{"run":{"id":816,"source_url":"https://artificialanalysis.ai/models","status":"success","started_at":"2026-07-09T14:00:40.455Z","completed_at":"2026-07-09T14:00:45.506Z","duration_ms":5051,"http_status":200,"html_bytes":1331544,"html_sha256":"9b743b4ea0d06af4ebe4b84d4db2995d029ca714d8b7e1b549b5fa1cef9bef4f","html_gzip_bytes":147376,"raw_html_encoding":"gzip-base64-chunks","parser_version":"aa-next-rsc-manifest-aes-gcm-v4","model_count":551,"result_count":551,"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":285.50036960891265,"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\":285.50036960891265,\"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":285.50036960891265,"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\":285.50036960891265,\"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":413.0605882713055,"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\":413.0605882713055,\"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":230.62605285893787,"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\":230.62605285893787,\"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":157.70373921415262,"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\":157.70373921415262,\"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":492.74882352907014,"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\":492.74882352907014,\"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":"claude-opus-4-7","sourceId":"e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2","slug":"claude-opus-4-7","name":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","shortName":"Claude Opus 4.7 (max)","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2026-04-16","cutoffDate":"2026-01-01","totalCost":3737.818042898671,"inputCost":1236.1138178986712,"outputCost":2501.704225,"reasoningCost":2184.9446,"answerCost":316.75962499999997,"costPerTask":1.9733096609430143,"inputCostPerTask":1.1866547500954012,"outputCostPerTask":0.7866549108476135,"reasoningCostPerTask":0.5427368701412603,"answerCostPerTask":0.24391804070635303,"timePerTask":362.75454940338983,"intelligence":53.5296569524586,"coding":73.6020079067832,"agentic":44.3863264604811,"mmmu":0.788439306358382,"priceInput1m":5,"priceOutput1m":25,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2\",\"slug\":\"claude-opus-4-7\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)\",\"short_name\":\"Claude Opus 4.7 (max)\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2026-04-16\",\"knowledge_cutoff_date\":\"2026-01-01\",\"intelligence_index\":53.5296569524586,\"coding_index\":73.6020079067832,\"agentic_index\":44.3863264604811,\"mmmu_pro\":0.788439306358382,\"intelligence_index_cost\":{\"total\":3737.818042898671,\"input\":1236.1138178986712,\"nonCacheInput\":87.44887500000002,\"cacheRead\":569.4169462696807,\"cacheWrite\":579.2479966289904,\"output\":2501.704225,\"reasoning\":2184.9446,\"answer\":316.75962499999997},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.9733096609430143,\"input\":1.1866547500954012,\"nonCacheInput\":0.047228405896136576,\"cacheRead\":0.5652371768671622,\"cacheWrite\":0.574189167332102,\"output\":0.7866549108476135,\"reasoning\":0.5427368701412603,\"answer\":0.24391804070635303},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.8168694598914165},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.18211703890154657},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.6927487782033731},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0195271412037037},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.08938369439295644},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.020504326073232326},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.09888403571428571},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0044414709375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.048833715624999996}]},\"intelligence_index_time_per_task\":362.75454940338983,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":25,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":57.17266377324097,"costForScoring":1.9733096609430143,"costPenalty":22.951952421129764,"pointsPerK":28972.98123291964,"costPerQuality":0.03451491553322726,"deltaTop":-5.882851490628468,"costVsTop":0.7176131025370934,"calculated":57.17266377324097,"frontier":false},{"modelKey":"gpt-5-5-high","sourceId":"b13c1257-d746-4027-8fc8-4892dc14701c","slug":"gpt-5-5-high","name":"GPT-5.5 (high)","shortName":"GPT-5.5 (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-04-23","cutoffDate":null,"totalCost":1654.5879017149896,"inputCost":369.6990917149898,"outputCost":1284.88881,"reasoningCost":1166.03919,"answerCost":118.84961999999999,"costPerTask":0.6095853425706699,"inputCostPerTask":0.30729151826050716,"outputCostPerTask":0.30229382431016266,"reasoningCostPerTask":0.20798050125698342,"answerCostPerTask":0.09431332305317924,"timePerTask":150.31976908680954,"intelligence":53.1275095349873,"coding":71.5680919683729,"agentic":43.4581786941581,"mmmu":0.810982658959538,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"b13c1257-d746-4027-8fc8-4892dc14701c\",\"slug\":\"gpt-5-5-high\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.5 (high)\",\"short_name\":\"GPT-5.5 (high)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-04-23\",\"knowledge_cutoff_date\":null,\"intelligence_index\":53.1275095349873,\"coding_index\":71.5680919683729,\"agentic_index\":43.4581786941581,\"mmmu_pro\":0.810982658959538,\"intelligence_index_cost\":{\"total\":1654.5879017149896,\"input\":369.6990917149898,\"nonCacheInput\":62.498355,\"cacheRead\":94.11916036500112,\"cacheWrite\":213.08157634998864,\"output\":1284.88881,\"reasoning\":1166.03919,\"answer\":118.84961999999999},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.6095853425706699,\"input\":0.30729151826050716,\"nonCacheInput\":0.03167666193854673,\"cacheRead\":0.08522646482130583,\"cacheWrite\":0.19038839150065467,\"output\":0.30229382431016266,\"reasoning\":0.20798050125698342,\"answer\":0.09431332305317924},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.19907988955952322},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.12569539702430974},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.14147101191034198},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00941989583333333},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.02833371901065802},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0056100631313131324},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.05750148214285715},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.010735052708333331},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.03173883125}]},\"intelligence_index_time_per_task\":150.31976908680954,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":56.051260065839436,"costForScoring":0.6095853425706699,"costPenalty":17.850345158820573,"pointsPerK":91949.81596746866,"costPerQuality":0.010875497568736783,"deltaTop":-7.004255198030002,"costVsTop":0.22168159291037293,"calculated":56.051260065839436,"frontier":false},{"modelKey":"gpt-5-4","sourceId":"a89c4b28-2d8c-456e-88ea-255fb51fd2b6","slug":"gpt-5-4","name":"GPT-5.4 (xhigh)","shortName":"GPT-5.4 (xhigh)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-03-05","cutoffDate":"2025-08-31","totalCost":2131.7653830456115,"inputCost":490.3601730456113,"outputCost":1641.4052100000001,"reasoningCost":1552.897455,"answerCost":88.507755,"costPerTask":0.8868298551068886,"inputCostPerTask":0.397021492182344,"outputCostPerTask":0.48980836292454466,"reasoningCostPerTask":0.41763290874324654,"answerCostPerTask":0.07217545418129814,"timePerTask":205.64603422623512,"intelligence":51.4012420630147,"coding":71.0505097794423,"agentic":41.0770927835052,"mmmu":0.784393063583815,"priceInput1m":2.5,"priceOutput1m":15,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"a89c4b28-2d8c-456e-88ea-255fb51fd2b6\",\"slug\":\"gpt-5-4\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.4 (xhigh)\",\"short_name\":\"GPT-5.4 (xhigh)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-03-05\",\"knowledge_cutoff_date\":\"2025-08-31\",\"intelligence_index\":51.4012420630147,\"coding_index\":71.0505097794423,\"agentic_index\":41.0770927835052,\"mmmu_pro\":0.784393063583815,\"intelligence_index_cost\":{\"total\":2131.7653830456115,\"input\":490.3601730456113,\"nonCacheInput\":29.68895,\"cacheRead\":157.96204493937654,\"cacheWrite\":302.7091781062348,\"output\":1641.4052100000001,\"reasoning\":1552.897455,\"answer\":88.507755},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.8868298551068886,\"input\":0.397021492182344,\"nonCacheInput\":0.01585308402087614,\"cacheRead\":0.1295218243162152,\"cacheWrite\":0.2516465838452526,\"output\":0.48980836292454466,\"reasoning\":0.41763290874324654,\"answer\":0.07217545418129814},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.32943853624619635},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.16495218559778185},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.2317642437543334},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.016931007667824072},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.031158365529425396},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.005732763573232324},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.07644399107142856},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.013626633541666665},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.016782128125}]},\"intelligence_index_time_per_task\":205.64603422623512,\"price_1m_input_tokens\":2.5,\"price_1m_output_tokens\":15,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":54.50961487532073,"costForScoring":0.8868298551068886,"costPenalty":19.47840305202405,"pointsPerK":61465.69667385719,"costPerQuality":0.016269237218705823,"deltaTop":-8.54590038854871,"costVsTop":0.3225042355702294,"calculated":54.50961487532073,"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":189.8668446068344,"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\":189.8668446068344,\"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":"gpt-5-5-medium","sourceId":"6b79f899-e3c0-45f6-923c-243faccdb2fc","slug":"gpt-5-5-medium","name":"GPT-5.5 (medium)","shortName":"GPT-5.5 (medium)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-04-23","cutoffDate":null,"totalCost":869.9057044386701,"inputCost":230.91893443867002,"outputCost":638.9867700000001,"reasoningCost":540.2006700000001,"answerCost":98.7861,"costPerTask":0.34412566885902274,"inputCostPerTask":0.1901529667172091,"outputCostPerTask":0.1539727021418136,"reasoningCostPerTask":0.07859751210021937,"answerCostPerTask":0.07537519004159425,"timePerTask":81.51461637103841,"intelligence":50.4090068672092,"coding":71.5069704535997,"agentic":37.7910652920962,"mmmu":0.811560693641619,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"6b79f899-e3c0-45f6-923c-243faccdb2fc\",\"slug\":\"gpt-5-5-medium\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.5 (medium)\",\"short_name\":\"GPT-5.5 (medium)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-04-23\",\"knowledge_cutoff_date\":null,\"intelligence_index\":50.4090068672092,\"coding_index\":71.5069704535997,\"agentic_index\":37.7910652920962,\"mmmu_pro\":0.811560693641619,\"intelligence_index_cost\":{\"total\":869.9057044386701,\"input\":230.91893443867002,\"nonCacheInput\":61.61127,\"cacheRead\":58.27104672903666,\"cacheWrite\":111.03661770963336,\"output\":638.9867700000001,\"reasoning\":540.2006700000001,\"answer\":98.7861},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.34412566885902274,\"input\":0.1901529667172091,\"nonCacheInput\":0.03226918379648743,\"cacheRead\":0.05484648130070874,\"cacheWrite\":0.10303730162001297,\"output\":0.1539727021418136,\"reasoning\":0.07859751210021937,\"answer\":0.07537519004159425},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.10673988393921155},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.07856767417894843},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.08074725635695658},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.005184007523148148},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.015782593547265987},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0032756423611111115},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.018349776785714287},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.004662834166666667},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.030816000000000003}]},\"intelligence_index_time_per_task\":81.51461637103841,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":53.235680870968366,"costForScoring":0.34412566885902274,"costPenalty":15.367170685176248,"pointsPerK":154698.37239249164,"costPerQuality":0.006464192121316303,"deltaTop":-9.819834392901072,"costVsTop":0.12514462062409534,"calculated":53.235680870968366,"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":"claude-sonnet-4-6-adaptive","sourceId":"df8d14e0-3997-4e4d-b4ad-9c047acc9c69","slug":"claude-sonnet-4-6-adaptive","name":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","shortName":"Claude Sonnet 4.6 (max)","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2026-02-17","cutoffDate":null,"totalCost":3355.8518741364983,"inputCost":404.68930913649876,"outputCost":2951.1625649999996,"reasoningCost":2801.87598,"answerCost":149.286585,"costPerTask":1.1355620170084484,"inputCostPerTask":0.38037126130138377,"outputCostPerTask":0.7551907557070645,"reasoningCostPerTask":0.6509368361058735,"answerCostPerTask":0.10425391960119107,"timePerTask":732.1537451623622,"intelligence":47.2100024360452,"coding":63.0271188791788,"agentic":40.7694879725086,"mmmu":0.732947976878613,"priceInput1m":3,"priceOutput1m":15,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"df8d14e0-3997-4e4d-b4ad-9c047acc9c69\",\"slug\":\"claude-sonnet-4-6-adaptive\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)\",\"short_name\":\"Claude Sonnet 4.6 (max)\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2026-02-17\",\"knowledge_cutoff_date\":null,\"intelligence_index\":47.2100024360452,\"coding_index\":63.0271188791788,\"agentic_index\":40.7694879725086,\"mmmu_pro\":0.732947976878613,\"intelligence_index_cost\":{\"total\":3355.8518741364983,\"input\":404.68930913649876,\"nonCacheInput\":41.495244,\"cacheRead\":205.4320787924784,\"cacheWrite\":157.76198634402036,\"output\":2951.1625649999996,\"reasoning\":2801.87598,\"answer\":149.286585},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.1355620170084484,\"input\":0.38037126130138377,\"nonCacheInput\":0.021565057427932008,\"cacheRead\":0.19728787824191174,\"cacheWrite\":0.16151832563154006,\"output\":0.7551907557070645,\"reasoning\":0.6509368361058735,\"answer\":0.10425391960119107},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.3228937169982244},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.07139628081569996},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.333949808669228},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.01881645746527778},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.11432665680027804},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.025861985795454547},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.2187486857142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00549986725},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.024068557499999997}]},\"intelligence_index_time_per_task\":732.1537451623622,\"price_1m_input_tokens\":3,\"price_1m_output_tokens\":15,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":50.3355364292442,"costForScoring":1.1355620170084484,"costPenalty":20.55210857542165,"pointsPerK":44326.541109440535,"costPerQuality":0.022559847327835444,"deltaTop":-12.719978834625238,"costVsTop":0.4129580867501996,"calculated":50.3355364292442,"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":93.91740725178664,"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\":93.91740725178664,\"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":435.60796650458235,"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\":435.60796650458235,\"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":248.61036535670576,"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\":248.61036535670576,\"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":88.01367633615352,"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\":88.01367633615352,\"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":890.00139424875,"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\":890.00139424875,\"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":"gpt-5-5-low","sourceId":"c77cfe51-f4a0-4692-9dee-5061ef667f23","slug":"gpt-5-5-low","name":"GPT-5.5 (low)","shortName":"GPT-5.5 (low)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-04-23","cutoffDate":null,"totalCost":358.1707625538829,"inputCost":154.2788825538829,"outputCost":203.89188000000001,"reasoningCost":138.69840000000002,"answerCost":65.19348,"costPerTask":0.19300784226111395,"inputCostPerTask":0.12880557088976902,"outputCostPerTask":0.06420227137134495,"reasoningCostPerTask":0.016734277970007316,"answerCostPerTask":0.047467993401337644,"timePerTask":34.71166453789992,"intelligence":43.4604883103599,"coding":60.9021708974893,"agentic":30.4173711340206,"mmmu":0.790173410404624,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"c77cfe51-f4a0-4692-9dee-5061ef667f23\",\"slug\":\"gpt-5-5-low\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.5 (low)\",\"short_name\":\"GPT-5.5 (low)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-04-23\",\"knowledge_cutoff_date\":null,\"intelligence_index\":43.4604883103599,\"coding_index\":60.9021708974893,\"agentic_index\":30.4173711340206,\"mmmu_pro\":0.790173410404624,\"intelligence_index_cost\":{\"total\":358.1707625538829,\"input\":154.2788825538829,\"nonCacheInput\":59.498810000000006,\"cacheRead\":24.4365713829019,\"cacheWrite\":70.343501170981,\"output\":203.89188000000001,\"reasoning\":138.69840000000002,\"answer\":65.19348},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.19300784226111395,\"input\":0.12880557088976902,\"nonCacheInput\":0.032056295655332655,\"cacheRead\":0.025589792022160544,\"cacheWrite\":0.07115948321227582,\"output\":0.06420227137134495,\"reasoning\":0.016734277970007316,\"answer\":0.047467993401337644},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.030223592294206476},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.05951196348584903},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.05512474761798142},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00261470630787037},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.004794213681649675},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001337299558080808},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.007844736607142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0013847014583333334},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.03017188125}]},\"intelligence_index_time_per_task\":34.71166453789992,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":44.92667678062327,"costForScoring":0.19300784226111395,"costPenalty":12.855749555442168,"pointsPerK":232771.25040257923,"costPerQuality":0.004296063187659534,"deltaTop":-18.12883848324617,"costVsTop":0.07018916454946991,"calculated":44.92667678062327,"frontier":false},{"modelKey":"kimi-k2-7-code","sourceId":"8d0cb231-7303-452c-9923-a9620b948475","slug":"kimi-k2-7-code","name":"Kimi K2.7 Code","shortName":"Kimi K2.7 Code","creatorName":"Kimi","creatorSlug":"kimi","releaseDate":"2026-06-12","cutoffDate":null,"totalCost":524.5600213600001,"inputCost":109.77084536000001,"outputCost":414.789176,"reasoningCost":390.508976,"answerCost":24.2802,"costPerTask":0.17772103999963917,"inputCostPerTask":0.10685671482364328,"outputCostPerTask":0.07086432517599595,"reasoningCostPerTask":0.05060162427591036,"answerCostPerTask":0.02026270090008558,"timePerTask":362.0882275499435,"intelligence":41.9493685067994,"coding":60.761721459287,"agentic":29.5911099656357,"mmmu":null,"priceInput1m":0.95,"priceOutput1m":4,"activeParams":32,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"8d0cb231-7303-452c-9923-a9620b948475\",\"slug\":\"kimi-k2-7-code\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Kimi K2.7 Code\",\"short_name\":\"Kimi K2.7 Code\",\"creator_name\":\"Kimi\",\"creator_slug\":\"kimi\",\"release_date\":\"2026-06-12\",\"knowledge_cutoff_date\":null,\"intelligence_index\":41.9493685067994,\"coding_index\":60.761721459287,\"agentic_index\":29.5911099656357,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":524.5600213600001,\"input\":109.77084536000001,\"nonCacheInput\":11.3309407,\"cacheRead\":74.20090736,\"cacheWrite\":24.2389973,\"output\":414.789176,\"reasoning\":390.508976,\"answer\":24.2802},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.17772103999963917,\"input\":0.10685671482364328,\"nonCacheInput\":0.0061435829015183225,\"cacheRead\":0.07816364035064885,\"cacheWrite\":0.02254949157147608,\"output\":0.07086432517599595,\"reasoning\":0.05060162427591036,\"answer\":0.02026270090008558},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.05701005767424243},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.018669265257731955},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.05977746024344569},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0019855123263888886},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.013087821385542169},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.002475086868686869},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.016018989732142858},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.002654034042708333},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00604281246875}]},\"intelligence_index_time_per_task\":362.0882275499435,\"price_1m_input_tokens\":0.95,\"price_1m_output_tokens\":4,\"activeParams\":32,\"is_open_weights\":true,\"reasoning_model\":true}","quality":44.100733310574036,"costForScoring":0.17772103999963917,"costPenalty":12.497388460092054,"pointsPerK":248145.82061113062,"costPerQuality":0.004029888545119203,"deltaTop":-18.954781953295402,"costVsTop":0.06462997137474762,"calculated":44.100733310574036,"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":420.70598657280544,"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\":420.70598657280544,\"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":343.9408768912057,"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\":343.9408768912057,\"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":470.9381509422239,"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\":470.9381509422239,\"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":"glm-5-1","sourceId":"5aa1c578-af76-4b91-8699-cdd43582b3af","slug":"glm-5-1","name":"GLM-5.1 (Reasoning)","shortName":"GLM-5.1","creatorName":"Z AI","creatorSlug":"zai","releaseDate":"2026-04-07","cutoffDate":null,"totalCost":658.9766025176309,"inputCost":121.77778211763085,"outputCost":537.1988204,"reasoningCost":496.815,"answerCost":40.383820400000005,"costPerTask":0.22589274187412675,"inputCostPerTask":0.10977664077167572,"outputCostPerTask":0.11611610110245105,"reasoningCostPerTask":0.07350310437632471,"answerCostPerTask":0.04261299672612631,"timePerTask":289.3287833003676,"intelligence":40.1570857627689,"coding":55.7818352059925,"agentic":29.8734639175258,"mmmu":null,"priceInput1m":1.4,"priceOutput1m":4.4,"activeParams":40,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"5aa1c578-af76-4b91-8699-cdd43582b3af\",\"slug\":\"glm-5-1\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GLM-5.1 (Reasoning)\",\"short_name\":\"GLM-5.1\",\"creator_name\":\"Z AI\",\"creator_slug\":\"zai\",\"release_date\":\"2026-04-07\",\"knowledge_cutoff_date\":null,\"intelligence_index\":40.1570857627689,\"coding_index\":55.7818352059925,\"agentic_index\":29.8734639175258,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":658.9766025176309,\"input\":121.77778211763085,\"nonCacheInput\":16.760071999999997,\"cacheRead\":61.23271825036489,\"cacheWrite\":43.78499186726596,\"output\":537.1988204,\"reasoning\":496.815,\"answer\":40.383820400000005},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.22589274187412675,\"input\":0.10977664077167572,\"nonCacheInput\":0.009062530070390146,\"cacheRead\":0.05921803127056866,\"cacheWrite\":0.041496079430716905,\"output\":0.11611610110245105,\"reasoning\":0.07350310437632471,\"answer\":0.04261299672612631},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.06745520313085343},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.028499039575232796},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.061759051534332116},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.006756276736111111},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.02085486585959222},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004896159217171719},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.024431968750000005},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0012831099458333335},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.009957067125}]},\"intelligence_index_time_per_task\":289.3287833003676,\"price_1m_input_tokens\":1.4,\"price_1m_output_tokens\":4.4,\"activeParams\":40,\"is_open_weights\":true,\"reasoning_model\":true}","quality":41.9374616287624,"costForScoring":0.22589274187412675,"costPenalty":13.539022768935546,"pointsPerK":185652.0987829305,"costPerQuality":0.005386419041614107,"deltaTop":-21.11805363510704,"costVsTop":0.08214807566463547,"calculated":41.9374616287624,"frontier":false},{"modelKey":"gpt-5-4-nano","sourceId":"d4fc3f33-f2b0-4da1-88ee-f1f82bd4de31","slug":"gpt-5-4-nano","name":"GPT-5.4 nano (xhigh)","shortName":"GPT-5.4 nano (xhigh)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-03-17","cutoffDate":"2025-08-31","totalCost":271.56828239211177,"inputCost":44.076433642111795,"outputCost":227.49184875,"reasoningCost":218.58745,"answerCost":8.90439875,"costPerTask":0.12724692856512554,"inputCostPerTask":0.038888387352215774,"outputCostPerTask":0.08835854121290979,"reasoningCostPerTask":0.07936746247587266,"answerCostPerTask":0.008991078737037089,"timePerTask":435.2593129198025,"intelligence":38.2417263132715,"coding":56.0744382022472,"agentic":27.5439759450172,"mmmu":0.653757225433526,"priceInput1m":0.2,"priceOutput1m":1.25,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"d4fc3f33-f2b0-4da1-88ee-f1f82bd4de31\",\"slug\":\"gpt-5-4-nano\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.4 nano (xhigh)\",\"short_name\":\"GPT-5.4 nano (xhigh)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-03-17\",\"knowledge_cutoff_date\":\"2025-08-31\",\"intelligence_index\":38.2417263132715,\"coding_index\":56.0744382022472,\"agentic_index\":27.5439759450172,\"mmmu_pro\":0.653757225433526,\"intelligence_index_cost\":{\"total\":271.56828239211177,\"input\":44.076433642111795,\"nonCacheInput\":2.359461,\"cacheRead\":19.38649726198758,\"cacheWrite\":22.33047538012422,\"output\":227.49184875,\"reasoning\":218.58745,\"answer\":8.90439875},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.12724692856512554,\"input\":0.038888387352215774,\"nonCacheInput\":0.001262924529127332,\"cacheRead\":0.017586799911959147,\"cacheWrite\":0.020038662911129296,\"output\":0.08835854121290979,\"reasoning\":0.07936746247587266,\"answer\":0.008991078737037089},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03726191252658153},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.016686110608257372},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.053347416402645315},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0016463993778935183},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.005360651995481928},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001331692361111111},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.008891175803571428},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0012436362708333334},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00147793321875}]},\"intelligence_index_time_per_task\":435.2593129198025,\"price_1m_input_tokens\":0.2,\"price_1m_output_tokens\":1.25,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":40.62004682017863,"costForScoring":0.12724692856512554,"costPenalty":11.046473083108314,"pointsPerK":319222.2183924,"costPerQuality":0.0031326140299255804,"deltaTop":-22.43546844369081,"costVsTop":0.046274573627890746,"calculated":40.62004682017863,"frontier":false},{"modelKey":"qwen3-6-plus","sourceId":"f371ad68-6947-4767-a78f-1f6c81f96b93","slug":"qwen3-6-plus","name":"Qwen3.6 Plus","shortName":"Qwen3.6 Plus","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-04-02","cutoffDate":null,"totalCost":525.5754352045657,"inputCost":221.74430620456565,"outputCost":303.83112900000003,"reasoningCost":268.50507600000003,"answerCost":35.326053,"costPerTask":0.31383547131763045,"inputCostPerTask":0.24962649155913616,"outputCostPerTask":0.0642089797584943,"reasoningCostPerTask":0.04006684933570125,"answerCostPerTask":0.02414213042279304,"timePerTask":384.77335892828216,"intelligence":39.5608411628461,"coding":54.5290608961021,"agentic":27.5522817869416,"mmmu":0.779768786127168,"priceInput1m":0.5,"priceOutput1m":3,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"f371ad68-6947-4767-a78f-1f6c81f96b93\",\"slug\":\"qwen3-6-plus\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.6 Plus\",\"short_name\":\"Qwen3.6 Plus\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-04-02\",\"knowledge_cutoff_date\":null,\"intelligence_index\":39.5608411628461,\"coding_index\":54.5290608961021,\"agentic_index\":27.5522817869416,\"mmmu_pro\":0.779768786127168,\"intelligence_index_cost\":{\"total\":525.5754352045657,\"input\":221.74430620456565,\"nonCacheInput\":5.997744,\"cacheRead\":3.3574483409073355,\"cacheWrite\":212.3891138636583,\"output\":303.83112900000003,\"reasoning\":268.50507600000003,\"answer\":35.326053},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.31383547131763045,\"input\":0.24962649155913616,\"nonCacheInput\":0.00323811837463273,\"cacheRead\":0.0038640061682049887,\"cacheWrite\":0.2425243670162984,\"output\":0.0642089797584943,\"reasoning\":0.04006684933570125,\"answer\":0.02414213042279304},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.08580120263900257},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.04869537152745481},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.15058359225304283},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0012452022569444444},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.011715738357275254},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001913736426767677},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.009550649107142858},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0009692556249999998},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.003360723125}]},\"intelligence_index_time_per_task\":384.77335892828216,\"price_1m_input_tokens\":0.5,\"price_1m_output_tokens\":3,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":40.547394615296604,"costForScoring":0.31383547131763045,"costPenalty":14.967020282467862,"pointsPerK":129199.52752650734,"costPerQuality":0.007739966384899001,"deltaTop":-22.508120648572834,"costVsTop":0.11412929795864386,"calculated":40.547394615296604,"frontier":false},{"modelKey":"grok-build-0-1-06-16","sourceId":"0b7efa66-2115-49e0-a1b7-a2ba225fe9f6","slug":"grok-build-0-1-06-16","name":"Grok Build 0.1 0616","shortName":"Grok Build 0.1 0616","creatorName":"SpaceXAI","creatorSlug":"xai","releaseDate":null,"cutoffDate":null,"totalCost":375.00657010387033,"inputCost":106.35369210387037,"outputCost":268.652878,"reasoningCost":248.68659,"answerCost":19.966288,"costPerTask":0.21191134533727934,"inputCostPerTask":0.14150261859618377,"outputCostPerTask":0.07040872674109558,"reasoningCostPerTask":0.0501466763292964,"answerCostPerTask":0.02026205041179917,"timePerTask":285.36568686849967,"intelligence":39.8026227264218,"coding":51.4504438895825,"agentic":28.0356116838488,"mmmu":0.765317919075144,"priceInput1m":1,"priceOutput1m":2,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"0b7efa66-2115-49e0-a1b7-a2ba225fe9f6\",\"slug\":\"grok-build-0-1-06-16\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Grok Build 0.1 0616\",\"short_name\":\"Grok Build 0.1 0616\",\"creator_name\":\"SpaceXAI\",\"creator_slug\":\"xai\",\"release_date\":null,\"knowledge_cutoff_date\":null,\"intelligence_index\":39.8026227264218,\"coding_index\":51.4504438895825,\"agentic_index\":28.0356116838488,\"mmmu_pro\":0.765317919075144,\"intelligence_index_cost\":{\"total\":375.00657010387033,\"input\":106.35369210387037,\"nonCacheInput\":12.47759,\"cacheRead\":71.29844747403241,\"cacheWrite\":22.577654629837944,\"output\":268.652878,\"reasoning\":248.68659,\"answer\":19.966288},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.21191134533727934,\"input\":0.14150261859618377,\"nonCacheInput\":0.00624681371363317,\"cacheRead\":0.1066978907736566,\"cacheWrite\":0.028557914108894,\"output\":0.07040872674109558,\"reasoning\":0.0501466763292964,\"answer\":0.02026205041179917},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.023776779141019506},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.018682867790116246},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.14236086803376272},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0010687777777777777},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.007814724281742354},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001439031881313131},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.008627033035714285},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0017241252708333334},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.006417138125}]},\"intelligence_index_time_per_task\":285.36568686849967,\"price_1m_input_tokens\":1,\"price_1m_output_tokens\":2,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":39.7628927666177,"costForScoring":0.21191134533727934,"costPenalty":13.261542086479176,"pointsPerK":187639.28237693384,"costPerQuality":0.00532937446430422,"deltaTop":-23.292622497251735,"costVsTop":0.07706360588009405,"calculated":39.7628927666177,"frontier":false},{"modelKey":"qwen3-6-27b","sourceId":"8c29d66d-bf98-4ea3-8572-5409353ecc66","slug":"qwen3-6-27b","name":"Qwen3.6 