic_index\":47.1756219931271,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":3752.546240475629,\"input\":834.1656904756285,\"nonCacheInput\":87.46856,\"cacheRead\":434.32935224124975,\"cacheWrite\":312.36777823437876,\"output\":2918.3805500000003,\"reasoning\":2626.2547250000002,\"answer\":292.125825},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.7972215258754352,\"input\":0.7744653411750283,\"nonCacheInput\":0.04742450919381809,\"cacheRead\":0.4203530726567357,\"cacheWrite\":0.30668775932447445,\"output\":1.022756184700407,\"reasoning\":0.8116206279506174,\"answer\":0.21113555674978962},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.723487981207303},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.18453373887271307},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.5705707363935402},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.02220321759259259},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.1028802939643188},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.01951797348484849},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.12108069196428571},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.003082801770833333},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.049864090625}]},\"intelligence_index_time_per_task\":415.90369131506515,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":25,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":59.0403999792623,"costForScoring":1.7972215258754352,"costPenalty":22.54601611630833,"pointsPerK":32850.93080025482,"costPerQuality":0.030440537775941592,"deltaTop":-4.015115284607141,"costVsTop":0.6535769527999917,"calculated":59.0403999792623,"frontier":true},{"modelKey":"gpt-5-5","sourceId":"1f054429-397e-4fdb-9e71-67bc92c1735e","slug":"gpt-5-5","name":"GPT-5.5 (xhigh)","shortName":"GPT-5.5 (xhigh)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-04-23","cutoffDate":null,"totalCost":2630.037206075943,"inputCost":460.98512607594284,"outputCost":2169.05208,"reasoningCost":2037.2752500000001,"answerCost":131.77683,"costPerTask":0.8627064537302028,"inputCostPerTask":0.3807721733064226,"outputCostPerTask":0.4819342804237804,"reasoningCostPerTask":0.37475954041009674,"answerCostPerTask":0.10717474001368364,"timePerTask":229.52118123559333,"intelligence":54.8375984166433,"coding":74.8911950339853,"agentic":44.8710687285223,"mmmu":0.798843930635838,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"1f054429-397e-4fdb-9e71-67bc92c1735e\",\"slug\":\"gpt-5-5\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.5 (xhigh)\",\"short_name\":\"GPT-5.5 (xhigh)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-04-23\",\"knowledge_cutoff_date\":null,\"intelligence_index\":54.8375984166433,\"coding_index\":74.8911950339853,\"agentic_index\":44.8710687285223,\"mmmu_pro\":0.798843930635838,\"intelligence_index_cost\":{\"total\":2630.037206075943,\"input\":460.98512607594284,\"nonCacheInput\":62.47511,\"cacheRead\":151.0194848804508,\"cacheWrite\":247.49053119549205,\"output\":2169.05208,\"reasoning\":2037.2752500000001,\"answer\":131.77683},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.8627064537302028,\"input\":0.3807721733064226,\"nonCacheInput\":0.0318362333929463,\"cacheRead\":0.1325161276958315,\"cacheWrite\":0.21641981221764478,\"output\":0.4819342804237804,\"reasoning\":0.37475954041009674,\"answer\":0.10717474001368364},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.2835885311034458},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.15037980640831328},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.20612035647962126},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.013206209490740741},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.04750378562326228},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.009626583017676769},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.10083758035714287},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.01894610125},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0324975}]},\"intelligence_index_time_per_task\":229.52118123559333,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":58.19995405971696,"costForScoring":0.8627064537302028,"costPenalty":19.358630469180603,"pointsPerK":67462.0594387231,"costPerQuality":0.014823146644497513,"deltaTop":-4.85556120415248,"costVsTop":0.31373152784558456,"calculated":58.19995405971696,"frontier":true},{"modelKey":"grok-4-5","sourceId":"794f69b5-cede-482b-b1cc-d769478497cd","slug":"grok-4-5","name":"Grok 4.5 (high)","shortName":"Grok 4.5 (high)","creatorName":"SpaceXAI","creatorSlug":"xai","releaseDate":"2026-07-08","cutoffDate":null,"totalCost":600.9213511405209,"inputCost":241.65348914052083,"outputCost":359.26786200000004,"reasoningCost":312.494592,"answerCost":46.77327,"costPerTask":0.3110838295302332,"inputCostPerTask":0.22830559607320602,"outputCostPerTask":0.08277823345702727,"reasoningCostPerTask":0.04514198167229541,"answerCostPerTask":0.037636251784731845,"timePerTask":160.24418514305668,"intelligence":53.8265951657731,"coding":72.4489353585796,"agentic":45.6901065292096,"mmmu":0.804046242774566,"priceInput1m":2,"priceOutput1m":6,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"794f69b5-cede-482b-b1cc-d769478497cd\",\"slug\":\"grok-4-5\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Grok 4.5 (high)\",\"short_name\":\"Grok 4.5 (high)\",\"creator_name\":\"SpaceXAI\",\"creator_slug\":\"xai\",\"release_date\":\"2026-07-08\",\"knowledge_cutoff_date\":null,\"intelligence_index\":53.8265951657731,\"coding_index\":72.4489353585796,\"agentic_index\":45.6901065292096,\"mmmu_pro\":0.804046242774566,\"intelligence_index_cost\":{\"total\":600.9213511405209,\"input\":241.65348914052083,\"nonCacheInput\":24.009772,\"cacheRead\":154.91362895315973,\"cacheWrite\":62.73008818736112,\"output\":359.26786200000004,\"reasoning\":312.494592,\"answer\":46.77327},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3110838295302332,\"input\":0.22830559607320602,\"nonCacheInput\":0.012752604425658624,\"cacheRead\":0.1551614600811449,\"cacheWrite\":0.06039153156640248,\"output\":0.08277823345702727,\"reasoning\":0.04514198167229541,\"answer\":0.037636251784731845},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0822142771605782},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.09938276552957355},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.08236006032234829},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0021650439814814813},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.014058099281742353},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0019724141414141417},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.015455603571428573},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0008067992916666668},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.01266876625}]},\"intelligence_index_time_per_task\":160.24418514305668,\"price_1m_input_tokens\":2,\"price_1m_output_tokens\":6,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":57.32187901785411,"costForScoring":0.3110838295302332,"costPenalty":14.928774366043278,"pointsPerK":184265.05519240812,"costPerQuality":0.0054269649714961295,"deltaTop":-5.73363624601533,"costVsTop":0.11312863686666846,"calculated":57.32187901785411,"frontier":true},{"modelKey":"claude-sonnet-5","sourceId":"23c86e4a-c769-43c0-a056-79e3cd15834f","slug":"claude-sonnet-5","name":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","shortName":"Claude Sonnet 5 (max)","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2026-06-30","cutoffDate":null,"totalCost":4010.1228898246927,"inputCost":974.0086498246926,"outputCost":3036.11424,"reasoningCost":2866.59191,"answerCost":169.52233,"costPerTask":1.5254254480225784,"inputCostPerTask":0.8380683731603117,"outputCostPerTask":0.6873570748622667,"reasoningCostPerTask":0.55944142229203,"answerCostPerTask":0.1279156525702367,"timePerTask":530.6598204283875,"intelligence":53.3500026989169,"coding":71.5455507005132,"agentic":46.6941408934708,"mmmu":0.772832369942197,"priceInput1m":2,"priceOutput1m":10,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"23c86e4a-c769-43c0-a056-79e3cd15834f\",\"slug\":\"claude-sonnet-5\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)\",\"short_name\":\"Claude Sonnet 5 (max)\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2026-06-30\",\"knowledge_cutoff_date\":null,\"intelligence_index\":53.3500026989169,\"coding_index\":71.5455507005132,\"agentic_index\":46.6941408934708,\"mmmu_pro\":0.772832369942197,\"intelligence_index_cost\":{\"total\":4010.1228898246927,\"input\":974.0086498246926,\"nonCacheInput\":35.723138,\"cacheRead\":680.4456681022007,\"cacheWrite\":257.839843722492,\"output\":3036.11424,\"reasoning\":2866.59191,\"answer\":169.52233},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.5254254480225784,\"input\":0.8380683731603117,\"nonCacheInput\":0.019422892273995025,\"cacheRead\":0.5828711828415486,\"cacheWrite\":0.23577429804476807,\"output\":0.6873570748622667,\"reasoning\":0.55944142229203,\"answer\":0.1279156525702367},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.7839856467156713},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.08908804230470398},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.31465345864668753},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.015971962962962962},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.12760057460611676},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0228913970959596},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.14460963035714286},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0036284628333333336},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.022996272499999998}]},\"intelligence_index_time_per_task\":530.6598204283875,\"price_1m_input_tokens\":2,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":57.1965647643003,"costForScoring":1.5254254480225784,"costPenalty":21.83390987262865,"pointsPerK":37495.483531132035,"costPerQuality":0.026669878764724087,"deltaTop":-5.85895049956914,"costVsTop":0.5547356859953722,"calculated":57.1965647643003,"frontier":false},{"modelKey":"glm-5-2","sourceId":"f7a4ea75-e548-4069-80d4-9be8bc7c009b","slug":"glm-5-2","name":"GLM-5.2 (max)","shortName":"GLM-5.2 (max)","creatorName":"Z AI","creatorSlug":"zai","releaseDate":"2026-06-16","cutoffDate":null,"totalCost":820.3840342068177,"inputCost":201.22513340681775,"outputCost":619.1589008,"reasoningCost":586.2232948,"answerCost":32.935606,"costPerTask":0.370080167362808,"inputCostPerTask":0.1818002462152849,"outputCostPerTask":0.18827992114752315,"reasoningCostPerTask":0.16148805597970656,"answerCostPerTask":0.026791865167816648,"timePerTask":186.0145809292031,"intelligence":51.0858347714416,"coding":68.7560688028853,"agentic":43.0557079037801,"mmmu":null,"priceInput1m":1.4,"priceOutput1m":4.4,"activeParams":40,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"f7a4ea75-e548-4069-80d4-9be8bc7c009b\",\"slug\":\"glm-5-2\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GLM-5.2 (max)\",\"short_name\":\"GLM-5.2 (max)\",\"creator_name\":\"Z AI\",\"creator_slug\":\"zai\",\"release_date\":\"2026-06-16\",\"knowledge_cutoff_date\":null,\"intelligence_index\":51.0858347714416,\"coding_index\":68.7560688028853,\"agentic_index\":43.0557079037801,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":820.3840342068177,\"input\":201.22513340681775,\"nonCacheInput\":17.707790799999998,\"cacheRead\":128.20078558441,\"cacheWrite\":55.316557022407764,\"output\":619.1589008,\"reasoning\":586.2232948,\"answer\":32.935606},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.370080167362808,\"input\":0.1818002462152849,\"nonCacheInput\":0.009786523802333615,\"cacheRead\":0.12067354661234247,\"cacheWrite\":0.05134017580060882,\"output\":0.18827992114752315,\"reasoning\":0.16148805597970656,\"answer\":0.026791865167816648},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.15028764567819158},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03718835943607572},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.10928236166294515},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.004614115914351852},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.022379358677015758},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.005472933648989901},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.03014941392857143},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0010737395416666668},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.009632238875}]},\"intelligence_index_time_per_task\":186.0145809292031,\"price_1m_input_tokens\":1.4,\"price_1m_output_tokens\":4.4,\"activeParams\":40,\"is_open_weights\":true,\"reasoning_model\":true}","quality":54.299203826035665,"costForScoring":0.370080167362808,"costPenalty":15.682958118292884,"pointsPerK":146722.8147159895,"costPerQuality":0.006815572628808234,"deltaTop":-8.756311437833773,"costVsTop":0.1345832244908574,"calculated":54.299203826035665,"frontier":false},{"modelKey":"gemini-3-5-flash","sourceId":"0097ebf5-124f-42f6-9463-33b00e711f03","slug":"gemini-3-5-flash","name":"Gemini 3.5 Flash (high)","shortName":"Gemini 3.5 Flash","creatorName":"Google","creatorSlug":"google","releaseDate":"2026-05-19","cutoffDate":null,"totalCost":1040.8780605451614,"inputCost":362.42750554516135,"outputCost":678.450555,"reasoningCost":564.408621,"answerCost":114.041934,"costPerTask":0.585545242207561,"inputCostPerTask":0.33594515287361043,"outputCostPerTask":0.2496000893339504,"reasoningCostPerTask":0.16122540195542004,"answerCostPerTask":0.08837468737853037,"timePerTask":163.61863154083977,"intelligence":50.2034858842254,"coding":70.1427902621723,"agentic":37.4466082474227,"mmmu":0.842774566473988,"priceInput1m":1.5,"priceOutput1m":9,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"0097ebf5-124f-42f6-9463-33b00e711f03\",\"slug\":\"gemini-3-5-flash\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Gemini 3.5 Flash (high)\",\"short_name\":\"Gemini 3.5 Flash\",\"creator_name\":\"Google\",\"creator_slug\":\"google\",\"release_date\":\"2026-05-19\",\"knowledge_cutoff_date\":null,\"intelligence_index\":50.2034858842254,\"coding_index\":70.1427902621723,\"agentic_index\":37.4466082474227,\"mmmu_pro\":0.842774566473988,\"intelligence_index_cost\":{\"total\":1040.8780605451614,\"input\":362.42750554516135,\"nonCacheInput\":19.8340515,\"cacheRead\":127.94699032831538,\"cacheWrite\":214.64646371684594,\"output\":678.450555,\"reasoning\":564.408621,\"answer\":114.041934},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.585545242207561,\"input\":0.33594515287361043,\"nonCacheInput\":0.01089766676630774,\"cacheRead\":0.12138763995520149,\"cacheWrite\":0.20365984615210125,\"output\":0.2496000893339504,\"reasoning\":0.16122540195542004,\"answer\":0.08837468737853037},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.2900476835987163},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.08252448572942059},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1444751391494575},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.005681971354166666},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.018470218721037997},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0031407864583333344},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.02749599107142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0018021611250000002},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.011906805000000001}]},\"intelligence_index_time_per_task\":163.61863154083977,\"price_1m_input_tokens\":1.5,\"price_1m_output_tokens\":9,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":52.59762813127347,"costForScoring":0.585545242207561,"costPenalty":17.675604565083034,"pointsPerK":89826.7534938469,"costPerQuality":0.011132540820018608,"deltaTop":-10.457887132595971,"costVsTop":0.2129391784032502,"calculated":52.59762813127347,"frontier":false},{"modelKey":"qwen3-7-max","sourceId":"69534bed-2ffd-4235-832b-e20a810333ab","slug":"qwen3-7-max","name":"Qwen3.7 