27B (Reasoning)","shortName":"Qwen3.6 27B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-04-22","cutoffDate":null,"totalCost":668.077305,"inputCost":153.2220198,"outputCost":514.8552852,"reasoningCost":486.8075664,"answerCost":28.0477188,"costPerTask":0.26527574515202695,"inputCostPerTask":0.1621693887100847,"outputCostPerTask":0.10310635644194222,"reasoningCostPerTask":0.07795802130651305,"answerCostPerTask":0.02514833513542915,"timePerTask":402.4801605953756,"intelligence":37.0516798775037,"coding":53.7210431405188,"agentic":27.0255773195876,"mmmu":0.746242774566474,"priceInput1m":0.6,"priceOutput1m":3.6,"activeParams":null,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"8c29d66d-bf98-4ea3-8572-5409353ecc66\",\"slug\":\"qwen3-6-27b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.6 27B (Reasoning)\",\"short_name\":\"Qwen3.6 27B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-04-22\",\"knowledge_cutoff_date\":null,\"intelligence_index\":37.0516798775037,\"coding_index\":53.7210431405188,\"agentic_index\":27.0255773195876,\"mmmu_pro\":0.746242774566474,\"intelligence_index_cost\":{\"total\":668.077305,\"input\":153.2220198,\"nonCacheInput\":7.919981399999999,\"cacheRead\":136.3870116,\"cacheWrite\":8.9150268,\"output\":514.8552852,\"reasoning\":486.8075664,\"answer\":28.0477188},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.26527574515202695,\"input\":0.1621693887100847,\"nonCacheInput\":0.004337294511975976,\"cacheRead\":0.14875911865652935,\"cacheWrite\":0.009072975541579351,\"output\":0.10310635644194222,\"reasoning\":0.07795802130651305,\"answer\":0.02514833513542915},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.07361866136363636},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.028321644845360826},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.12585472134831457},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.001677878125},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.013502192863762743},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0026341541666666675},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.010913961964285714},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.004251175975},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0045013545}]},\"intelligence_index_time_per_task\":402.4801605953756,\"price_1m_input_tokens\":0.6,\"price_1m_output_tokens\":3.6,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":true}","quality":39.2661001125367,"costForScoring":0.26527574515202695,"costPenalty":14.236975431290187,"pointsPerK":148019.94087334926,"costPerQuality":0.006755846503516934,"deltaTop":-23.78941515133274,"costVsTop":0.0964700848904843,"calculated":39.2661001125367,"frontier":false},{"modelKey":"gpt-5-5-non-reasoning","sourceId":"6f1a7562-6e96-46ac-af4f-6ba5a7a3da96","slug":"gpt-5-5-non-reasoning","name":"GPT-5.5 (Non-reasoning)","shortName":"GPT-5.5 (Non-reasoning)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-04-23","cutoffDate":null,"totalCost":192.91132714075914,"inputCost":126.78526714075915,"outputCost":66.12606,"reasoningCost":0,"answerCost":66.12606,"costPerTask":0.15146641561230662,"inputCostPerTask":0.10387806531058964,"outputCostPerTask":0.047588350301716965,"reasoningCostPerTask":0,"answerCostPerTask":0.047588350301716965,"timePerTask":25.834144057793264,"intelligence":35.3827351786589,"coding":56.4784470800389,"agentic":25.8018109965636,"mmmu":0.713872832369942,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":false,"rawResultJson":"{\"id\":\"6f1a7562-6e96-46ac-af4f-6ba5a7a3da96\",\"slug\":\"gpt-5-5-non-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.5 (Non-reasoning)\",\"short_name\":\"GPT-5.5 (Non-reasoning)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-04-23\",\"knowledge_cutoff_date\":null,\"intelligence_index\":35.3827351786589,\"coding_index\":56.4784470800389,\"agentic_index\":25.8018109965636,\"mmmu_pro\":0.713872832369942,\"intelligence_index_cost\":{\"total\":192.91132714075914,\"input\":126.78526714075915,\"nonCacheInput\":59.49731,\"cacheRead\":20.50146365102676,\"cacheWrite\":46.786493489732386,\"output\":66.12606,\"reasoning\":0,\"answer\":66.12606},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.15146641561230662,\"input\":0.10387806531058964,\"nonCacheInput\":0.0320902418121363,\"cacheRead\":0.02202240499676058,\"cacheWrite\":0.04976541850169276,\"output\":0.047588350301716965,\"reasoning\":0,\"answer\":0.047588350301716965},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.023946177918184517},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03920665010735901},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.04931140742282715},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0022828023726851852},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0012158642261353107},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00047332228535353543},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.005172491071428571},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00011613145833333334},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.029741568750000003}]},\"intelligence_index_time_per_task\":25.834144057793264,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":39.2209977517538,"costForScoring":0.15146641561230662,"costPenalty":11.803163481443018,"pointsPerK":258941.87561778614,"costPerQuality":0.003861870536058295,"deltaTop":-23.83451751211564,"costVsTop":0.055082223833930286,"calculated":39.2209977517538,"frontier":false},{"modelKey":"qwen3-7-plus","sourceId":"a87fce42-eea3-4e45-a96d-fe057814f371","slug":"qwen3-7-plus","name":"Qwen3.7 Plus","shortName":"Qwen3.7 Plus","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-06-01","cutoffDate":null,"totalCost":320.33822171244503,"inputCost":138.64966011244502,"outputCost":181.6885616,"reasoningCost":174.16782880000002,"answerCost":7.520732800000001,"costPerTask":0.21943570508240284,"inputCostPerTask":0.18396074506106305,"outputCostPerTask":0.0354749600213398,"reasoningCostPerTask":0.029495446582286897,"answerCostPerTask":0.005979513439052893,"timePerTask":404.64813110498545,"intelligence":38.9772279786141,"coding":55.8611631294216,"agentic":20.8054719358534,"mmmu":0.804624277456647,"priceInput1m":0.4,"priceOutput1m":1.6,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"a87fce42-eea3-4e45-a96d-fe057814f371\",\"slug\":\"qwen3-7-plus\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.7 Plus\",\"short_name\":\"Qwen3.7 Plus\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-06-01\",\"knowledge_cutoff_date\":null,\"intelligence_index\":38.9772279786141,\"coding_index\":55.8611631294216,\"agentic_index\":20.8054719358534,\"mmmu_pro\":0.804624277456647,\"intelligence_index_cost\":{\"total\":320.33822171244503,\"input\":138.64966011244502,\"nonCacheInput\":5.3356580000000005,\"cacheRead\":0.9068633815265206,\"cacheWrite\":132.4071387309185,\"output\":181.6885616,\"reasoning\":174.16782880000002,\"answer\":7.520732800000001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.21943570508240284,\"input\":0.18396074506106305,\"nonCacheInput\":0.0029128941887433734,\"cacheRead\":0.0012427416852202585,\"cacheWrite\":0.1798051091870994,\"output\":0.0354749600213398,\"reasoning\":0.029495446582286897,\"answer\":0.005979513439052893},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.024802875562017327},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03268704173246111},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.13570673294756067},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0011628359953703704},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.007677949930491196},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001299987878787879},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.012904861785714285},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00036274025},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.002830679}]},\"intelligence_index_time_per_task\":404.64813110498545,\"price_1m_input_tokens\":0.4,\"price_1m_output_tokens\":1.6,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":38.547954347963035,"costForScoring":0.21943570508240284,"costPenalty":13.413072944266474,"pointsPerK":175668.5601073328,"costPerQuality":0.005692538262902616,"deltaTop":-24.507560915906403,"costVsTop":0.07979991191871288,"calculated":38.547954347963035,"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":113.20088956368457,"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\":113.20088956368457,\"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":"claude-4-5-sonnet-thinking","sourceId":"90e078f2-051b-4c63-8919-76618971cb3f","slug":"claude-4-5-sonnet-thinking","name":"Claude 4.5 Sonnet (Reasoning)","shortName":"Claude 4.5 Sonnet","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2025-09-29","cutoffDate":"2025-07-01","totalCost":1132.8540777463882,"inputCost":186.08062774638807,"outputCost":946.7734500000001,"reasoningCost":845.4071100000001,"answerCost":101.36634,"costPerTask":0.41290380463528553,"inputCostPerTask":0.17715751403584135,"outputCostPerTask":0.23574629059944427,"reasoningCostPerTask":0.15747824339018823,"answerCostPerTask":0.07826804720925604,"timePerTask":306.2850398842488,"intelligence":36.4198423016253,"coding":52.0954709391039,"agentic":24.5823573883162,"mmmu":0.68728323699422,"priceInput1m":3,"priceOutput1m":15,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"90e078f2-051b-4c63-8919-76618971cb3f\",\"slug\":\"claude-4-5-sonnet-thinking\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude 4.5 Sonnet (Reasoning)\",\"short_name\":\"Claude 4.5 Sonnet\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2025-09-29\",\"knowledge_cutoff_date\":\"2025-07-01\",\"intelligence_index\":36.4198423016253,\"coding_index\":52.0954709391039,\"agentic_index\":24.5823573883162,\"mmmu_pro\":0.68728323699422,\"intelligence_index_cost\":{\"total\":1132.8540777463882,\"input\":186.08062774638807,\"nonCacheInput\":39.020075999999996,\"cacheRead\":66.70617060900973,\"cacheWrite\":80.35438113737835,\"output\":946.7734500000001,\"reasoning\":845.4071100000001,\"answer\":101.36634},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.41290380463528553,\"input\":0.17715751403584135,\"nonCacheInput\":0.021146087162555484,\"cacheRead\":0.07351996765137786,\"cacheWrite\":0.082491459221908,\"output\":0.23574629059944427,\"reasoning\":0.15747824339018823,\"answer\":0.07826804720925604},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0847158493184302},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.06225720381621176},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.16039348390260247},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.010795097222222222},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.032041431533827616},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.009622317234848484},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.028225224107142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.003676285625},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.021176911875}]},\"intelligence_index_time_per_task\":306.2850398842488,\"price_1m_input_tokens\":3,\"price_1m_output_tokens\":15,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":37.69922354301513,"costForScoring":0.41290380463528553,"costPenalty":16.158488846293583,"pointsPerK":91302.67902548036,"costPerQuality":0.010952581136430007,"deltaTop":-25.35629172085431,"costVsTop":0.15015645347425982,"calculated":37.69922354301513,"frontier":false},{"modelKey":"gpt-5-1","sourceId":"4dc12a38-b18f-4c43-8e1b-678f8434b5b1","slug":"gpt-5-1","name":"GPT-5.1 (high)","shortName":"GPT-5.1 (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2025-11-13","cutoffDate":"2024-09-30","totalCost":778.1361142582324,"inputCost":59.26536425823249,"outputCost":718.8707499999999,"reasoningCost":663.52785,"answerCost":55.3429,"costPerTask":0.2690906889061637,"inputCostPerTask":0.05204183724443376,"outputCostPerTask":0.21704885166173,"reasoningCostPerTask":0.1784091458506802,"answerCostPerTask":0.038639705811049745,"timePerTask":224.74908535692842,"intelligence":36.8735132371926,"coding":49.3853169649049,"agentic":21.0115395189003,"mmmu":0.754913294797688,"priceInput1m":1.25,"priceOutput1m":10,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"4dc12a38-b18f-4c43-8e1b-678f8434b5b1\",\"slug\":\"gpt-5-1\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.1 (high)\",\"short_name\":\"GPT-5.1 (high)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2025-11-13\",\"knowledge_cutoff_date\":\"2024-09-30\",\"intelligence_index\":36.8735132371926,\"coding_index\":49.3853169649049,\"agentic_index\":21.0115395189003,\"mmmu_pro\":0.754913294797688,\"intelligence_index_cost\":{\"total\":778.1361142582324,\"input\":59.26536425823249,\"nonCacheInput\":15.21595,\"cacheRead\":17.988395221307503,\"cacheWrite\":26.061019036924982,\"output\":718.8707499999999,\"reasoning\":663.52785,\"answer\":55.3429},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.2690906889061637,\"input\":0.05204183724443376,\"nonCacheInput\":0.008269311206452901,\"cacheRead\":0.01859119031267077,\"cacheWrite\":0.025181335725310082,\"output\":0.21704885166173,\"reasoning\":0.1784091458506802,\"answer\":0.038639705811049745},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.05499726521993544},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03748245041249596},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.111674872449012},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.005206725622106481},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.022221530714202967},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0046580760732323236},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.02112420982142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00309206953125},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.008633489062500001}]},\"intelligence_index_time_per_task\":224.74908535692842,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":35.756789906999266,"costForScoring":0.2690906889061637,"costPenalty":14.298986705373185,"pointsPerK":132880.0712218929,"costPerQuality":0.007525582962174414,"deltaTop":-27.29872535687017,"costVsTop":0.09785742600455066,"calculated":35.756789906999266,"frontier":false},{"modelKey":"glm-4-7","sourceId":"6fc35842-0165-44cf-8570-c484a92b3d8c","slug":"glm-4-7","name":"GLM-4.7 (Reasoning)","shortName":"GLM-4.7","creatorName":"Z AI","creatorSlug":"zai","releaseDate":"2025-12-22","cutoffDate":null,"totalCost":582.2186145852468,"inputCost":205.57654218524667,"outputCost":376.6420724000001,"reasoningCost":360.0404192000001,"answerCost":16.6016532,"costPerTask":0.29717889817375276,"inputCostPerTask":0.24572500791981197,"outputCostPerTask":0.05145389025394071,"reasoningCostPerTask":0.035720758473479795,"answerCostPerTask":0.015733131780460922,"timePerTask":248.62586076764984,"intelligence":33.70492387461,"coding":45.258531002913,"agentic":25.3919072164948,"mmmu":null,"priceInput1m":0.6,"priceOutput1m":2.2,"activeParams":32,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"6fc35842-0165-44cf-8570-c484a92b3d8c\",\"slug\":\"glm-4-7\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GLM-4.7 (Reasoning)\",\"short_name\":\"GLM-4.7\",\"creator_name\":\"Z AI\",\"creator_slug\":\"zai\",\"release_date\":\"2025-12-22\",\"knowledge_cutoff_date\":null,\"intelligence_index\":33.70492387461,\"coding_index\":45.258531002913,\"agentic_index\":25.3919072164948,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":582.2186145852468,\"input\":205.57654218524667,\"nonCacheInput\":7.175616,\"cacheRead\":145.64501150327345,\"cacheWrite\":52.755914681973216,\"output\":376.6420724000001,\"reasoning\":360.0404192000001,\"answer\":16.6016532},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.29717889817375276,\"input\":0.24572500791981197,\"nonCacheInput\":0.003887268194274768,\"cacheRead\":0.17833981802535337,\"cacheWrite\":0.06349792170018385,\"output\":0.05145389025394071,\"reasoning\":0.035720758473479795,\"answer\":0.015733131780460922},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.08173349054476373},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.02730325532730601},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.16208809263141258},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0015443785300925928},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.008586972405004634},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0017424386363636367},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.006346540357142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0038200296166666673},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.004013700125}]},\"intelligence_index_time_per_task\":248.62586076764984,\"price_1m_input_tokens\":0.6,\"price_1m_output_tokens\":2.2,\"activeParams\":32,\"is_open_weights\":true,\"reasoning_model\":true}","quality":34.78512069800593,"costForScoring":0.29717889817375276,"costPenalty":14.730179681704396,"pointsPerK":117051.11268589462,"costPerQuality":0.008543276326500964,"deltaTop":-28.270394565863505,"costVsTop":0.10807197438292998,"calculated":34.78512069800593,"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":120.19053475235198,"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\":120.19053475235198,\"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":307.7166890054693,"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\":307.7166890054693,\"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":"qwen3-6-27b-non-reasoning","sourceId":"3b156101-b0d7-4438-b350-2d1f1168f40a","slug":"qwen3-6-27b-non-reasoning","name":"Qwen3.6 