Max","shortName":"Qwen3.7 Max","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-05-19","cutoffDate":null,"totalCost":1631.3504971502557,"inputCost":859.6015321502559,"outputCost":771.7489649999999,"reasoningCost":724.1328599999999,"answerCost":47.616105,"costPerTask":1.061325321467105,"inputCostPerTask":0.8935285616828742,"outputCostPerTask":0.16779675978423086,"reasoningCostPerTask":0.1334930681431125,"answerCostPerTask":0.03430369164111838,"timePerTask":92.38459859843077,"intelligence":45.9937184770221,"coding":65.9687543348592,"agentic":30.5882783505155,"mmmu":null,"priceInput1m":2.5,"priceOutput1m":7.5,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"69534bed-2ffd-4235-832b-e20a810333ab\",\"slug\":\"qwen3-7-max\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.7 Max\",\"short_name\":\"Qwen3.7 Max\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-05-19\",\"knowledge_cutoff_date\":null,\"intelligence_index\":45.9937184770221,\"coding_index\":65.9687543348592,\"agentic_index\":30.5882783505155,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":1631.3504971502557,\"input\":859.6015321502559,\"nonCacheInput\":33.1299275,\"cacheRead\":5.814852584760357,\"cacheWrite\":820.6567520654955,\"output\":771.7489649999999,\"reasoning\":724.1328599999999,\"answer\":47.616105},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.061325321467105,\"input\":0.8935285616828742,\"nonCacheInput\":0.018014952291583917,\"cacheRead\":0.006166823038538993,\"cacheWrite\":0.8693467863527512,\"output\":0.16779675978423086,\"reasoning\":0.1334930681431125,\"answer\":0.03430369164111838},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.21514194270449277},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.34239012866312196},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.392499425124441},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.004866382378472222},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.03118987995250232},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.005116905776515151},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.05098561160714286},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0017244765104166664},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.01741056875}]},\"intelligence_index_time_per_task\":92.38459859843077,\"price_1m_input_tokens\":2.5,\"price_1m_output_tokens\":7.5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":47.51691705413227,"costForScoring":1.061325321467105,"costPenalty":20.25848525901472,"pointsPerK":44771.3025337491,"costPerQuality":0.022335736139152733,"deltaTop":-15.538598209737167,"costVsTop":0.38596119596111456,"calculated":47.51691705413227,"frontier":false},{"modelKey":"deepseek-v4-pro","sourceId":"bf220674-68bd-43cc-a1b8-ce5ed4d2f18d","slug":"deepseek-v4-pro","name":"DeepSeek V4 Pro (Reasoning, Max Effort)","shortName":"DeepSeek V4 Pro (max)","creatorName":"DeepSeek","creatorSlug":"deepseek","releaseDate":"2026-04-24","cutoffDate":null,"totalCost":176.33920107780003,"inputCost":15.6498609078,"outputCost":160.68934017000004,"reasoningCost":153.45185715000002,"answerCost":7.23748302,"costPerTask":0.044843733471261124,"inputCostPerTask":0.012686253718118372,"outputCostPerTask":0.032157479753142745,"reasoningCostPerTask":0.025855877778002877,"answerCostPerTask":0.006301601975139872,"timePerTask":461.3801813832595,"intelligence":44.2735554261611,"coding":59.3632958801498,"agentic":36.3637319587629,"mmmu":null,"priceInput1m":0.435,"priceOutput1m":0.87,"activeParams":49,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"bf220674-68bd-43cc-a1b8-ce5ed4d2f18d\",\"slug\":\"deepseek-v4-pro\",\"model_url\":null,\"hosts_url\":null,\"name\":\"DeepSeek V4 Pro (Reasoning, Max Effort)\",\"short_name\":\"DeepSeek V4 Pro (max)\",\"creator_name\":\"DeepSeek\",\"creator_slug\":\"deepseek\",\"release_date\":\"2026-04-24\",\"knowledge_cutoff_date\":null,\"intelligence_index\":44.2735554261611,\"coding_index\":59.3632958801498,\"agentic_index\":36.3637319587629,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":176.33920107780003,\"input\":15.6498609078,\"nonCacheInput\":5.468218395,\"cacheRead\":1.1771512128,\"cacheWrite\":9.0044913,\"output\":160.68934017000004,\"reasoning\":153.45185715000002,\"answer\":7.23748302},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.044843733471261124,\"input\":0.012686253718118372,\"nonCacheInput\":0.002844427589479215,\"cacheRead\":0.0012177412061614523,\"cacheWrite\":0.008624084922477702,\"output\":0.032157479753142745,\"reasoning\":0.025855877778002877,\"answer\":0.006301601975139872},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.008813995842727273},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0032855209814432987},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.015023615651685394},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0009467102864583332},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.005793920490326692},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001577533678977273},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.005805499513392858},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00069622435125},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0029007126750000005}]},\"intelligence_index_time_per_task\":461.3801813832595,\"price_1m_input_tokens\":0.435,\"price_1m_output_tokens\":0.87,\"activeParams\":49,\"is_open_weights\":true,\"reasoning_model\":true}","quality":46.66686108835793,"costForScoring":0.044843733471261124,"costPenalty":6.517017626755929,"pointsPerK":1040655.1256100296,"costPerQuality":0.0009609331423931654,"deltaTop":-16.388654175511505,"costVsTop":0.016307856461960285,"calculated":46.66686108835793,"frontier":true},{"modelKey":"minimax-m3","sourceId":"277f939a-985b-4b37-859d-b3eabc7c0b26","slug":"minimax-m3","name":"MiniMax-M3","shortName":"MiniMax-M3","creatorName":"MiniMax","creatorSlug":"minimax","releaseDate":"2026-06-01","cutoffDate":null,"totalCost":203.85795386627436,"inputCost":97.32069266627437,"outputCost":106.53726119999999,"reasoningCost":91.99946279999999,"answerCost":14.5377984,"costPerTask":0.12455059919140353,"inputCostPerTask":0.09579395974794415,"outputCostPerTask":0.028756639443459357,"reasoningCostPerTask":0.014808572972802726,"answerCostPerTask":0.013948066470656634,"timePerTask":242.76238478795142,"intelligence":44.4372686326056,"coding":58.5691496740186,"agentic":35.3635635738832,"mmmu":0.785549132947977,"priceInput1m":0.3,"priceOutput1m":1.2,"activeParams":23,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"277f939a-985b-4b37-859d-b3eabc7c0b26\",\"slug\":\"minimax-m3\",\"model_url\":null,\"hosts_url\":null,\"name\":\"MiniMax-M3\",\"short_name\":\"MiniMax-M3\",\"creator_name\":\"MiniMax\",\"creator_slug\":\"minimax\",\"release_date\":\"2026-06-01\",\"knowledge_cutoff_date\":null,\"intelligence_index\":44.4372686326056,\"coding_index\":58.5691496740186,\"agentic_index\":35.3635635738832,\"mmmu_pro\":0.785549132947977,\"intelligence_index_cost\":{\"total\":203.85795386627436,\"input\":97.32069266627437,\"nonCacheInput\":5.5863648,\"cacheRead\":68.76588826356678,\"cacheWrite\":22.968439602707587,\"output\":106.53726119999999,\"reasoning\":91.99946279999999,\"answer\":14.5377984},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.12455059919140353,\"input\":0.09579395974794415,\"nonCacheInput\":0.002440208674091713,\"cacheRead\":0.07041142810573091,\"cacheWrite\":0.02294232296812152,\"output\":0.028756639443459357,\"reasoning\":0.014808572972802726,\"answer\":0.013948066470656634},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