27B (Non-reasoning)","shortName":"Qwen3.6 27B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-04-22","cutoffDate":null,"totalCost":348.36888059999995,"inputCost":260.49630779999995,"outputCost":87.8725728,"reasoningCost":0,"answerCost":87.8725728,"costPerTask":0.3534061197907822,"inputCostPerTask":0.3124020026404164,"outputCostPerTask":0.04100411715036582,"reasoningCostPerTask":0,"answerCostPerTask":0.04100411715036582,"timePerTask":181.50029552302084,"intelligence":30.4611236934534,"coding":46.6300804549868,"agentic":23.2881408934708,"mmmu":0.717341040462428,"priceInput1m":0.6,"priceOutput1m":3.6,"activeParams":null,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"3b156101-b0d7-4438-b350-2d1f1168f40a\",\"slug\":\"qwen3-6-27b-non-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.6 27B (Non-reasoning)\",\"short_name\":\"Qwen3.6 27B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-04-22\",\"knowledge_cutoff_date\":null,\"intelligence_index\":30.4611236934534,\"coding_index\":46.6300804549868,\"agentic_index\":23.2881408934708,\"mmmu_pro\":0.717341040462428,\"intelligence_index_cost\":{\"total\":348.36888059999995,\"input\":260.49630779999995,\"nonCacheInput\":8.4112362,\"cacheRead\":197.0223129587887,\"cacheWrite\":55.0627586412113,\"output\":87.8725728,\"reasoning\":0,\"answer\":87.8725728},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3534061197907822,\"input\":0.3124020026404164,\"nonCacheInput\":0.004623398756324749,\"cacheRead\":0.2414882311456104,\"cacheWrite\":0.06629037273848126,\"output\":0.04100411715036582,\"reasoning\":0,\"answer\":0.04100411715036582},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.09679455136363635},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03470426443298969},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.21118451460674154},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0004814869791666667},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.003083505375347544},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0006925950757575759},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.002302737857142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00002372785},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0041387362499999995}]},\"intelligence_index_time_per_task\":181.50029552302084,\"price_1m_input_tokens\":0.6,\"price_1m_output_tokens\":3.6,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":false}","quality":33.459781680637,"costForScoring":0.3534061197907822,"costPenalty":15.482740657376809,"pointsPerK":94677.99171232611,"costPerQuality":0.010562116727596476,"deltaTop":-29.595733583232438,"costVsTop":0.12851954617070244,"calculated":33.459781680637,"frontier":false},{"modelKey":"qwen3-5-122b-a10b","sourceId":"2236df45-0699-40d1-b5cc-69ee345d2257","slug":"qwen3-5-122b-a10b","name":"Qwen3.5 122B A10B (Reasoning)","shortName":"Qwen3.5 122B A10B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-02-24","cutoffDate":null,"totalCost":447.0722616,"inputCost":140.845484,"outputCost":306.2267776,"reasoningCost":273.51342719999997,"answerCost":32.7133504,"costPerTask":0.24119620563683528,"inputCostPerTask":0.1869039314390884,"outputCostPerTask":0.054292274197746876,"reasoningCostPerTask":0.03351849339142828,"answerCostPerTask":0.020773780806318597,"timePerTask":115.69678395527785,"intelligence":32.2791462784081,"coding":45.7149916770703,"agentic":20.7174158075601,"mmmu":0.74971098265896,"priceInput1m":0.4,"priceOutput1m":3.2,"activeParams":10,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"2236df45-0699-40d1-b5cc-69ee345d2257\",\"slug\":\"qwen3-5-122b-a10b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.5 122B A10B (Reasoning)\",\"short_name\":\"Qwen3.5 122B A10B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-02-24\",\"knowledge_cutoff_date\":null,\"intelligence_index\":32.2791462784081,\"coding_index\":45.7149916770703,\"agentic_index\":20.7174158075601,\"mmmu_pro\":0.74971098265896,\"intelligence_index_cost\":{\"total\":447.0722616,\"input\":140.845484,\"nonCacheInput\":4.7456488000000006,\"cacheRead\":130.541204,\"cacheWrite\":5.558631200000001,\"output\":306.2267776,\"reasoning\":273.51342719999997,\"answer\":32.7133504},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.24119620563683528,\"input\":0.1869039314390884,\"nonCacheInput\":0.0025359380169836412,\"cacheRead\":0.1784188751658716,\"cacheWrite\":0.00594911825623313,\"output\":0.054292274197746876,\"reasoning\":0.03351849339142828,\"answer\":0.020773780806318597},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03998594030303031},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.02231645429553265},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1528428756554307},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0013824890046296296},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.010523745481927712},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001422858080808081},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.007697965357142856},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0017040734583333335},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0033198039999999996}]},\"intelligence_index_time_per_task\":115.69678395527785,\"price_1m_input_tokens\":0.4,\"price_1m_output_tokens\":3.2,\"activeParams\":10,\"is_open_weights\":true,\"reasoning_model\":true}","quality":32.90385125434617,"costForScoring":0.24119620563683528,"costPenalty":13.823704714451186,"pointsPerK":136419.4397978586,"costPerQuality":0.007330333576224649,"deltaTop":-30.151664009523266,"costVsTop":0.08771332795508091,"calculated":32.90385125434617,"frontier":false},{"modelKey":"gpt-5","sourceId":"48e50f00-1fd1-4acc-b337-61078aa341e6","slug":"gpt-5","name":"GPT-5 (high)","shortName":"GPT-5 (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2025-08-07","cutoffDate":"2024-09-30","totalCost":781.4482331526665,"inputCost":67.22581315266655,"outputCost":714.2224199999999,"reasoningCost":668.35943,"answerCost":45.86299,"costPerTask":0.2116516801323397,"inputCostPerTask":0.052989730878184406,"outputCostPerTask":0.15866194925415525,"reasoningCostPerTask":0.12171040953607823,"answerCostPerTask":0.036951539718077055,"timePerTask":158.37798785081742,"intelligence":34.7127335292454,"coding":37.7839332778471,"agentic":25.7092096219931,"mmmu":0.742196531791907,"priceInput1m":1.25,"priceOutput1m":10,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"48e50f00-1fd1-4acc-b337-61078aa341e6\",\"slug\":\"gpt-5\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5 (high)\",\"short_name\":\"GPT-5 (high)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2025-08-07\",\"knowledge_cutoff_date\":\"2024-09-30\",\"intelligence_index\":34.7127335292454,\"coding_index\":37.7839332778471,\"agentic_index\":25.7092096219931,\"mmmu_pro\":0.742196531791907,\"intelligence_index_cost\":{\"total\":781.4482331526665,\"input\":67.22581315266655,\"nonCacheInput\":15.23766375,\"cacheRead\":23.671662705259276,\"cacheWrite\":28.316486697407267,\"output\":714.2224199999999,\"reasoning\":668.35943,\"answer\":45.86299},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.2116516801323397,\"input\":0.052989730878184406,\"nonCacheInput\":0.008221474081220542,\"cacheRead\":0.019740206606147875,\"cacheWrite\":0.02502805019081599,\"output\":0.15866194925415525,\"reasoning\":0.12171040953607823,\"answer\":0.036951539718077055},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.05296967935599061},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03857323136792212},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.0519361448323925},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00506040870949074},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.020225478886700652},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004336537642045455},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.020985573660714286},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0044587991145833335},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.013105826562499999}]},\"intelligence_index_time_per_task\":158.37798785081742,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":32.73529214302853,"costForScoring":0.2116516801323397,"costPenalty":13.256217203380604,"pointsPerK":154665.8742447029,"costPerQuality":0.006465550367095597,"deltaTop":-30.320223120840907,"costVsTop":0.0769691761222989,"calculated":32.73529214302853,"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":1394.6034522953298,"inputCost":710.7972447953297,"outputCost":683.8062075000001,"reasoningCost":630.0631350000001,"answerCost":53.7430725,"costPerTask":1.082796913829072,"inputCostPerTask":0.8919595802002301,"outputCostPerTask":0.19083733362884178,"reasoningCostPerTask":0.13797198974531544,"answerCostPerTask":0.05286534388352635,"timePerTask":177.87321872036043,"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\":1394.6034522953298,\"input\":710.7972447953297,\"nonCacheInput\":19.505827500000002,\"cacheRead\":9.86651968940781,\"cacheWrite\":681.4248976059218,\"output\":683.8062075000001,\"reasoning\":630.0631350000001,\"answer\":53.7430725},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.082796913829072,\"input\":0.8919595802002301,\"nonCacheInput\":0.01079570871477184,\"cacheRead\":0.012601855101315944,\"cacheWrite\":0.8685620163841425,\"output\":0.19083733362884178,\"reasoning\":0.13797198974531544,\"answer\":0.05286534388352635},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.18717978501873378},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.15644940288227469},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.6587523663214108},{\"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\":177.87321872036043,\"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":1.082796913829072,"costPenalty":20.345470092808533,"pointsPerK":29506.491480664103,"costPerQuality":0.03389084739726883,"deltaTop":-31.10597735068254,"costVsTop":0.39376954774505074,"calculated":31.949537913186898,"frontier":false},{"modelKey":"qwen3-6-35b-a3b","sourceId":"8665ca00-c687-44c7-875c-22618cb31c4f","slug":"qwen3-6-35b-a3b","name":"Qwen3.6 35B A3B (Reasoning)","shortName":"Qwen3.6 35B A3B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-04-16","cutoffDate":null,"totalCost":333.52623219500003,"inputCost":113.47825652,"outputCost":220.047975675,"reasoningCost":55.338238395,"answerCost":164.70973728,"costPerTask":0.17881593213598196,"inputCostPerTask":0.13468302288186834,"outputCostPerTask":0.04413290925411365,"reasoningCostPerTask":0.022850531706975596,"answerCostPerTask":0.021282377547138066,"timePerTask":173.09683393709915,"intelligence":31.649611240178,"coding":41.8838431127757,"agentic":21.413264604811,"mmmu":0.75028901734104,"priceInput1m":0.248,"priceOutput1m":1.485,"activeParams":3,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"8665ca00-c687-44c7-875c-22618cb31c4f\",\"slug\":\"qwen3-6-35b-a3b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.6 35B A3B (Reasoning)\",\"short_name\":\"Qwen3.6 35B A3B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-04-16\",\"knowledge_cutoff_date\":null,\"intelligence_index\":31.649611240178,\"coding_index\":41.8838431127757,\"agentic_index\":21.413264604811,\"mmmu_pro\":0.75028901734104,\"intelligence_index_cost\":{\"total\":333.52623219500003,\"input\":113.47825652,\"nonCacheInput\":3.2333962240000003,\"cacheRead\":105.443378424,\"cacheWrite\":4.801481872,\"output\":220.047975675,\"reasoning\":55.338238395,\"answer\":164.70973728},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.17881593213598196,\"input\":0.13468302288186834,\"nonCacheInput\":0.0017578181882199507,\"cacheRead\":0.12813063502952024,\"cacheWrite\":0.004794569664128134,\"output\":0.04413290925411365,\"reasoning\":0.022850531706975596,\"answer\":0.021282377547138066},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.04731923119999999},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.01526484214089347},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.09930098815543069},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0010612749606481481},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.009735403304158945},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0009271880669191922},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.002937672883035714},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00040240557052083337},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.001866925854375}]},\"intelligence_index_time_per_task\":173.09683393709915,\"price_1m_input_tokens\":0.248,\"price_1m_output_tokens\":1.485,\"activeParams\":3,\"is_open_weights\":true,\"reasoning_model\":true}","quality":31.648906319254902,"costForScoring":0.17881593213598196,"costPenalty":12.524062109391366,"pointsPerK":176991.53504502744,"costPerQuality":0.00564998772255179,"deltaTop":-31.406608944614536,"costVsTop":0.0650281394668903,"calculated":31.648906319254902,"frontier":false},{"modelKey":"ring-2-6-1t","sourceId":"eb4ba465-3fcd-4065-9fe2-e8225e7b2c6c","slug":"ring-2-6-1t","name":"Ring-2.6-1T","shortName":"Ring-2.6-1T","creatorName":"InclusionAI","creatorSlug":"inclusionai","releaseDate":"2026-05-08","cutoffDate":null,"totalCost":459.5832322,"inputCost":198.1651422,"outputCost":261.41809,"reasoningCost":237.8922975,"answerCost":23.525792499999998,"costPerTask":0.3451837452945369,"inputCostPerTask":0.27633355149378425,"outputCostPerTask":0.06885019380075258,"reasoningCostPerTask":0.04493744930039258,"answerCostPerTask":0.023912744500359986,"timePerTask":191.03374016519598,"intelligence":30.5727263188268,"coding":42.8344777361631,"agentic":18.8602680412371,"mmmu":null,"priceInput1m":0.3,"priceOutput1m":2.5,"activeParams":63,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"eb4ba465-3fcd-4065-9fe2-e8225e7b2c6c\",\"slug\":\"ring-2-6-1t\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Ring-2.6-1T\",\"short_name\":\"Ring-2.6-1T\",\"creator_name\":\"InclusionAI\",\"creator_slug\":\"inclusionai\",\"release_date\":\"2026-05-08\",\"knowledge_cutoff_date\":null,\"intelligence_index\":30.5727263188268,\"coding_index\":42.8344777361631,\"agentic_index\":18.8602680412371,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":459.5832322,\"input\":198.1651422,\"nonCacheInput\":5.2152447,\"cacheRead\":152.9635529336032,\"cacheWrite\":39.98634456639679,\"output\":261.41809,\"reasoning\":237.8922975,\"answer\":23.525792499999998},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3451837452945369,\"input\":0.27633355149378425,\"nonCacheInput\":0.0032491348868426504,\"cacheRead\":0.21821712217956435,\"cacheWrite\":0.054867294427377256,\"output\":0.06885019380075258,\"reasoning\":0.04493744930039258,\"answer\":0.023912744500359986},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.047862820681818186},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03171169501718213},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.23236232902621723},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0016307303530092594},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.010049283653846153},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001283403061868687},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.017453729821428572},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0006065123041666667},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.002223241375}]},\"intelligence_index_time_per_task\":191.03374016519598,\"price_1m_input_tokens\":0.3,\"price_1m_output_tokens\":2.5,\"activeParams\":63,\"is_open_weights\":true,\"reasoning_model\":true}","quality":30.75582403207567,"costForScoring":0.3451837452945369,"costPenalty":15.380503365938763,"pointsPerK":89099.86188901355,"costPerQuality":0.011223361953642992,"deltaTop":-32.29969123179377,"costVsTop":0.1255294003313248,"calculated":30.75582403207567,"frontier":false},{"modelKey":"glm-4-6-reasoning","sourceId":"6a5d56e1-bb68-4205-8d9b-26b97888bc84","slug":"glm-4-6-reasoning","name":"GLM-4.6 (Reasoning)","shortName":"GLM-4.6","creatorName":"Z AI","creatorSlug":"zai","releaseDate":"2025-09-30","cutoffDate":null,"totalCost":312.71565435,"inputCost":177.92184135000002,"outputCost":134.793813,"reasoningCost":119.2376636,"answerCost":15.5561494,"costPerTask":0.28294770145479164,"inputCostPerTask":0.2419297090580874,"outputCostPerTask":0.041017992396704256,"reasoningCostPerTask":0.026657041812727513,"answerCostPerTask":0.014360950583976753,"timePerTask":426.82345272836807,"intelligence":28.6958810162247,"coding":45.767443473436,"agentic":17.6564879725086,"mmmu":null,"priceInput1m":0.55,"priceOutput1m":2.2,"activeParams":32,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"6a5d56e1-bb68-4205-8d9b-26b97888bc84\",\"slug\":\"glm-4-6-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GLM-4.6 (Reasoning)\",\"short_name\":\"GLM-4.6\",\"creator_name\":\"Z AI\",\"creator_slug\":\"zai\",\"release_date\":\"2025-09-30\",\"knowledge_cutoff_date\":null,\"intelligence_index\":28.6958810162247,\"coding_index\":45.767443473436,\"agentic_index\":17.6564879725086,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":312.71565435,\"input\":177.92184135000002,\"nonCacheInput\":6.56537365,\"cacheRead\":76.25009624625346,\"cacheWrite\":95.10637145374655,\"output\":134.793813,\"reasoning\":119.2376636,\"answer\":15.5561494},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.28294770145479164,\"input\":0.2419297090580874,\"nonCacheInput\":0.003554226043926623,\"cacheRead\":0.0689812955545552,\"cacheWrite\":0.16939418745960558,\"output\":0.041017992396704256,\"reasoning\":0.026657041812727513,\"answer\":0.014360950583976753},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03953551624999999},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.02955683556701031},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1990451143258427},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0009660524016203703},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00424495266160797},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0010485368055555557},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00455337142857143},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0006119338270833334},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.003385388187500001}]},\"intelligence_index_time_per_task\":426.82345272836807,\"price_1m_input_tokens\":0.55,\"price_1m_output_tokens\":2.2,\"activeParams\":32,\"is_open_weights\":true,\"reasoning_model\":true}","quality":30.706604154056436,"costForScoring":0.28294770145479164,"costPenalty":14.517061702644373,"pointsPerK":108523.95688735653,"costPerQuality":0.009214555280526303,"deltaTop":-32.348911109813,"costVsTop":0.10289666235135102,"calculated":30.706604154056436,"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":216.5488322414238,"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\":216.5488322414238,\"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":"qwen3-5-122b-a10b-non-reasoning","sourceId":"021b1b31-d2fc-4653-ab74-c10bd2f41c8e","slug":"qwen3-5-122b-a10b-non-reasoning","name":"Qwen3.5 122B A10B (Non-reasoning)","shortName":"Qwen3.5 122B A10B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-02-24","cutoffDate":null,"totalCost":214.02738680000002,"inputCost":110.97041400000002,"outputCost":103.0569728,"reasoningCost":0,"answerCost":103.0569728,"costPerTask":0.17592587162540868,"inputCostPerTask":0.14753933032366742,"outputCostPerTask":0.028386541301741227,"reasoningCostPerTask":0,"answerCostPerTask":0.028386541301741227,"timePerTask":52.642537310535644,"intelligence":27.5952535086828,"coding":43.3433902066861,"agentic":15.8337216494845,"mmmu":0.702890173410405,"priceInput1m":0.4,"priceOutput1m":3.2,"activeParams":10,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"021b1b31-d2fc-4653-ab74-c10bd2f41c8e\",\"slug\":\"qwen3-5-122b-a10b-non-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.5 122B A10B (Non-reasoning)\",\"short_name\":\"Qwen3.5 122B A10B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-02-24\",\"knowledge_cutoff_date\":null,\"intelligence_index\":27.5952535086828,\"coding_index\":43.3433902066861,\"agentic_index\":15.8337216494845,\"mmmu_pro\":0.702890173410405,\"intelligence_index_cost\":{\"total\":214.02738680000002,\"input\":110.97041400000002,\"nonCacheInput\":4.9825756000000005,\"cacheRead\":81.2811251365629,\"cacheWrite\":24.70671326343711,\"output\":103.0569728,\"reasoning\":0,\"answer\":103.0569728},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.17592587162540868,\"input\":0.14753933032366742,\"nonCacheInput\":0.0026043095528057955,\"cacheRead\":0.11223684984457177,\"cacheWrite\":0.03269817092628985,\"output\":0.028386541301741227,\"reasoning\":0,\"answer\":0.028386541301741227},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.031946990606060606},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.01550379209621993},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.11513588314606742},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0005072484953703703},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0045294468489341985},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0005702781565656566},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.005175299642857144},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000014760633333333332},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0025421719999999997}]},\"intelligence_index_time_per_task\":52.642537310535644,\"price_1m_input_tokens\":0.4,\"price_1m_output_tokens\":3.2,\"activeParams\":10,\"is_open_weights\":true,\"reasoning_model\":false}","quality":28.924121788284467,"costForScoring":0.17592587162540868,"costPenalty":12.453297114184469,"pointsPerK":164410.8482797308,"costPerQuality":0.006082323705906478,"deltaTop":-34.13139347558497,"costVsTop":0.06397714107035819,"calculated":28.924121788284467,"frontier":false},{"modelKey":"mimo-v2-flash","sourceId":"82b36b4d-84dd-4bc0-ad32-e3aee9442789","slug":"mimo-v2-flash","name":"MiMo-V2-Flash (Non-reasoning)","shortName":"MiMo-V2-Flash","creatorName":"Xiaomi","creatorSlug":"xiaomi","releaseDate":"2025-12-16","cutoffDate":null,"totalCost":409.66168600000003,"inputCost":398.24291020000004,"outputCost":11.4187758,"reasoningCost":0,"answerCost":11.4187758,"costPerTask":0.3511773843295714,"inputCostPerTask":0.34305497480629665,"outputCostPerTask":0.008122409523274839,"reasoningCostPerTask":0,"answerCostPerTask":0.008122409523274839,"timePerTask":null,"intelligence":24.6700650875255,"coding":49.8404771813012,"agentic":11.9909278350515,"mmmu":null,"priceInput1m":0.1,"priceOutput1m":0.3,"activeParams":15,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"82b36b4d-84dd-4bc0-ad32-e3aee9442789\",\"slug\":\"mimo-v2-flash\",\"model_url\":null,\"hosts_url\":null,\"name\":\"MiMo-V2-Flash (Non-reasoning)\",\"short_name\":\"MiMo-V2-Flash\",\"creator_name\":\"Xiaomi\",\"creator_slug\":\"xiaomi\",\"release_date\":\"2025-12-16\",\"knowledge_cutoff_date\":null,\"intelligence_index\":24.6700650875255,\"coding_index\":49.8404771813012,\"agentic_index\":11.9909278350515,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":409.66168600000003,\"input\":398.24291020000004,\"nonCacheInput\":1.3281772,\"cacheRead\":383.803312472412,\"cacheWrite\":13.111420527587981,\"output\":11.4187758,\"reasoning\":0,\"answer\":11.4187758},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3511773843295714,\"input\":0.34305497480629665,\"nonCacheInput\":0.0007531379736705452,\"cacheRead\":0.33070173797877384,\"cacheWrite\":0.01160009885385227,\"output\":0.008122409523274839,\"reasoning\":0,\"answer\":0.008122409523274839},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.22512481037878793},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.06533498041237114},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.05917849007490636},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00005154950810185185},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00015032447289156626},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0000796147095959596},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.000661315},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000002702085416666666},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0005935976875}]},\"intelligence_index_time_per_task\":null,\"price_1m_input_tokens\":0.1,\"price_1m_output_tokens\":0.3,\"activeParams\":15,\"is_open_weights\":true,\"reasoning_model\":false}","quality":28.833823367959397,"costForScoring":0.3511773843295714,"costPenalty":15.455265397593308,"pointsPerK":82106.15106381555,"costPerQuality":0.012179355469028963,"deltaTop":-34.22169189591004,"costVsTop":0.12770904501079344,"calculated":28.833823367959397,"frontier":false},{"modelKey":"grok-4-3-non-reasoning","sourceId":"90c2a9cf-ad7e-4332-9be2-2fd1309833e2","slug":"grok-4-3-non-reasoning","name":"Grok 4.3 (Non-reasoning)","shortName":"Grok 4.3 (Non-reasoning)","creatorName":"SpaceXAI","creatorSlug":"xai","releaseDate":"2026-04-30","cutoffDate":null,"totalCost":200.75978853622763,"inputCost":178.31564603622763,"outputCost":22.4441425,"reasoningCost":0,"answerCost":22.4441425,"costPerTask":0.29295162234785854,"inputCostPerTask":0.26997224527535996,"outputCostPerTask":0.022979377072498638,"reasoningCostPerTask":0,"answerCostPerTask":0.022979377072498638,"timePerTask":88.9080156527873,"intelligence":24.7517904486036,"coding":35.1830177555833,"agentic":22.8129553264605,"mmmu":0.647976878612717,"priceInput1m":1.25,"priceOutput1m":2.5,"activeParams":null,"isOpenWeights":false,"isReasoning":false,"rawResultJson":"{\"id\":\"90c2a9cf-ad7e-4332-9be2-2fd1309833e2\",\"slug\":\"grok-4-3-non-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Grok 4.3 (Non-reasoning)\",\"short_name\":\"Grok 4.3 (Non-reasoning)\",\"creator_name\":\"SpaceXAI\",\"creator_slug\":\"xai\",\"release_date\":\"2026-04-30\",\"knowledge_cutoff_date\":null,\"intelligence_index\":24.7517904486036,\"coding_index\":35.1830177555833,\"agentic_index\":22.8129553264605,\"mmmu_pro\":0.647976878612717,\"intelligence_index_cost\":{\"total\":200.75978853622763,\"input\":178.31564603622763,\"nonCacheInput\":15.7003375,\"cacheRead\":111.76534123119472,\"cacheWrite\":50.84996730503292,\"output\":22.4441425,\"reasoning\":0,\"answer\":22.4441425},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.29295162234785854,\"input\":0.26997224527535996,\"nonCacheInput\":0.007881797205342975,\"cacheRead\":0.18458715414982405,\"cacheWrite\":0.0775032939201929,\"output\":0.022979377072498638,\"reasoning\":0,\"answer\":0.022979377072498638},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.027906145850893658},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.00909952156393032},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.24730552979893844},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00032437717013888886},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0003269673887859129},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00010230863320707073},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0005832767857142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0000396959375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00726379921875}]},\"intelligence_index_time_per_task\":88.9080156527873,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":2.5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":27.582587843549135,"costForScoring":0.29295162234785854,"costPenalty":14.667959074460164,"pointsPerK":94154.07097761978,"costPerQuality":0.010620889671756178,"deltaTop":-35.4729274203203,"costVsTop":0.10653468473156816,"calculated":27.582587843549135,"frontier":false},{"modelKey":"gemma-4-26b-a4b","sourceId":"6e1b44ff-c227-496b-aef4-19b70cd18c76","slug":"gemma-4-26b-a4b","name":"Gemma 4 26B A4B (Reasoning)","shortName":"Gemma 4 26B A4B","creatorName":"Google","creatorSlug":"google","releaseDate":"2026-04-02","cutoffDate":null,"totalCost":51.917683007742106,"inputCost":22.181991407742103,"outputCost":29.735691600000003,"reasoningCost":27.4816284,"answerCost":2.2540632,"costPerTask":0.02940972218693016,"inputCostPerTask":0.021296653448221674,"outputCostPerTask":0.008113068738708479,"reasoningCostPerTask":0.006171652418566655,"answerCostPerTask":0.0019414163201418235,"timePerTask":null,"intelligence":25.6946061195095,"coding":39.3163060063809,"agentic":10.9671924398625,"mmmu":0.692485549132948,"priceInput1m":0.13,"priceOutput1m":0.4,"activeParams":3.8,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"6e1b44ff-c227-496b-aef4-19b70cd18c76\",\"slug\":\"gemma-4-26b-a4b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Gemma 4 26B A4B (Reasoning)\",\"short_name\":\"Gemma 4 26B A4B\",\"creator_name\":\"Google\",\"creator_slug\":\"google\",\"release_date\":\"2026-04-02\",\"knowledge_cutoff_date\":null,\"intelligence_index\":25.6946061195095,\"coding_index\":39.3163060063809,\"agentic_index\":10.9671924398625,\"mmmu_pro\":0.692485549132948,\"intelligence_index_cost\":{\"total\":51.917683007742106,\"input\":22.181991407742103,\"nonCacheInput\":1.52308663,\"cacheRead\":14.460838335376026,\"cacheWrite\":6.198066442366079,\"output\":29.735691600000003,\"reasoning\":27.4816284,\"answer\":2.2540632},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.02940972218693016,\"input\":0.021296653448221674,\"nonCacheInput\":0.0008185234149300485,\"cacheRead\":0.014298383130689447,\"cacheWrite\":0.006179746902602182,\"output\":0.008113068738708479,\"reasoning\":0.006171652418566655,\"answer\":0.0019414163201418235},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.009829482310226196},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0055266276353268555},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.010048366218582521},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0002616901070601852},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0008500965077618167},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000306783952020202},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0015352380892857146},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00015495299791666668},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0008964843687500001}]},\"intelligence_index_time_per_task\":null,\"price_1m_input_tokens\":0.13,\"price_1m_output_tokens\":0.4,\"activeParams\":3.8,\"is_open_weights\":true,\"reasoning_model\":true}","quality":25.326034855250967,"costForScoring":0.02940972218693016,"costPenalty":4.684909220503169,"pointsPerK":861144.9878471139,"costPerQuality":0.001161244638373879,"deltaTop":-37.72948040861847,"costVsTop":0.010695129305367757,"calculated":25.326034855250967,"frontier":false},{"modelKey":"nvidia-nemotron-3-super-120b-a12b","sourceId":"63872e9c-3377-4a6b-b477-7bba244c38e9","slug":"nvidia-nemotron-3-super-120b-a12b","name":"NVIDIA Nemotron 3 Super 120B A12B (Reasoning)","shortName":"NVIDIA Nemotron 3 Super","creatorName":"NVIDIA","creatorSlug":"nvidia","releaseDate":"2026-03-11","cutoffDate":null,"totalCost":253.84463035269977,"inputCost":171.08524630269977,"outputCost":82.75938405,"reasoningCost":77.3385272,"answerCost":5.42085685,"costPerTask":0.20551170435365923,"inputCostPerTask":0.18568682855016738,"outputCostPerTask":0.01982487580349185,"reasoningCostPerTask":0.014057214554773557,"answerCostPerTask":0.005767661248718291,"timePerTask":148.96921207372657,"intelligence":25.4059430700317,"coding":37.7163094742683,"agentic":8.7233642611684,"mmmu":null,"priceInput1m":0.25,"priceOutput1m":0.775,"activeParams":12.7,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"63872e9c-3377-4a6b-b477-7bba244c38e9\",\"slug\":\"nvidia-nemotron-3-super-120b-a12b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"NVIDIA Nemotron 3 Super 120B A12B (Reasoning)\",\"short_name\":\"NVIDIA Nemotron 3 Super\",\"creator_name\":\"NVIDIA\",\"creator_slug\":\"nvidia\",\"release_date\":\"2026-03-11\",\"knowledge_cutoff_date\":null,\"intelligence_index\":25.4059430700317,\"coding_index\":37.7163094742683,\"agentic_index\":8.7233642611684,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":253.84463035269977,\"input\":171.08524630269977,\"nonCacheInput\":3.0016425,\"cacheRead\":45.07181804642123,\"cacheWrite\":123.01178575627856,\"output\":82.75938405,\"reasoning\":77.3385272,\"answer\":5.42085685},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.20551170435365923,\"input\":0.18568682855016738,\"nonCacheInput\":0.0016297358511600793,\"cacheRead\":0.04953572034364763,\"cacheWrite\":0.13452137235535966,\"output\":0.01982487580349185,\"reasoning\":0.014057214554773557,\"answer\":0.005767661248718291},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.06352552416858501},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03698184454850692},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.09543343571293167},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00019160729166666665},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0031643745061978685},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001128758641098485},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0029523066294642854},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00022400873020833338},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.001909844125}]},\"intelligence_index_time_per_task\":148.96921207372657,\"price_1m_input_tokens\":0.25,\"price_1m_output_tokens\":0.775,\"activeParams\":12.7,\"is_open_weights\":true,\"reasoning_model\":true}","quality":23.948538935156133,"costForScoring":0.20551170435365923,"costPenalty":13.128365609637068,"pointsPerK":116531.26526528034,"costPerQuality":0.008581387988223816,"deltaTop":-39.1069763287133,"costVsTop":0.07473631467371314,"calculated":23.948538935156133,"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":123.70551818859515,"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\":123.70551818859515,\"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":"gemini-2-5-pro","sourceId":"27202e5f-c82d-4710-92e9-4317877d4883","slug":"gemini-2-5-pro","name":"Gemini 