.058050754688591756},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.005311196200909725},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.04690039269564482},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0021619684027777775},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.003240098111677479},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0006179965909090909},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.005971537232142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00043695076875},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0018597045000000002}]},\"intelligence_index_time_per_task\":242.76238478795142,\"price_1m_input_tokens\":0.3,\"price_1m_output_tokens\":1.2,\"activeParams\":23,\"is_open_weights\":true,\"reasoning_model\":true}","quality":46.12332729350246,"costForScoring":0.12455059919140353,"costPenalty":10.953458211932334,"pointsPerK":370317.98797388596,"costPerQuality":0.002700381921686499,"deltaTop":-16.932187970366975,"costVsTop":0.0452940274289663,"calculated":46.12332729350246,"frontier":false},{"modelKey":"gemini-3-1-pro-preview","sourceId":"bbd93ebe-80da-4594-bb19-61e69d0331df","slug":"gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","shortName":"Gemini 3.1 Pro Preview","creatorName":"Google","creatorSlug":"google","releaseDate":"2026-02-19","cutoffDate":null,"totalCost":815.1126168932034,"inputCost":143.63810889320337,"outputCost":671.474508,"reasoningCost":622.437984,"answerCost":49.036524,"costPerTask":0.29113642988035915,"inputCostPerTask":0.133079967904319,"outputCostPerTask":0.15805646197604017,"reasoningCostPerTask":0.1251654007402225,"answerCostPerTask":0.03289106123581768,"timePerTask":88.41110763914182,"intelligence":46.4594206066426,"coding":68.825860036066,"agentic":21.3959484536082,"mmmu":0.824277456647399,"priceInput1m":2,"priceOutput1m":12,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"bbd93ebe-80da-4594-bb19-61e69d0331df\",\"slug\":\"gemini-3-1-pro-preview\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Gemini 3.1 Pro Preview\",\"short_name\":\"Gemini 3.1 Pro Preview\",\"creator_name\":\"Google\",\"creator_slug\":\"google\",\"release_date\":\"2026-02-19\",\"knowledge_cutoff_date\":null,\"intelligence_index\":46.4594206066426,\"coding_index\":68.825860036066,\"agentic_index\":21.3959484536082,\"mmmu_pro\":0.824277456647399,\"intelligence_index_cost\":{\"total\":815.1126168932034,\"input\":143.63810889320337,\"nonCacheInput\":23.72652,\"cacheRead\":47.59359145631074,\"cacheWrite\":72.31799743689264,\"output\":671.474508,\"reasoning\":622.437984,\"answer\":49.036524},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.29113642988035915,\"input\":0.133079967904319,\"nonCacheInput\":0.012854042745448995,\"cacheRead\":0.04905441960502928,\"cacheWrite\":0.0711715055538407,\"output\":0.15805646197604017,\"reasoning\":0.1251654007402225,\"answer\":0.03289106123581768},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.04544787932103789},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0677771088361332},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.09632816012017663},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0073936215277777785},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.024594324953660797},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004471650252525253},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.029619801785714283},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0022089280833333335},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.013294954999999999}]},\"intelligence_index_time_per_task\":88.41110763914182,\"price_1m_input_tokens\":2,\"price_1m_output_tokens\":12,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":45.560409698772276,"costForScoring":0.29113642988035915,"costPenalty":14.640965520761046,"pointsPerK":156491.61363109064,"costPerQuality":0.006390118785262031,"deltaTop":-17.495105565097163,"costVsTop":0.10587457247240975,"calculated":45.560409698772276,"frontier":false},{"modelKey":"kimi-k2-6","sourceId":"0de67206-4d36-4d10-b8f6-cf37fa747a03","slug":"kimi-k2-6","name":"Kimi K2.6","shortName":"Kimi K2.6","creatorName":"Kimi","creatorSlug":"kimi","releaseDate":"2026-04-20","cutoffDate":null,"totalCost":851.6340396518642,"inputCost":191.0975356518643,"outputCost":660.5365039999999,"reasoningCost":635.547972,"answerCost":24.988532,"costPerTask":0.34554319749943396,"inputCostPerTask":0.1929978964237625,"outputCostPerTask":0.15254530107567138,"reasoningCostPerTask":0.13095474719708786,"answerCostPerTask":0.021590553878583475,"timePerTask":891.1077672997611,"intelligence":44.2196682298639,"coding":61.7691427382439,"agentic":30.2685189003436,"mmmu":0.79364161849711,"priceInput1m":0.95,"priceOutput1m":4,"activeParams":32,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"0de67206-4d36-4d10-b8f6-cf37fa747a03\",\"slug\":\"kimi-k2-6\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Kimi K2.6\",\"short_name\":\"Kimi K2.6\",\"creator_name\":\"Kimi\",\"creator_slug\":\"kimi\",\"release_date\":\"2026-04-20\",\"knowledge_cutoff_date\":null,\"intelligence_index\":44.2196682298639,\"coding_index\":61.7691427382439,\"agentic_index\":30.2685189003436,\"mmmu_pro\":0.79364161849711,\"intelligence_index_cost\":{\"total\":851.6340396518642,\"input\":191.0975356518643,\"nonCacheInput\":11.16486265,\"cacheRead\":65.4737920705085,\"cacheWrite\":114.45888093135581,\"output\":660.5365039999999,\"reasoning\":635.547972,\"answer\":24.988532},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.34554319749943396,\"input\":0.1929978964237625,\"nonCacheInput\":0.006016116644985975,\"cacheRead\":0.06449165287486945,\"cacheWrite\":0.1224901269039071,\"output\":0.15254530107567138,\"reasoning\":0.13095474719708786,\"answer\":0.021590553878583475},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.09621586870839749},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03172331984361347},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.13142066293785307},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0038632766493055548},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0215131765205051},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.005364700568181819},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.04582329633928571},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0032125399635416665},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.006406355968749999}]},\"intelligence_index_time_per_task\":891.1077672997611,\"price_1m_input_tokens\":0.95,\"price_1m_output_tokens\":4,\"activeParams\":32,\"is_open_weights\":true,\"reasoning_model\":true}","quality":45.419109956150464,"costForScoring":0.34554319749943396,"costPenalty":15.38502347695558,"pointsPerK":131442.63954501628,"costPerQuality":0.007607881304434103,"deltaTop":-17.636405307718974,"costVsTop":0.12566011859469492,"calculated":45.419109956150464,"frontier":false},{"modelKey":"mimo-v2-5-pro","sourceId":"00f1248e-78e3-4230-8dc8-5e13ba8645e2","slug":"mimo-v2-5-pro","name":"MiMo-V2.5-Pro","shortName":"MiMo-V2.5-Pro","creatorName":"Xiaomi","creatorSlug":"xiaomi","releaseDate":"2026-04-22","cutoffDate":null,"totalCost":98.46748027500001,"inputCost":15.130792755,"outputCost":83.33668752000001,"reasoningCost":76.59469734000001,"answerCost":6.74199018,"costPerTask":0.03139528698492376,"inputCostPerTask":0.01358083051611694,"outputCostPerTask":0.01781445646880682,"reasoningCostPerTask":0.013151636428062862,"answerCostPerTask":0.00466282004074396,"timePerTask":419.83416267172214,"intelligence":42.2394366693508,"coding":60.189520044389,"agentic":29.1125979381443,"mmmu":null,"priceInput1m":0.435,"priceOutput1m":0.87,"activeParams":42,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"00f1248e-78e3-4230-8dc8-5e13ba8645e2\",\"slug\":\"mimo-v2-5-pro\",\"model_url\":null,\"hosts_url\":null