2.5 Pro","shortName":"Gemini 2.5 Pro","creatorName":"Google","creatorSlug":"google","releaseDate":"2025-06-05","cutoffDate":"2025-01-01","totalCost":609.6689950996661,"inputCost":83.71304509966612,"outputCost":525.9559499999999,"reasoningCost":467.57593999999995,"answerCost":58.38001,"costPerTask":0.19782530888396901,"inputCostPerTask":0.07680142161376999,"outputCostPerTask":0.12102388727019908,"reasoningCostPerTask":0.09048363429923885,"answerCostPerTask":0.030540252970960233,"timePerTask":80.56955407179622,"intelligence":25.8175930098627,"coding":33.2509710084616,"agentic":7.10078350515464,"mmmu":0.749132947976879,"priceInput1m":1.25,"priceOutput1m":10,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"27202e5f-c82d-4710-92e9-4317877d4883\",\"slug\":\"gemini-2-5-pro\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Gemini 2.5 Pro\",\"short_name\":\"Gemini 2.5 Pro\",\"creator_name\":\"Google\",\"creator_slug\":\"google\",\"release_date\":\"2025-06-05\",\"knowledge_cutoff_date\":\"2025-01-01\",\"intelligence_index\":25.8175930098627,\"coding_index\":33.2509710084616,\"agentic_index\":7.10078350515464,\"mmmu_pro\":0.749132947976879,\"intelligence_index_cost\":{\"total\":609.6689950996661,\"input\":83.71304509966612,\"nonCacheInput\":15.45992625,\"cacheRead\":13.379477905592655,\"cacheWrite\":54.873640944073465,\"output\":525.9559499999999,\"reasoning\":467.57593999999995,\"answer\":58.38001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.19782530888396901,\"input\":0.07680142161376999,\"nonCacheInput\":0.008325149841769642,\"cacheRead\":0.013377148932709207,\"cacheWrite\":0.05509912283929114,\"output\":0.12102388727019908,\"reasoning\":0.09048363429923885,\"answer\":0.030540252970960233},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0397729736600636},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.022131476424317804},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.07882223794096672},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0064932316984953695},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.018255465419369787},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004979567155934344},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.016679016741071428},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00215844140625},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0085328984375}]},\"intelligence_index_time_per_task\":80.56955407179622,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":22.05644917449298,"costForScoring":0.19782530888396901,"costPenalty":12.962818525064524,"pointsPerK":111494.57720513307,"costPerQuality":0.008969046074412679,"deltaTop":-40.999066089376456,"costVsTop":0.0719410827800551,"calculated":22.05644917449298,"frontier":false},{"modelKey":"qwen3-coder-next","sourceId":"fc92f822-04b7-420d-9c07-a21af5e9aac7","slug":"qwen3-coder-next","name":"Qwen3 Coder Next","shortName":"Qwen3 Coder Next","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-02-03","cutoffDate":null,"totalCost":245.3820372,"inputCost":206.86110480000002,"outputCost":38.5209324,"reasoningCost":0,"answerCost":38.5209324,"costPerTask":0.32760562537368265,"inputCostPerTask":0.3091791301772715,"outputCostPerTask":0.01842649519641114,"reasoningCostPerTask":0,"answerCostPerTask":0.01842649519641114,"timePerTask":162.5672221879012,"intelligence":21.1086120792868,"coding":36.2320536828964,"agentic":8.78654639175257,"mmmu":null,"priceInput1m":0.35,"priceOutput1m":1.2,"activeParams":3,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"fc92f822-04b7-420d-9c07-a21af5e9aac7\",\"slug\":\"qwen3-coder-next\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3 Coder Next\",\"short_name\":\"Qwen3 Coder Next\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-02-03\",\"knowledge_cutoff_date\":null,\"intelligence_index\":21.1086120792868,\"coding_index\":36.2320536828964,\"agentic_index\":8.78654639175257,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":245.3820372,\"input\":206.86110480000002,\"nonCacheInput\":4.903409,\"cacheRead\":154.50770140493896,\"cacheWrite\":47.44999439506106,\"output\":38.5209324,\"reasoning\":0,\"answer\":38.5209324},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.32760562537368265,\"input\":0.3091791301772715,\"nonCacheInput\":0.0026098707778037652,\"cacheRead\":0.23646083585396752,\"cacheWrite\":0.07010842354550029,\"output\":0.01842649519641114,\"reasoning\":0,\"answer\":0.01842649519641114},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0454754953030303},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.008558295532646048},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.2675791378277153},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0005329548466435185},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0013572466143419832},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0003998284722222223},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00124283625},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000013739402083333332},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.002446091125}]},\"intelligence_index_time_per_task\":162.5672221879012,\"price_1m_input_tokens\":0.35,\"price_1m_output_tokens\":1.2,\"activeParams\":3,\"is_open_weights\":true,\"reasoning_model\":false}","quality":22.042404051311923,"costForScoring":0.32760562537368265,"costPenalty":15.153513504991675,"pointsPerK":67283.35029708144,"costPerQuality":0.014862517927312207,"deltaTop":-41.01311121255752,"costVsTop":0.11913694737635111,"calculated":22.042404051311923,"frontier":false},{"modelKey":"gemini-3-1-flash-lite-preview","sourceId":"598190f8-dc9c-4fea-a7ea-4b81c402ab18","slug":"gemini-3-1-flash-lite-preview","name":"Gemini 3.1 Flash-Lite","shortName":"Gemini 3.1 Flash-Lite","creatorName":"Google","creatorSlug":"google","releaseDate":"2026-03-03","cutoffDate":"2025-01-01","totalCost":93.72015133584392,"inputCost":10.718464335843926,"outputCost":83.00168699999999,"reasoningCost":78.86947649999999,"answerCost":4.1322105,"costPerTask":0.041571620355421224,"inputCostPerTask":0.011247002928975994,"outputCostPerTask":0.030324617426445235,"reasoningCostPerTask":0.027267016536222714,"answerCostPerTask":0.003057600890222524,"timePerTask":61.46001542057265,"intelligence":25.038457882447,"coding":34.6901442641143,"agentic":6.17159793814433,"mmmu":0.755491329479769,"priceInput1m":0.25,"priceOutput1m":1.5,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"598190f8-dc9c-4fea-a7ea-4b81c402ab18\",\"slug\":\"gemini-3-1-flash-lite-preview\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Gemini 3.1 Flash-Lite\",\"short_name\":\"Gemini 3.1 Flash-Lite\",\"creator_name\":\"Google\",\"creator_slug\":\"google\",\"release_date\":\"2026-03-03\",\"knowledge_cutoff_date\":\"2025-01-01\",\"intelligence_index\":25.038457882447,\"coding_index\":34.6901442641143,\"agentic_index\":6.17159793814433,\"mmmu_pro\":0.755491329479769,\"intelligence_index_cost\":{\"total\":93.72015133584392,\"input\":10.718464335843926,\"nonCacheInput\":2.9360455,\"cacheRead\":1.7679439904617862,\"cacheWrite\":6.01447484538214,\"output\":83.00168699999999,\"reasoning\":78.86947649999999,\"answer\":4.1322105},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.041571620355421224,\"input\":0.011247002928975994,\"nonCacheInput\":0.0015781274372618122,\"cacheRead\":0.0023540867455481835,\"cacheWrite\":0.007314788746165997,\"output\":0.030324617426445235,\"reasoning\":0.027267016536222714,\"answer\":0.003057600890222524},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.002767301865547517},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.003540987381456292},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.023911548803943965},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0015175426793981477},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0028062979465940685},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0008104060921717172},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.004320935044642857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00019489022916666668},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0017017103125}]},\"intelligence_index_time_per_task\":61.46001542057265,\"price_1m_input_tokens\":0.25,\"price_1m_output_tokens\":1.5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":21.966733361568544,"costForScoring":0.041571620355421224,"costPenalty":6.187969525241014,"pointsPerK":528406.9558453939,"costPerQuality":0.001892480764943959,"deltaTop":-41.088781902300894,"costVsTop":0.015117920948348063,"calculated":21.966733361568544,"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":97.42295400659044,"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\":97.42295400659044,\"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-5-mini","sourceId":"29855680-7469-43eb-8b88-cd3fb1d99da3","slug":"gpt-5-mini","name":"GPT-5 mini (high)","shortName":"GPT-5 mini (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2025-08-07","cutoffDate":"2024-05-30","totalCost":130.1557531833946,"inputCost":10.086251183394623,"outputCost":120.069502,"reasoningCost":113.7187,"answerCost":6.350802,"costPerTask":0.02935038848780333,"inputCostPerTask":0.007365158718027282,"outputCostPerTask":0.021985229769776043,"reasoningCostPerTask":0.018087614525881035,"answerCostPerTask":0.003897615243895011,"timePerTask":113.2624046192405,"intelligence":25.3051924538853,"coding":15.575582605077,"agentic":19.368058419244,"mmmu":0.700578034682081,"priceInput1m":0.25,"priceOutput1m":2,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"29855680-7469-43eb-8b88-cd3fb1d99da3\",\"slug\":\"gpt-5-mini\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5 mini (high)\",\"short_name\":\"GPT-5 mini (high)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2025-08-07\",\"knowledge_cutoff_date\":\"2024-05-30\",\"intelligence_index\":25.3051924538853,\"coding_index\":15.575582605077,\"agentic_index\":19.368058419244,\"mmmu_pro\":0.700578034682081,\"intelligence_index_cost\":{\"total\":130.1557531833946,\"input\":10.086251183394623,\"nonCacheInput\":3.0639415,\"cacheRead\":3.438319618511709,\"cacheWrite\":3.5839900648829146,\"output\":120.069502,\"reasoning\":113.7187,\"answer\":6.350802},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.02935038848780333,\"input\":0.007365158718027282,\"nonCacheInput\":0.0016500944011189475,\"cacheRead\":0.0027540306520849843,\"cacheWrite\":0.0029610336648233497,\"output\":0.021985229769776043,\"reasoning\":0.018087614525881035,\"answer\":0.003897615243895011},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.007263298103122922},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.008418072975947086},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.0009485865978838184},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0008986336805555554},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.003633685327849861},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0008885657354797981},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0048062283482142865},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00069478740625},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0017985303124999998}]},\"intelligence_index_time_per_task\":113.2624046192405,\"price_1m_input_tokens\":0.25,\"price_1m_output_tokens\":2,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":20.082944492735432,"costForScoring":0.02935038848780333,"costPenalty":4.676138540331282,"pointsPerK":684247.9955957305,"costPerQuality":0.0014614584279919807,"deltaTop":-42.972570771134,"costVsTop":0.010673552033053051,"calculated":20.082944492735432,"frontier":false},{"modelKey":"qwen3-5-9b","sourceId":"2d28a13a-096e-475a-beb8-26bbd1c7d51c","slug":"qwen3-5-9b","name":"Qwen3.5 9B (Reasoning)","shortName":"Qwen3.5 9B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-03-02","cutoffDate":null,"totalCost":178.7470683,"inputCost":147.7552419,"outputCost":30.991826399999997,"reasoningCost":28.415755349999998,"answerCost":2.57607105,"costPerTask":0.16358096536693414,"inputCostPerTask":0.15869551287667602,"outputCostPerTask":0.004885452490258115,"reasoningCostPerTask":0.003103565662029565,"answerCostPerTask":0.0017818868282285494,"timePerTask":463.9057108205907,"intelligence":21.4379662021172,"coding":28.6577541961437,"agentic":7.40947422680412,"mmmu":0.692485549132948,"priceInput1m":0.1,"priceOutput1m":0.15,"activeParams":null,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"2d28a13a-096e-475a-beb8-26bbd1c7d51c\",\"slug\":\"qwen3-5-9b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.5 9B (Reasoning)\",\"short_name\":\"Qwen3.5 9B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-03-02\",\"knowledge_cutoff_date\":null,\"intelligence_index\":21.4379662021172,\"coding_index\":28.6577541961437,\"agentic_index\":7.40947422680412,\"mmmu_pro\":0.692485549132948,\"intelligence_index_cost\":{\"total\":178.7470683,\"input\":147.7552419,\"nonCacheInput\":1.1930614000000002,\"cacheRead\":128.9803724663758,\"cacheWrite\":17.581808033624192,\"output\":30.991826399999997,\"reasoning\":28.415755349999998,\"answer\":2.57607105},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.16358096536693414,\"input\":0.15869551287667602,\"nonCacheInput\":0.0006369481258783386,\"cacheRead\":0.13892836521815102,\"cacheWrite\":0.019130199532646643,\"output\":0.004885452490258115,\"reasoning\":0.003103565662029565,\"answer\":0.0017818868282285494},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.07578981143939395},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.006110851761168385},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.07914546601123594},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00011971154513888888},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0008420795093836886},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00008736409406565656},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0005511755357142856},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0002583432833333333},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0006761621875}]},\"intelligence_index_time_per_task\":463.9057108205907,\"price_1m_input_tokens\":0.1,\"price_1m_output_tokens\":0.15,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":true}","quality":19.168398208355004,"costForScoring":0.16358096536693414,"costPenalty":12.137327668350066,"pointsPerK":117179.8819340484,"costPerQuality":0.008533888100030886,"deltaTop":-43.88711705551444,"costVsTop":0.05948779676925141,"calculated":19.168398208355004,"frontier":false},{"modelKey":"nova-2-0-pro-reasoning-low","sourceId":"f4274721-ef28-4121-aa88-8e97267a5a82","slug":"nova-2-0-pro-reasoning-low","name":"Nova 2.0 Pro Preview (low)","shortName":"Nova 2.0 Pro Preview (low)","creatorName":"Amazon","creatorSlug":"aws","releaseDate":"2025-11-27","cutoffDate":null,"totalCost":243.65079,"inputCost":120.12977000000001,"outputCost":123.52102,"reasoningCost":98.13054,"answerCost":25.390480000000004,"costPerTask":0.21277260985423777,"inputCostPerTask":0.16361896973328147,"outputCostPerTask":0.04915364012095631,"reasoningCostPerTask":0.02769788979511986,"answerCostPerTask":0.021455750325836444,"timePerTask":41.480435792310686,"intelligence":19.6058827132159,"coding":25.8695727562769,"agentic":6.4193883161512,"mmmu":0.627167630057804,"priceInput1m":1.25,"priceOutput1m":10,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"f4274721-ef28-4121-aa88-8e97267a5a82\",\"slug\":\"nova-2-0-pro-reasoning-low\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Nova 2.0 Pro Preview (low)\",\"short_name\":\"Nova 2.0 Pro Preview (low)\",\"creator_name\":\"Amazon\",\"creator_slug\":\"aws\",\"release_date\":\"2025-11-27\",\"knowledge_cutoff_date\":null,\"intelligence_index\":19.6058827132159,\"coding_index\":25.8695727562769,\"agentic_index\":6.4193883161512,\"mmmu_pro\":0.627167630057804,\"intelligence_index_cost\":{\"total\":243.65079,\"input\":120.12977000000001,\"nonCacheInput\":15.0330275,\"cacheRead\":68.5784022,\"cacheWrite\":36.518340300000006,\"output\":123.52102,\"reasoning\":98.13054,\"answer\":25.390480000000004},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.21277260985423777,\"input\":0.16361896973328147,\"nonCacheInput\":0.00805109982813859,\"cacheRead\":0.11579478137302597,\"cacheWrite\":0.039773088532116904,\"output\":0.04915364012095631,\"reasoning\":0.02769788979511986,\"answer\":0.021455750325836444},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.017813631628787876},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.02535051009450172},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.151910702247191},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0013523777488425926},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0021082601801436516},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0017640640782828287},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0028858761160714284},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0009542549479166668},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0086329328125}]},\"intelligence_index_time_per_task\":41.480435792310686,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":17.298281261881332,"costForScoring":0.21277260985423777,"costPenalty":13.279157206400459,"pointsPerK":81299.37999882463,"costPerQuality":0.01230021680379921,"deltaTop":-45.75723400198811,"costVsTop":0.07737681303371649,"calculated":17.298281261881332,"frontier":false},{"modelKey":"hypernova-60b","sourceId":"340fb211-4fad-41d3-87d5-ed0d0cd34088","slug":"hypernova-60b","name":"HyperNova 60B 2605","shortName":"HyperNova 60B 2605","creatorName":"Multiverse Computing","creatorSlug":"multiversecomputing","releaseDate":"2026-05-26","cutoffDate":null,"totalCost":30.175502980000005,"inputCost":11.386879559999999,"outputCost":18.788623420000004,"reasoningCost":17.841186160000003,"answerCost":0.9474372600000001,"costPerTask":0.014264160674413665,"inputCostPerTask":0.01033375820040373,"outputCostPerTask":0.003930402474009934,"reasoningCostPerTask":0.003213598148319183,"answerCostPerTask":0.0007168043256907511,"timePerTask":81.13335581912195,"intelligence":17.8040703229111,"coding":23.2300769870994,"agentic":6.68960824742268,"mmmu":null,"priceInput1m":0.04,"priceOutput1m":0.14,"activeParams":4.8,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"340fb211-4fad-41d3-87d5-ed0d0cd34088\",\"slug\":\"hypernova-60b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"HyperNova 60B 2605\",\"short_name\":\"HyperNova 60B 2605\",\"creator_name\":\"Multiverse Computing\",\"creator_slug\":\"multiversecomputing\",\"release_date\":\"2026-05-26\",\"knowledge_cutoff_date\":null,\"intelligence_index\":17.8040703229111,\"coding_index\":23.2300769870994,\"agentic_index\":6.68960824742268,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":30.175502980000005,\"input\":11.386879559999999,\"nonCacheInput\":0.50318504,\"cacheRead\":7.333656885257349,\"cacheWrite\":3.5500376347426505,\"output\":18.788623420000004,\"reasoning\":17.841186160000003,\"answer\":0.9474372600000001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.014264160674413665,\"input\":0.01033375820040373,\"nonCacheInput\":0.0002602335473388548,\"cacheRead\":0.006760583023937497,\"cacheWrite\":0.0033129416291273815,\"output\":0.003930402474009934,\"reasoning\":0.003213598148319183,\"answer\":0.0007168043256907511},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0057237525757575765},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0032352399828178688},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.003927296142322097},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00008352013888888889},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00042586768767377206},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0001225287310606061},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0003238852321428571},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00016573478375000002},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00025633540000000003}]},\"intelligence_index_time_per_task\":81.13335581912195,\"price_1m_input_tokens\":0.04,\"price_1m_output_tokens\":0.14,\"activeParams\":4.8,\"is_open_weights\":true,\"reasoning_model\":true}","quality":15.907918519144395,"costForScoring":0.014264160674413665,"costPenalty":1.54246222176428,"pointsPerK":1115236.9131454907,"costPerQuality":0.0008966704636591803,"deltaTop":-47.14759674472504,"costVsTop":0.005187299692113143,"calculated":15.907918519144395,"frontier":true},{"modelKey":"deepseek-r1-0120","sourceId":"0e34f05c-387e-4968-be15-ccec4a55d8c1","slug":"deepseek-r1-0120","name":"DeepSeek R1 (Jan '25)","shortName":"DeepSeek R1 (Jan)","creatorName":"DeepSeek","creatorSlug":"deepseek","releaseDate":"2025-01-20","cutoffDate":null,"totalCost":415.907224975,"inputCost":212.47310177500003,"outputCost":203.4341232,"reasoningCost":181.4152718,"answerCost":22.0188514,"costPerTask":0.24713753983015388,"inputCostPerTask":0.17381585431759883,"outputCostPerTask":0.07332168551255507,"reasoningCostPerTask":0.05800365061838551,"answerCostPerTask":0.01531803489416955,"timePerTask":null,"intelligence":18.5075067596643,"coding":24.6388443017656,"agentic":3.08858419243986,"mmmu":null,"priceInput1m":1.675,"priceOutput1m":4.7,"activeParams":37,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"0e34f05c-387e-4968-be15-ccec4a55d8c1\",\"slug\":\"deepseek-r1-0120\",\"model_url\":null,\"hosts_url\":null,\"name\":\"DeepSeek R1 (Jan '25)\",\"short_name\":\"DeepSeek R1 (Jan)\",\"creator_name\":\"DeepSeek\",\"creator_slug\":\"deepseek\",\"release_date\":\"2025-01-20\",\"knowledge_cutoff_date\":null,\"intelligence_index\":18.5075067596643,\"coding_index\":24.6388443017656,\"agentic_index\":3.08858419243986,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":415.907224975,\"input\":212.47310177500003,\"nonCacheInput\":19.8575069,\"cacheRead\":126.67512311436332,\"cacheWrite\":65.94047176063671,\"output\":203.4341232,\"reasoning\":181.4152718,\"answer\":22.0188514},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.24713753983015388,\"input\":0.17381585431759883,\"nonCacheInput\":0.010694773610279477,\"cacheRead\":0.10585538558823314,\"cacheWrite\":0.0572656951190862,\"output\":0.07332168551255507,\"reasoning\":0.05800365061838551,\"answer\":0.01531803489416955},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.14646397306818182},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.026677983097079035},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.04631984550561797},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0021875557291666666},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.005944371673714088},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001989025773358586},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.006715736808035715},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00054822520625},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.01029082296875}]},\"intelligence_index_time_per_task\":null,\"price_1m_input_tokens\":1.675,\"price_1m_output_tokens\":4.7,\"activeParams\":37,\"is_open_weights\":true,\"reasoning_model\":true}","quality":15.411645084623252,"costForScoring":0.24713753983015388,"costPenalty":13.929387191082627,"pointsPerK":62360.59926474529,"costPerQuality":0.016035766361939634,"deltaTop":-47.643870179246186,"costVsTop":0.08987395147406758,"calculated":15.411645084623252,"frontier":false},{"modelKey":"mistral-small-3-1","sourceId":"24ac5b00-5f03-4c47-8e37-522d1195383e","slug":"mistral-small-3-1","name":"Mistral Small 3.1","shortName":"Mistral Small 3.1","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-03-17","cutoffDate":null,"totalCost":29.887950300000004,"inputCost":28.400486100000002,"outputCost":1.4874642,"reasoningCost":0,"answerCost":1.4874642,"costPerTask":0.04100283502410408,"inputCostPerTask":0.03957566310370008,"outputCostPerTask":0.0014271719204039855,"reasoningCostPerTask":0,"answerCostPerTask":0.0014271719204039855,"timePerTask":29.903268349252585,"intelligence":14.7448087533968,"coding":26.3130288528229,"agentic":5.16543642611684,"mmmu":null,"priceInput1m":0.1,"priceOutput1m":0.3,"activeParams":null,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"24ac5b00-5f03-4c47-8e37-522d1195383e\",\"slug\":\"mistral-small-3-1\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Mistral Small 3.1\",\"short_name\":\"Mistral Small 3.1\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-03-17\",\"knowledge_cutoff_date\":null,\"intelligence_index\":14.7448087533968,\"coding_index\":26.3130288528229,\"agentic_index\":5.16543642611684,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":29.887950300000004,\"input\":28.400486100000002,\"nonCacheInput\":1.1911525,\"cacheRead\":0.8737502611160313,\"cacheWrite\":26.33558333888397,\"output\":1.4874642,\"reasoning\":0,\"answer\":1.4874642},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.04100283502410408,\"input\":0.03957566310370008,\"nonCacheInput\":0.0006416175779075873,\"cacheRead\":0.0012600075134021889,\"cacheWrite\":0.03767403801239031,\"output\":0.0014271719204039855,\"reasoning\":0,\"answer\":0.0014271719204039855},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.004216813106060606},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.005500231357388316},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.03056966816479401},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.000030166811342592593},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.000020058120945319742},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000009829482323232323},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00005967624999999999},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0000019944187500000004},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0005943973125000001}]},\"intelligence_index_time_per_task\":29.903268349252585,\"price_1m_input_tokens\":0.1,\"price_1m_output_tokens\":0.3,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":false}","quality":15.407758010778847,"costForScoring":0.04100283502410408,"costPenalty":6.128138858114028,"pointsPerK":375772.9923240962,"costPerQuality":0.0026611811397491843,"deltaTop":-47.64775725309059,"costVsTop":0.014911076673289366,"calculated":15.407758010778847,"frontier":false},{"modelKey":"nova-2-0-lite-reasoning","sourceId":"61bd9367-e520-4ec8-989e-5fbf50e61610","slug":"nova-2-0-lite-reasoning","name":"Nova 2.0 Lite (high)","shortName":"Nova 2.0 Lite (high)","creatorName":"Amazon","creatorSlug":"aws","releaseDate":"2025-10-29","cutoffDate":null,"totalCost":634.8228193,"inputCost":75.7211493,"outputCost":559.10167,"reasoningCost":545.9686325,"answerCost":13.1330375,"costPerTask":0.24542698374402477,"inputCostPerTask":0.12994997515524354,"outputCostPerTask":0.1154770085887812,"reasoningCostPerTask":0.10214910047697251,"answerCostPerTask":0.013327908111808659,"timePerTask":318.5704235344926,"intelligence":18.1684165088961,"coding":23.0436780413372,"agentic":3.1260412371134,"mmmu":0.63757225433526,"priceInput1m":0.3,"priceOutput1m":2.5,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"61bd9367-e520-4ec8-989e-5fbf50e61610\",\"slug\":\"nova-2-0-lite-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Nova 2.0 Lite (high)\",\"short_name\":\"Nova 2.0 Lite (high)\",\"creator_name\":\"Amazon\",\"creator_slug\":\"aws\",\"release_date\":\"2025-10-29\",\"knowledge_cutoff_date\":null,\"intelligence_index\":18.1684165088961,\"coding_index\":23.0436780413372,\"agentic_index\":3.1260412371134,\"mmmu_pro\":0.63757225433526,\"intelligence_index_cost\":{\"total\":634.8228193,\"input\":75.7211493,\"nonCacheInput\":3.5919731999999995,\"cacheRead\":49.211594879999986,\"cacheWrite\":22.917581220000006,\"output\":559.10167,\"reasoning\":545.9686325,\"answer\":13.1330375},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.24542698374402477,\"input\":0.12994997515524354,\"nonCacheInput\":0.0019307274191516315,\"cacheRead\":0.08784637219298302,\"cacheWrite\":0.0401728755431089,\"output\":0.1154770085887812,\"reasoning\":0.10214910047697251,\"answer\":0.013327908111808659},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.01605813636363636},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.002825494501718213},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1855890599250936},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0067090260706018515},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.017667420528266913},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.007178258238636364},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.003925622053571429},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0031711236874999997},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.002302842375}]},\"intelligence_index_time_per_task\":318.5704235344926,\"price_1m_input_tokens\":0.3,\"price_1m_output_tokens\":2.5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":14.779378595782234,"costForScoring":0.24542698374402477,"costPenalty":13.899223100082803,"pointsPerK":60219.04507124944,"costPerQuality":0.016606042138609615,"deltaTop":-48.276136668087204,"costVsTop":0.08925189124483615,"calculated":14.779378595782234,"frontier":false},{"modelKey":"mistral-large-3","sourceId":"4928e950-7f37-4475-b0dc-c5bad781a321","slug":"mistral-large-3","name":"Mistral Large 3","shortName":"Mistral Large 3","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-12-02","cutoffDate":null,"totalCost":71.038521,"inputCost":62.611368,"outputCost":8.427153,"reasoningCost":0,"answerCost":8.427153,"costPerTask":0.05988932957210771,"inputCostPerTask":0.05534271151963587,"outputCostPerTask":0.004546618052471828,"reasoningCostPerTask":0,"answerCostPerTask":0.004546618052471828,"timePerTask":74.5163194092688,"intelligence":15.9300825619952,"coding":20.0656297683452,"agentic":5.51939862542955,"mmmu":0.556647398843931,"priceInput1m":0.5,"priceOutput1m":1.5,"activeParams":41,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"4928e950-7f37-4475-b0dc-c5bad781a321\",\"slug\":\"mistral-large-3\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Mistral Large 3\",\"short_name\":\"Mistral Large 3\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-12-02\",\"knowledge_cutoff_date\":null,\"intelligence_index\":15.9300825619952,\"coding_index\":20.0656297683452,\"agentic_index\":5.51939862542955,\"mmmu_pro\":0.556647398843931,\"intelligence_index_cost\":{\"total\":71.038521,\"input\":62.611368,\"nonCacheInput\":6.013087,\"cacheRead\":0,\"cacheWrite\":56.598281,\"output\":8.427153,\"reasoning\":0,\"answer\":8.427153},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.05988932957210771,\"input\":0.05534271151963587,\"nonCacheInput\":0.003271154660429305,\"cacheRead\":0,\"cacheWrite\":0.05207155685920657,\"output\":0.004546618052471828,\"reasoning\":0,\"answer\":0.004546618052471828},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.017707708333333336},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.026005658505154638},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.012160508426966291},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00016087282986111112},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0002448593025949954},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00008003140782828283},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0005486763392857142},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000010326302083333333},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.002970688125}]},\"intelligence_index_time_per_task\":74.5163194092688,\"price_1m_input_tokens\":0.5,\"price_1m_output_tokens\":1.5,\"activeParams\":41,\"is_open_weights\":true,\"reasoning_model\":false}","quality":13.838370318589982,"costForScoring":0.05988932957210771,"costPenalty":7.773494514251031,"pointsPerK":231065.70765545743,"costPerQuality":0.004327773299407553,"deltaTop":-49.21714494527946,"costVsTop":0.02177933268849882,"calculated":13.838370318589982,"frontier":false},{"modelKey":"mistral-medium-3-1","sourceId":"05a32e26-e609-4377-951b-8fa23d329926","slug":"mistral-medium-3-1","name":"Mistral Medium 3.1","shortName":"Mistral Medium 3.1","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-08-12","cutoffDate":null,"totalCost":131.5947016,"inputCost":114.30674560000001,"outputCost":17.287956,"reasoningCost":0,"answerCost":17.287956,"costPerTask":0.1448042873568494,"inputCostPerTask":0.13471121090095206,"outputCostPerTask":0.010093076455897328,"reasoningCostPerTask":0,"answerCostPerTask":0.010093076455897328,"timePerTask":57.02321716707784,"intelligence":14.6788898631869,"coding":20.5038840338466,"agentic":6.16520274914089,"mmmu":0.541618497109827,"priceInput1m":0.4,"priceOutput1m":2,"activeParams":null,"isOpenWeights":false,"isReasoning":false,"rawResultJson":"{\"id\":\"05a32e26-e609-4377-951b-8fa23d329926\",\"slug\":\"mistral-medium-3-1\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Mistral Medium 3.1\",\"short_name\":\"Mistral Medium 