,\"name\":\"MiMo-V2.5-Pro\",\"short_name\":\"MiMo-V2.5-Pro\",\"creator_name\":\"Xiaomi\",\"creator_slug\":\"xiaomi\",\"release_date\":\"2026-04-22\",\"knowledge_cutoff_date\":null,\"intelligence_index\":42.2394366693508,\"coding_index\":60.189520044389,\"agentic_index\":29.1125979381443,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":98.46748027500001,\"input\":15.130792755,\"nonCacheInput\":5.963311035,\"cacheRead\":1.0611792899999999,\"cacheWrite\":8.10630243,\"output\":83.33668752000001,\"reasoning\":76.59469734000001,\"answer\":6.74199018},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.03139528698492376,\"input\":0.01358083051611694,\"nonCacheInput\":0.0033644625351784176,\"cacheRead\":0.0013231160803496096,\"cacheWrite\":0.008893251900588914,\"output\":0.01781445646880682,\"reasoning\":0.013151636428062862,\"answer\":0.00466282004074396},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.006620279709545454},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0022842764701030928},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.011427574816853931},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00041103598090277776},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.002979155906510658},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0007511285606060608},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0035784913794642856},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00035297336406249995},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.002990370796875}]},\"intelligence_index_time_per_task\":419.83416267172214,\"price_1m_input_tokens\":0.435,\"price_1m_output_tokens\":0.87,\"activeParams\":42,\"is_open_weights\":true,\"reasoning_model\":true}","quality":43.84718488396137,"costForScoring":0.03139528698492376,"costPenalty":4.968644573067464,"pointsPerK":1396616.7885331672,"costPerQuality":0.0007160160240163487,"deltaTop":-19.20833037990807,"costVsTop":0.01141719910676715,"calculated":43.84718488396137,"frontier":true},{"modelKey":"deepseek-v4-flash","sourceId":"d8ddb241-b3e4-4c25-a6a3-72eb1b30c541","slug":"deepseek-v4-flash","name":"DeepSeek V4 Flash (Reasoning, Max Effort)","shortName":"DeepSeek V4 Flash (max)","creatorName":"DeepSeek","creatorSlug":"deepseek","releaseDate":"2026-04-24","cutoffDate":null,"totalCost":74.3126277163192,"inputCost":8.879784436319195,"outputCost":65.43284328,"reasoningCost":62.714646120000005,"answerCost":2.71819716,"costPerTask":0.0222818336454049,"inputCostPerTask":0.009604395083955603,"outputCostPerTask":0.012677438561449298,"reasoningCostPerTask":0.009745442529604026,"answerCostPerTask":0.0029319960318452726,"timePerTask":336.48577689902214,"intelligence":40.2825017625236,"coding":56.1676376751283,"agentic":31.0645326460481,"mmmu":null,"priceInput1m":0.14,"priceOutput1m":0.28,"activeParams":13,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"d8ddb241-b3e4-4c25-a6a3-72eb1b30c541\",\"slug\":\"deepseek-v4-flash\",\"model_url\":null,\"hosts_url\":null,\"name\":\"DeepSeek V4 Flash (Reasoning, Max Effort)\",\"short_name\":\"DeepSeek V4 Flash (max)\",\"creator_name\":\"DeepSeek\",\"creator_slug\":\"deepseek\",\"release_date\":\"2026-04-24\",\"knowledge_cutoff_date\":null,\"intelligence_index\":40.2825017625236,\"coding_index\":56.1676376751283,\"agentic_index\":31.0645326460481,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":74.3126277163192,\"input\":8.879784436319195,\"nonCacheInput\":1.73830104,\"cacheRead\":1.8371617523200163,\"cacheWrite\":5.304321643999178,\"output\":65.43284328,\"reasoning\":62.714646120000005,\"answer\":2.71819716},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.0222818336454049,\"input\":0.009604395083955603,\"nonCacheInput\":0.0008938034761465444,\"cacheRead\":0.0024927649042623106,\"cacheWrite\":0.006217826703546748,\"output\":0.012677438561449298,\"reasoning\":0.009745442529604026,\"answer\":0.0029319960318452726},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.003402522399077933},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0016091632284983167},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.00919032238120652},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0003072323090277778},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0025005785518999075},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000516052152777778},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0035603702500000005},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00024296123541666666},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0009526311375}]},\"intelligence_index_time_per_task\":336.48577689902214,\"price_1m_input_tokens\":0.14,\"price_1m_output_tokens\":0.28,\"activeParams\":13,\"is_open_weights\":true,\"reasoning_model\":true}","quality":42.50489069456666,"costForScoring":0.0222818336454049,"costPenalty":3.479509274942142,"pointsPerK":1907602.9096614446,"costPerQuality":0.0005242181142287505,"deltaTop":-20.550624569302776,"costVsTop":0.008103003846265647,"calculated":42.50489069456666,"frontier":true},{"modelKey":"gpt-5-4-mini","sourceId":"ba242e40-83b7-4cd3-a0e0-b56237984914","slug":"gpt-5-4-mini","name":"GPT-5.4 mini (xhigh)","shortName":"GPT-5.4 mini (xhigh)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-03-17","cutoffDate":"2025-08-31","totalCost":1127.4359095629068,"inputCost":153.4656025629069,"outputCost":973.9703069999999,"reasoningCost":952.0490295,"answerCost":21.9212775,"costPerTask":0.47929864085182117,"inputCostPerTask":0.12775208811082625,"outputCostPerTask":0.35154655274099506,"reasoningCostPerTask":0.3300396390286433,"answerCostPerTask":0.02150691371235167,"timePerTask":469.84454728725024,"intelligence":39.9783061419024,"coding":56.0787730614509,"agentic":30.1670996563574,"mmmu":0.732947976878613,"priceInput1m":0.75,"priceOutput1m":4.5,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"ba242e40-83b7-4cd3-a0e0-b56237984914\",\"slug\":\"gpt-5-4-mini\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.4 mini (xhigh)\",\"short_name\":\"GPT-5.4 mini (xhigh)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-03-17\",\"knowledge_cutoff_date\":\"2025-08-31\",\"intelligence_index\":39.9783061419024,\"coding_index\":56.0787730614509,\"agentic_index\":30.1670996563574,\"mmmu_pro\":0.732947976878613,\"intelligence_index_cost\":{\"total\":1127.4359095629068,\"input\":153.4656025629069,\"nonCacheInput\":8.81514675,\"cacheRead\":42.18475704856589,\"cacheWrite\":102.465698764341,\"output\":973.9703069999999,\"reasoning\":952.0490295,\"answer\":21.9212775},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.47929864085182117,\"input\":0.12775208811082625,\"nonCacheInput\":0.0047302123966912225,\"cacheRead\":0.035685374138592685,\"cacheWrite\":0.08733650157554233,\"output\":0.35154655274099506,\"reasoning\":0.3300396390286433,\"answer\":0.02150691371235167},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.1134531378044491},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.05980924875618238},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.21695943231992096},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.017140938151041663},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.018887208816033365},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004821155776515152},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.03498214419642857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00713899971875},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0061063753125}]},\"intelligence_index_time_per_task\":469.84454728725024,\"price_1m_input_tokens\":0.75,\"price_1m_output_tokens\":4.5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":42.07472628657024,"costForScoring":0.47929864085182117,"costPenalty":16.806061974637448,"pointsPerK":87783.94658452194,"costPerQuality":0.011391604489291893,"deltaTop":-20.9807889772992,"costVsTop":0.1743015764383977,"calculated":42.07472628657024,"frontier":false},{"modelKey":"nvidia-nemotron-3-ultra-550b-a55b","sourceId":"5b52def2-ac9b-4465-ad80-91ea8079e253","slug":"nvidia-nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B (Reasoning)","shortName":"Nemotron 3 Ultra","creatorName":"NVIDIA","creatorSlug":"nvidia","releaseDate":"2026-06-04","cutoffDate":null,"totalCost":443.06889920540624,"inputCost":154.60985958040624,"outputCost":288.459039625,"reasoningCost":254.9132797,"answerCost":33.545759925,"costPerTask":0.24390316682824711,"inputCostPerTask":0.1825452781125399,"outputCostPerTask":0.06135788871570717,"reasoningCostPerTask":0.04050174423253931,"answerCostPerTask":0.020856144483167846,"timePerTask":104.9939095121878,"intelligence":37.7619546243905,"coding":49.2652413649605,"agentic":27.3604776632302,"mmmu":null,"priceInput1m":0.675,"priceOutput1m":2.675,"activeParams":55,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"5b52def2-ac9b-4465-ad80-91ea8079e253\",\"slug\":\"nvidia-nemotron-3-ultra-550b-a55b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Nemotron 3 Ultra 550B A55B (Reasoning)\",\"short_name\":\"Nemotron 3 Ultra\",\"creator_name\":\"NVIDIA\",\"creator_slug\":\"nvidia\",\"release_date\":\"2026-06-04\",\"knowledge_cutoff_date\":null,\"intelligence_index\":37.7619546243905,\"coding_index\":49.2652413649605,\"agentic_index\":27.3604776632302,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":443.06889920540624,\"input\":154.60985958040624,\"nonCacheInput\":8.99135505,\"cacheRead\":63.356794879172796,\"cacheWrite\":82.26170965123346,\"output\":288.459039625,\"reasoning\":254.9132797,\"answer\":33.545759925},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.24390316682824711,\"input\":0.1825452781125399,\"nonCacheInput\":0.004871827724390802,\"cacheRead\":0.0787037439110585,\"cacheWrite\":0.09896970647709064,\"output\":0.06135788871570717,\"reasoning\":0.04050174423253931,\"answer\":0.020856144483167846},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.058882267227163824},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.02435817953835217},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1250958280110638},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0010322995008680556},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.01245460079500695},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.002474031881313131},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.013911199999999999},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0004111307182291666},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0052836291562500005}]},\"intelligence_index_time_per_task\":104.9939095121878,\"price_1m_input_tokens\":0.675,\"price_1m_output_tokens\":2.675,\"activeParams\":55,\"is_open_weights\":true,\"reasoning_model\":true}","quality":38.1292245508604,"costForScoring":0.24390316682824711,"costPenalty":13.872174392112466,"pointsPerK":156329.3541723893,"costPerQuality":0.006396751303003967,"deltaTop":-24.92629071300904,"costVsTop":0.08869774051711553,"calculated":38.1292245508604,"frontier":false},{"modelKey":"grok-4-3","sourceId":"948892b5-db03-4118-a4a8-ccd51ed871ea","slug":"grok-4-3","name":"Grok 4.3 (high)","shortName":"Grok 4.3 (high)","creatorName":"SpaceXAI","creatorSlug":"xai","releaseDate":"2026-04-30","cutoffDate":null,"totalCost":287.6431168111509,"inputCost":79.55449681115093,"outputCost":208.08862,"reasoningCost":195.56833,"answerCost":12.520290000000001,"costPerTask":0.13850067515455958,"inputCostPerTask":0.10258732037383253,"outputCostPerTask":0.035913354780727054,"reasoningCostPerTask":0.025833286911049913,"answerCostPerTask":0.010080067869677146,"timePerTask":119.60470934036678,"intelligence":37.5766393431307,"coding":42.2462373422111,"agentic":24.0959828178694,"mmmu":0.78092485549133,"priceInput1m":1.25,"priceOutput1m":2.5,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"948892b5-db03-4118-a4a8-ccd51ed871ea\",\"slug\":\"grok-4-3\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Grok 4.3 (high)\",\"short_name\":\"Grok 4.3 (high)\",\"creator_name\":\"SpaceXAI\",\"creator_slug\":\"xai\",\"release_date\":\"2026-04-30\",\"knowledge_cutoff_date\":null,\"intelligence_index\":37.5766393431307,\"coding_index\":42.2462373422111,\"agentic_index\":24.0959828178694,\"mmmu_pro\":0.78092485549133,\"intelligence_index_cost\":{\"total\":287.6431168111509,\"input\":79.55449681115093,\"nonCacheInput\":14.29012875,\"cacheRead\":40.0813422740665,\"cacheWrite\":25.183025787084418,\"output\":208.08862,\"reasoning\":195.56833,\"answer\":12.520290000000001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.13850067515455958,\"input\":0.10258732037383253,\"nonCacheInput\":0.007727402444387977,\"cacheRead\":0.06140205430964321,\"cacheWrite\":0.03345786361980134,\"output\":0.035913354780727054,\"reasoning\":0.025833286911049913,\"answer\":0.010080067869677146},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.016259559894139373},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.011877840266146364},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.0834183715938063},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0010846252893518516},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.007716486547150139},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0014861288667929295},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.007964401785714285},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0009333187239583334},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.007759942187500001}]},\"intelligence_index_time_per_task\":119.60470934036678,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":2.5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":34.63961983440374,"costForScoring":0.13850067515455958,"costPenalty":11.414518904776152,"pointsPerK":250104.33917197672,"costPerQuality":0.003998331269704122,"deltaTop":-28.4158954294657,"costVsTop":0.05036710718461122,"calculated":34.63961983440374,"frontier":false},{"modelKey":"qwen3-5-397b-a17b","sourceId":"0e66bae9-41f1-42fc-9276-ce8cb6f72919","slug":"qwen3-5-397b-a17b","name":"Qwen3.5 397B A17B (Reasoning)","shortName":"Qwen3.5 397B A17B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-02-16","cutoffDate":null,"totalCost":528.0552312,"inputCost":210.809094,"outputCost":317.24613719999996,"reasoningCost":292.3710516,"answerCost":24.875085600000002,"costPerTask":0.3331057741426611,"inputCostPerTask":0.2712415755611569,"outputCostPerTask":0.06186419858150416,"reasoningCostPerTask":0.039844462989320734,"answerCostPerTask":0.022019735592183433,"timePerTask":308.49784137619446,"intelligence":33.6817059499116,"coding":48.2118705784436,"agentic":19.84535395189,"mmmu":0.772832369942197,"priceInput1m":0.6,"priceOutput1m":3.6,"activeParams":17,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"0e66bae9-41f1-42fc-9276-ce8cb6f72919\",\"slug\":\"qwen3-5-397b-a17b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.5 397B A17B (Reasoning)\",\"short_name\":\"Qwen3.5 397B A17B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-02-16\",\"knowledge_cutoff_date\":null,\"intelligence_index\":33.6817059499116,\"coding_index\":48.2118705784436,\"agentic_index\":19.84535395189,\"mmmu_pro\":0.772832369942197,\"intelligence_index_cost\":{\"total\":528.0552312,\"input\":210.809094,\"nonCacheInput\":7.1158014,\"cacheRead\":172.88645939999998,\"cacheWrite\":30.806833199999996,\"output\":317.24613719999996,\"reasoning\":292.3710516,\"answer\":24.875085600000002},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3331057741426611,\"input\":0.2712415755611569,\"nonCacheInput\":0.003801430975634272,\"cacheRead\":0.23921569535798148,\"cacheWrite\":0.02822444922754125,\"output\":0.06186419858150416,\"reasoning\":0.039844462989320734,\"answer\":0.022019735592183433},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0619163259090909},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03330484948453608},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.20746836629213478},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.002095584201388889},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.010065809951343837},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001574916666666667},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.01024905},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0019179866375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.004512885}]},\"intelligence_index_time_per_task\":308.49784137619446,\"price_1m_input_tokens\":0.6,\"price_1m_output_tokens\":3.6,\"activeParams\":17,\"is_open_weights\":true,\"reasoning_model\":true}","quality":33.9129768267484,"costForScoring":0.3331057741426611,"costPenalty":15.225821609306273,"pointsPerK":101808.43281396944,"costPerQuality":0.009822369054901971,"deltaTop":-29.14253843712104,"costVsTop":0.12113712955791303,"calculated":33.9129768267484,"frontier":false},{"modelKey":"mistral-medium-3-5","sourceId":"dd059b25-d82a-4ead-82a4-4adceaaec48b","slug":"mistral-medium-3-5","name":"Mistral Medium 3.5","shortName":"Mistral Medium 3.5","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2026-04-29","cutoffDate":null,"totalCost":1483.4021295000002,"inputCost":799.5959220000001,"outputCost":683.8062075000001,"reasoningCost":630.0631350000001,"answerCost":53.7430725,"costPerTask":1.1962136097409157,"inputCostPerTask":1.005376276112074,"outputCostPerTask":0.19083733362884178,"reasoningCostPerTask":0.13797198974531544,"answerCostPerTask":0.05286534388352635,"timePerTask":169.23907071626127,"intelligence":29.947307563003,"coding":46.9023096129838,"agentic":18.9989965635739,"mmmu":0.648554913294798,"priceInput1m":1.5,"priceOutput1m":7.5,"activeParams":null,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"dd059b25-d82a-4ead-82a4-4adceaaec48b\",\"slug\":\"mistral-medium-3-5\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Mistral Medium 3.5\",\"short_name\":\"Mistral Medium 3.5\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2026-04-29\",\"knowledge_cutoff_date\":null,\"intelligence_index\":29.947307563003,\"coding_index\":46.9023096129838,\"agentic_index\":18.9989965635739,\"mmmu_pro\":0.648554913294798,\"intelligence_index_cost\":{\"total\":1483.4021295000002,\"input\":799.5959220000001,\"nonCacheInput\":19.505827500000002,\"cacheRead\":0,\"cacheWrite\":780.0900945000001,\"output\":683.8062075000001,\"reasoning\":630.0631350000001,\"answer\":53.7430725},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.1962136097409157,\"input\":1.005376276112074,\"nonCacheInput\":0.01079570871477184,\"cacheRead\":0,\"cacheWrite\":0.994580567397302,\"output\":0.19083733362884178,\"reasoning\":0.13797198974531544,\"answer\":0.05286534388352635},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.20766154545454546},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.17571209793814435},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.7324246067415731},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.006624554253472221},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.025282815396200184},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004542096590909091},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.03018673392857143},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0018108431875000002},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.01196831625}]},\"intelligence_index_time_per_task\":169.23907071626127,\"price_1m_input_tokens\":1.5,\"price_1m_output_tokens\":7.5,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":true}","quality":31.949537913186898,"costForScoring":1.1962136097409157,"costPenalty":20.77808739224522,"pointsPerK":26708.89016227357,"costPerQuality":0.03744071707676213,"deltaTop":-31.10597735068254,"costVsTop":0.43501462379353545,"calculated":31.949537913186898,"frontier":false},{"modelKey":"claude-4-5-haiku-reasoning","sourceId":"a6340098-d7ae-462d-b372-0a0a67fc44b4","slug":"claude-4-5-haiku-reasoning","name":"Claude 4.5 Haiku (Reasoning)","shortName":"Claude 4.5 Haiku","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2025-10-15","cutoffDate":"2025-07-01","totalCost":539.0420164053902,"inputCost":98.37391640539013,"outputCost":440.66810000000004,"reasoningCost":402.01882500000005,"answerCost":38.649274999999996,"costPerTask":0.23747351037813688,"inputCostPerTask":0.11978604846157734,"outputCostPerTask":0.11768746191655952,"reasoningCostPerTask":0.08803767257421066,"answerCostPerTask":0.02964978934234885,"timePerTask":215.41200433446505,"intelligence":29.5762345971708,"coding":43.8921833818837,"agentic":16.4030549828179,"mmmu":0.585549132947977,"priceInput1m":1,"priceOutput1m":5,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"a6340098-d7ae-462d-b372-0a0a67fc44b4\",\"slug\":\"claude-4-5-haiku-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude 4.5 Haiku (Reasoning)\",\"short_name\":\"Claude 4.5 Haiku\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2025-10-15\",\"knowledge_cutoff_date\":\"2025-07-01\",\"intelligence_index\":29.5762345971708,\"coding_index\":43.8921833818837,\"agentic_index\":16.4030549828179,\"mmmu_pro\":0.585549132947977,\"intelligence_index_cost\":{\"total\":539.0420164053902,\"input\":98.37391640539013,\"nonCacheInput\":13.03874,\"cacheRead\":22.698606182139986,\"cacheWrite\":62.63657022325014,\"output\":440.66810000000004,\"reasoning\":402.01882500000005,\"answer\":38.649274999999996},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.23747351037813688,\"input\":0.11978604846157734,\"nonCacheInput\":0.007056618425483764,\"cacheRead\":0.03167014784989213,\"cacheWrite\":0.08105928218620145,\"output\":0.11768746191655952,\"reasoning\":0.08803767257421066,\"answer\":0.02964978934234885},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03610975046033978},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.01797169438884642},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.13949826503581345},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.004220961805555556},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.015560394925857276},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004681968434343434},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.010299601785714286},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0015466872916666664},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0075841862500000004}]},\"intelligence_index_time_per_task\":215.41200433446505,\"price_1m_input_tokens\":1,\"price_1m_output_tokens\":5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":29.957157653957466,"costForScoring":0.23747351037813688,"costPenalty":13.756151721157575,"pointsPerK":126149.47076099436,"costPerQuality":0.007927104203985309,"deltaTop":-33.09835760991197,"costVsTop":0.08635953389666738,"calculated":29.957157653957466,"frontier":false},{"modelKey":"gpt-oss-120b","sourceId":"f0083258-8646-45b8-8082-7aaf6c2ea82a","slug":"gpt-oss-120b","name":"gpt-oss-120b (high)","shortName":"gpt-oss-120b (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2025-08-05","cutoffDate":"2024-05-31","totalCost":96.276024,"inputCost":43.8453252,"outputCost":52.4306988,"reasoningCost":48.8940852,"answerCost":3.5366136,"costPerTask":0.06067164425252872,"inputCostPerTask":0.03929974221734161,"outputCostPerTask":0.02137190203518711,"reasoningCostPerTask":0.01682907062489461,"answerCostPerTask":0.0045428314102924985,"timePerTask":123.72687209378557,"intelligence":23.8309678073278,"coding":30.441115272576,"agentic":13.1731638029782,"mmmu":null,"priceInput1m":0.15,"priceOutput1m":0.6,"activeParams":5.1,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"f0083258-8646-45b8-8082-7aaf6c2ea82a\",\"slug\":\"gpt-oss-120b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"gpt-oss-120b (high)\",\"short_name\":\"gpt-oss-120b (high)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2025-08-05\",\"knowledge_cutoff_date\":\"2024-05-31\",\"intelligence_index\":23.8309678073278,\"coding_index\":30.441115272576,\"agentic_index\":13.1731638029782,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":96.276024,\"input\":43.8453252,\"nonCacheInput\":1.8105514499999997,\"cacheRead\":29.92352134014615,\"cacheWrite\":12.111252409853849,\"output\":52.4306988,\"reasoning\":48.8940852,\"answer\":3.5366136},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.06067164425252872,\"input\":0.03929974221734161,\"nonCacheInput\":0.0009778510395144515,\"cacheRead\":0.026735284436310798,\"cacheWrite\":0.011586606741516356,\"output\":0.02137190203518711,\"reasoning\":0.01682907062489461,\"answer\":0.0045428314102924985},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.017541052499999998},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.01749044368556701},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.02094808426966292},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0003163763020833333},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.001699512111909175},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00041149266098484846},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0011567745535714285},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00014592798124999997},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0009619801875000001}]},\"intelligence_index_time_per_task\":123.72687209378557,\"price_1m_input_tokens\":0.15,\"price_1m_output_tokens\":0.6,\"activeParams\":5.1,\"is_open_weights\":true,\"reasoning_model\":true}","quality":22.48174896096066,"costForScoring":0.06067164425252872,"costPenalty":7.829857648488408,"pointsPerK":370547.87682012835,"costPerQuality":0.00269870659786676,"deltaTop":-40.57376630290878,"costVsTop":0.02206382897212262,"calculated":22.48174896096066,"frontier":false},{"modelKey":"nova-2-0-pro-reasoning-medium","sourceId":"0d94dc87-12c8-4d4a-8d99-804ce3f17bc2","slug":"nova-2-0-pro-reasoning-medium","name":"Nova 2.0 Pro Preview (medium)","shortName":"Nova 2.0 Pro Preview (medium)","creatorName":"Amazon","creatorSlug":"aws","releaseDate":"2025-11-27","cutoffDate":null,"totalCost":406.77955563472,"inputCost":54.18382563472,"outputCost":352.59573,"reasoningCost":327.90179,"answerCost":24.693939999999998,"costPerTask":0.1728370588534525,"inputCostPerTask":0.05630845599118991,"outputCostPerTask":0.11652860286226255,"reasoningCostPerTask":0.09578375048111509,"answerCostPerTask":0.020744852381147434,"timePerTask":96.74425392465314,"intelligence":21.7654780663193,"coding":33.96145443196,"agentic":6.99762199312715,"mmmu":0.645086705202312,"priceInput1m":1.25,"priceOutput1m":10,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"0d94dc87-12c8-4d4a-8d99-804ce3f17bc2\",\"slug\":\"nova-2-0-pro-reasoning-medium\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Nova 2.0 Pro Preview (medium)\",\"short_name\":\"Nova 2.0 Pro Preview (medium)\",\"creator_name\":\"Amazon\",\"creator_slug\":\"aws\",\"release_date\":\"2025-11-27\",\"knowledge_cutoff_date\":null,\"intelligence_index\":21.7654780663193,\"coding_index\":33.96145443196,\"agentic_index\":6.99762199312715,\"mmmu_pro\":0.645086705202312,\"intelligence_index_cost\":{\"total\":406.77955563472,\"input\":54.18382563472,\"nonCacheInput\":14.918130000000001,\"cacheRead\":20.645096334719998,\"cacheWrite\":18.620599300000002,\"output\":352.59573,\"reasoning\":327.90179,\"answer\":24.693939999999998},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.1728370588534525,\"input\":0.05630845599118991,\"nonCacheInput\":0.008001879499885713,\"cacheRead\":0.02654613855341874,\"cacheWrite\":0.02176043793788546,\"output\":0.11652860286226255,\"reasoning\":0.09578375048111509,\"answer\":0.020744852381147434},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.029723459348303026},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.014457227104948454},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.09253358978426966},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0028877481192129627},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0093762687528962},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004181210542929294},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.009118541294642858},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0019202201562499997},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00863879375}]},\"intelligence_index_time_per_task\":96.74425392465314,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":20.908184830468816,"costForScoring":0.1728370588534525,"costPenalty":12.376368673673571,"pointsPerK":120970.49654262366,"costPerQuality":0.008266478427222562,"deltaTop":-42.147330433400626,"costVsTop":0.06285386449582381,"calculated":20.908184830468816,"frontier":false},{"modelKey":"gpt-oss-20b","sourceId":"36f73aaf-d38a-4b56-a2b3-d04d17186910","slug":"gpt-oss-20b","name":"gpt-oss-20b (high)","shortName":"gpt-oss-20b (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2025-08-05","cutoffDate":"2024-05-31","totalCost":29.871728500000003,"inputCost":16.4047679,"outputCost":13.466960600000002,"reasoningCost":12.672229600000001,"answerCost":0.7947310000000001,"costPerTask":0.017842778338181632,"inputCostPerTask":0.013372092423261268,"outputCostPerTask":0.004470685914920368,"reasoningCostPerTask":0.0039160444356494085,"answerCostPerTask":0.0005546414792709588,"timePerTask":103.29901582326632,"intelligence":14.8851031229075,"coding":20.6967852684145,"agentic":3.10310309278351,"mmmu":null,"priceInput1m":0.05,"priceOutput1m":0.2,"activeParams":3.6,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"36f73aaf-d38a-4b56-a2b3-d04d17186910\",\"slug\":\"gpt-oss-20b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"gpt-oss-20b (high)\",\"short_name\":\"gpt-oss-20b (high)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2025-08-05\",\"knowledge_cutoff_date\":\"2024-05-31\",\"intelligence_index\":14.8851031229075,\"coding_index\":20.6967852684145,\"agentic_index\":3.10310309278351,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":29.871728500000003,\"input\":16.4047679,\"nonCacheInput\":0.5929486,\"cacheRead\":11.056508893241961,\"cacheWrite\":4.7553104067580385,\"output\":13.466960600000002,\"reasoning\":12.672229600000001,\"answer\":0.7947310000000001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.017842778338181632,\"input\":0.013372092423261268,\"nonCacheInput\":0.00031980788986843704,\"cacheRead\":0.009106739168599914,\"cacheWrite\":0.003945545364792916,\"output\":0.004470685914920368,\"reasoning\":0.0039160444356494085,\"answer\":0.0005546414792709588},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.010216165113636363},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0030964631443298972},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.0030528154494382023},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00007313619791666667},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0003929568610982391},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0001418271464646465},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0004809708482142858},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00005400070208333333},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.000334442875}]},\"intelligence_index_time_per_task\":103.29901582326632,\"price_1m_input_tokens\":0.05,\"price_1m_output_tokens\":0.2,\"activeParams\":3.6,\"is_open_weights\":true,\"reasoning_model\":true}","quality":12.894997161368506,"costForScoring":0.017842778338181632,"costPenalty":2.5146248025276012,"pointsPerK":722701.191314729,"costPerQuality":0.0013836977329189295,"deltaTop":-50.16051810250093,"costVsTop":0.006488698542642937,"calculated":12.894997161368506,"frontier":true}]}