3.1\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-08-12\",\"knowledge_cutoff_date\":null,\"intelligence_index\":14.6788898631869,\"coding_index\":20.5038840338466,\"agentic_index\":6.16520274914089,\"mmmu_pro\":0.541618497109827,\"intelligence_index_cost\":{\"total\":131.5947016,\"input\":114.30674560000001,\"nonCacheInput\":3.0723004,\"cacheRead\":41.87364539001429,\"cacheWrite\":69.36079980998572,\"output\":17.287956,\"reasoning\":0,\"answer\":17.287956},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.1448042873568494,\"input\":0.13471121090095206,\"nonCacheInput\":0.001528329337290387,\"cacheRead\":0.05020642419033433,\"cacheWrite\":0.08297645737332729,\"output\":0.010093076455897328,\"reasoning\":0,\"answer\":0.010093076455897328},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03626317818181817},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.021715327147766326},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.08420547415730337},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00015749780092592594},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0005533360518999074},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00010442790404040406},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00048325607142857144},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000008640041666666667},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0013131500000000001}]},\"intelligence_index_time_per_task\":57.02321716707784,\"price_1m_input_tokens\":0.4,\"price_1m_output_tokens\":2,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":13.78265888205813,"costForScoring":0.1448042873568494,"costPenalty":11.607814206170449,"pointsPerK":95181.29009600899,"costPerQuality":0.01050626650459669,"deltaTop":-49.27285638181131,"costVsTop":0.05265947659789131,"calculated":13.78265888205813,"frontier":false},{"modelKey":"magistral-medium-2509","sourceId":"864da2a5-156c-45fd-873c-8923be91914f","slug":"magistral-medium-2509","name":"Magistral Medium 1.2","shortName":"Magistral Medium 1.2","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-09-18","cutoffDate":null,"totalCost":886.34599,"inputCost":667.0898,"outputCost":219.25619,"reasoningCost":198.69339,"answerCost":20.562800000000003,"costPerTask":0.7471451276458294,"inputCostPerTask":0.7018431953438794,"outputCostPerTask":0.04530193230195018,"reasoningCostPerTask":0.029811510105589505,"answerCostPerTask":0.015490422196360685,"timePerTask":205.67041841937663,"intelligence":17.8744831166998,"coding":21.3184040782356,"agentic":1.85567010309278,"mmmu":0.596531791907514,"priceInput1m":2,"priceOutput1m":5,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"864da2a5-156c-45fd-873c-8923be91914f\",\"slug\":\"magistral-medium-2509\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Magistral Medium 1.2\",\"short_name\":\"Magistral Medium 1.2\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-09-18\",\"knowledge_cutoff_date\":null,\"intelligence_index\":17.8744831166998,\"coding_index\":21.3184040782356,\"agentic_index\":1.85567010309278,\"mmmu_pro\":0.596531791907514,\"intelligence_index_cost\":{\"total\":886.34599,\"input\":667.0898,\"nonCacheInput\":23.307618,\"cacheRead\":509.0520154016579,\"cacheWrite\":134.73016659834204,\"output\":219.25619,\"reasoning\":198.69339,\"answer\":20.562800000000003},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.7471451276458294,\"input\":0.7018431953438794,\"nonCacheInput\":0.012615137125766358,\"cacheRead\":0.5452212583491083,\"cacheWrite\":0.14400679986900472,\"output\":0.04530193230195018,\"reasoning\":0.029811510105589505,\"answer\":0.015490422196360685},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.30087250075757577},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.075109441580756},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.3353977078651685},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.003203932291666667},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.008614555085727527},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0021257698863636366},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.008863096428571427},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000549050625},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.012409073125000001}]},\"intelligence_index_time_per_task\":205.67041841937663,\"price_1m_input_tokens\":2,\"price_1m_output_tokens\":5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":13.682852432676057,"costForScoring":0.7471451276458294,"costPenalty":18.73404968634642,"pointsPerK":18313.51356836013,"costPerQuality":0.05460448625913483,"deltaTop":-49.37266283119338,"costVsTop":0.2717065363371166,"calculated":13.682852432676057,"frontier":false},{"modelKey":"deepseek-v3","sourceId":"43fc5506-c5ed-4dee-9b85-962bf7ae3986","slug":"deepseek-v3","name":"DeepSeek V3 (Dec '24)","shortName":"DeepSeek V3 (Dec)","creatorName":"DeepSeek","creatorSlug":"deepseek","releaseDate":"2024-12-26","cutoffDate":null,"totalCost":21.710229570000006,"inputCost":18.775104800000005,"outputCost":2.9351247700000003,"reasoningCost":0,"answerCost":2.9351247700000003,"costPerTask":0.025399514988864336,"inputCostPerTask":0.023384061113711295,"outputCostPerTask":0.0020154538751530385,"reasoningCostPerTask":0,"answerCostPerTask":0.0020154538751530385,"timePerTask":null,"intelligence":14.160584979307,"coding":23.0415106117354,"agentic":1.5807560137457,"mmmu":null,"priceInput1m":0.4,"priceOutput1m":0.89,"activeParams":37,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"43fc5506-c5ed-4dee-9b85-962bf7ae3986\",\"slug\":\"deepseek-v3\",\"model_url\":null,\"hosts_url\":null,\"name\":\"DeepSeek V3 (Dec '24)\",\"short_name\":\"DeepSeek V3 (Dec)\",\"creator_name\":\"DeepSeek\",\"creator_slug\":\"deepseek\",\"release_date\":\"2024-12-26\",\"knowledge_cutoff_date\":null,\"intelligence_index\":14.160584979307,\"coding_index\":23.0415106117354,\"agentic_index\":1.5807560137457,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":21.710229570000006,\"input\":18.775104800000005,\"nonCacheInput\":4.743875200000001,\"cacheRead\":9.805664133979981,\"cacheWrite\":4.225565466020021,\"output\":2.9351247700000003,\"reasoning\":0,\"answer\":2.9351247700000003},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.025399514988864336,\"input\":0.023384061113711295,\"nonCacheInput\":0.002545688046902819,\"cacheRead\":0.014880877107942173,\"cacheWrite\":0.005957495958866304,\"output\":0.0020154538751530385,\"reasoning\":0,\"answer\":0.0020154538751530385},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0013850960000000002},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0036450693213058425},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.01760370438202247},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00010489813078703704},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00008225804448563485},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0000392809816919192},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0001616860535714286},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000007466968749999999},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0023700551062500004}]},\"intelligence_index_time_per_task\":null,\"price_1m_input_tokens\":0.4,\"price_1m_output_tokens\":0.89,\"activeParams\":37,\"is_open_weights\":true,\"reasoning_model\":false}","quality":12.927617201596034,"costForScoring":0.025399514988864336,"costPenalty":4.0482542371950645,"pointsPerK":508971.025913832,"costPerQuality":0.0019647483826894666,"deltaTop":-50.1278980622734,"costVsTop":0.009236778755436655,"calculated":12.927617201596034,"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":101.21140109231865,"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\":101.21140109231865,\"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":false},{"modelKey":"deepseek-v3-0324","sourceId":"75e1c197-f239-4361-a9d6-66dccfead236","slug":"deepseek-v3-0324","name":"DeepSeek V3 0324","shortName":"DeepSeek V3 0324","creatorName":"DeepSeek","creatorSlug":"deepseek","releaseDate":"2025-03-25","cutoffDate":null,"totalCost":137.78945643999998,"inputCost":132.08877768999997,"outputCost":5.70067875,"reasoningCost":0,"answerCost":5.70067875,"costPerTask":0.18953428564807268,"inputCostPerTask":0.1861964116057445,"outputCostPerTask":0.003337874042328135,"reasoningCostPerTask":0,"answerCostPerTask":0.003337874042328135,"timePerTask":null,"intelligence":15.4301213476181,"coding":21.1597482313774,"agentic":1.51202749140893,"mmmu":null,"priceInput1m":1.1949999999999998,"priceOutput1m":1.25,"activeParams":37,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"75e1c197-f239-4361-a9d6-66dccfead236\",\"slug\":\"deepseek-v3-0324\",\"model_url\":null,\"hosts_url\":null,\"name\":\"DeepSeek V3 0324\",\"short_name\":\"DeepSeek V3 0324\",\"creator_name\":\"DeepSeek\",\"creator_slug\":\"deepseek\",\"release_date\":\"2025-03-25\",\"knowledge_cutoff_date\":null,\"intelligence_index\":15.4301213476181,\"coding_index\":21.1597482313774,\"agentic_index\":1.51202749140893,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":137.78945643999998,\"input\":132.08877768999997,\"nonCacheInput\":14.314178439999997,\"cacheRead\":85.45653355215437,\"cacheWrite\":32.31806569784561,\"output\":5.70067875,\"reasoning\":0,\"answer\":5.70067875},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.18953428564807268,\"input\":0.1861964116057445,\"nonCacheInput\":0.0077149801965430455,\"cacheRead\":0.13031160291956084,\"cacheWrite\":0.04816982848964059,\"output\":0.003337874042328135,\"reasoning\":0,\"answer\":0.003337874042328135},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.014029164643939393},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.018874820030068726},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.14844242304307115},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0002805119401041666},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0002296995577502317},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00007922359217171719},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0004404943973214285},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00001940475614583333},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.007138543687499999}]},\"intelligence_index_time_per_task\":null,\"price_1m_input_tokens\":1.1949999999999998,\"price_1m_output_tokens\":1.25,\"activeParams\":37,\"is_open_weights\":true,\"reasoning_model\":false}","quality":12.700632356801476,"costForScoring":0.18953428564807268,"costPenalty":12.77687782752228,"pointsPerK":67009.68277783797,"costPerQuality":0.014923216444933373,"deltaTop":-50.35488290706796,"costVsTop":0.06892597216397701,"calculated":12.700632356801476,"frontier":false},{"modelKey":"nova-2-0-pro","sourceId":"a20ae33a-46e1-41e6-81a0-fe8b00d2e538","slug":"nova-2-0-pro","name":"Nova 2.0 Pro Preview (Non-reasoning)","shortName":"Nova 2.0 Pro Preview","creatorName":"Amazon","creatorSlug":"aws","releaseDate":"2025-11-27","cutoffDate":null,"totalCost":206.39835125,"inputCost":153.08218125,"outputCost":53.31617,"reasoningCost":0,"answerCost":53.31617,"costPerTask":0.24556414020453576,"inputCostPerTask":0.20925236631396815,"outputCostPerTask":0.0363117738905676,"reasoningCostPerTask":0,"answerCostPerTask":0.0363117738905676,"timePerTask":32.80170729082376,"intelligence":14.3557330595446,"coding":20.8606429463171,"agentic":2.85237457044674,"mmmu":null,"priceInput1m":1.25,"priceOutput1m":10,"activeParams":null,"isOpenWeights":false,"isReasoning":false,"rawResultJson":"{\"id\":\"a20ae33a-46e1-41e6-81a0-fe8b00d2e538\",\"slug\":\"nova-2-0-pro\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Nova 2.0 Pro Preview (Non-reasoning)\",\"short_name\":\"Nova 2.0 Pro Preview\",\"creator_name\":\"Amazon\",\"creator_slug\":\"aws\",\"release_date\":\"2025-11-27\",\"knowledge_cutoff_date\":null,\"intelligence_index\":14.3557330595446,\"coding_index\":20.8606429463171,\"agentic_index\":2.85237457044674,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":206.39835125,\"input\":153.08218125,\"nonCacheInput\":14.805647500000001,\"cacheRead\":117.19335825892858,\"cacheWrite\":21.083175491071408,\"output\":53.31617,\"reasoning\":0,\"answer\":53.31617},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.24556414020453576,\"input\":0.20925236631396815,\"nonCacheInput\":0.007998763533806422,\"cacheRead\":0.17350313830013622,\"cacheWrite\":0.02775046448002553,\"output\":0.0363117738905676,\"reasoning\":0,\"answer\":0.0363117738905676},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.031387011363636357},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.022159272981099657},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1799511329588015},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0007967849392361111},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0010081011787534753},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000841036931818182},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0017927243303571428},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0001302903645833333},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00749778515625}]},\"intelligence_index_time_per_task\":32.80170729082376,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":12.689583525436147,"costForScoring":0.24556414020453576,"costPenalty":13.901649469628047,"pointsPerK":51675.23040972804,"costPerQuality":0.019351631179408278,"deltaTop":-50.36593173843329,"costVsTop":0.08930176951539266,"calculated":12.689583525436147,"frontier":false},{"modelKey":"gpt-4-1-mini","sourceId":"9f7c7566-a704-49a2-a383-cb3181da33a4","slug":"gpt-4-1-mini","name":"GPT-4.1 mini","shortName":"GPT-4.1 mini","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2025-04-14","cutoffDate":"2024-05-31","totalCost":68.1882457252249,"inputCost":59.912986525224895,"outputCost":8.2752592,"reasoningCost":0,"answerCost":8.2752592,"costPerTask":0.05779363242556173,"inputCostPerTask":0.05306230230107641,"outputCostPerTask":0.00473133012448532,"reasoningCostPerTask":0,"answerCostPerTask":0.00473133012448532,"timePerTask":42.69019009292721,"intelligence":14.7656334909109,"coding":20.2060792065474,"agentic":1.71821305841924,"mmmu":0.58728323699422,"priceInput1m":0.4,"priceOutput1m":1.6,"activeParams":null,"isOpenWeights":false,"isReasoning":false,"rawResultJson":"{\"id\":\"9f7c7566-a704-49a2-a383-cb3181da33a4\",\"slug\":\"gpt-4-1-mini\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-4.1 mini\",\"short_name\":\"GPT-4.1 mini\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2025-04-14\",\"knowledge_cutoff_date\":\"2024-05-31\",\"intelligence_index\":14.7656334909109,\"coding_index\":20.2060792065474,\"agentic_index\":1.71821305841924,\"mmmu_pro\":0.58728323699422,\"intelligence_index_cost\":{\"total\":68.1882457252249,\"input\":59.912986525224895,\"nonCacheInput\":4.8381108,\"cacheRead\":36.82169889159171,\"cacheWrite\":18.253176833633187,\"output\":8.2752592,\"reasoning\":0,\"answer\":8.2752592},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.05779363242556173,\"input\":0.05306230230107641,\"nonCacheInput\":0.002614104813725431,\"cacheRead\":0.03359937193690182,\"cacheWrite\":0.01684882555044917,\"output\":0.00473133012448532,\"reasoning\":0,\"answer\":0.00473133012448532},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03128835707373016},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.007594916065364107},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.015580408404152177},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0001554101851851852},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00023944223818350328},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00008556148989898991},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0004083167857142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000009095683333333335},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0024321245}]},\"intelligence_index_time_per_task\":42.69019009292721,\"price_1m_input_tokens\":0.4,\"price_1m_output_tokens\":1.6,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":12.22997525195918,"costForScoring":0.05779363242556173,"costPenalty":7.6187999145203396,"pointsPerK":211614.57999220595,"costPerQuality":0.004725572311873933,"deltaTop":-50.825540011910256,"costVsTop":0.021017212195665318,"calculated":12.22997525195918,"frontier":false},{"modelKey":"qwen3-next-80b-a3b-reasoning","sourceId":"c8a79180-7d16-4474-8701-9a77c0baa56a","slug":"qwen3-next-80b-a3b-reasoning","name":"Qwen3 Next 80B A3B (Reasoning)","shortName":"Qwen3 Next 80B A3B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2025-09-11","cutoffDate":null,"totalCost":392.29834,"inputCost":36.071554,"outputCost":356.226786,"reasoningCost":340.34169,"answerCost":15.885096,"costPerTask":0.16240749676309754,"inputCostPerTask":0.03289467010953409,"outputCostPerTask":0.12951282665356345,"reasoningCostPerTask":0.11836843366620856,"answerCostPerTask":0.011144392987354883,"timePerTask":109.96210647310687,"intelligence":16.7202061501106,"coding":17.4187647385213,"agentic":2.06185567010309,"mmmu":null,"priceInput1m":0.5,"priceOutput1m":6,"activeParams":3,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"c8a79180-7d16-4474-8701-9a77c0baa56a\",\"slug\":\"qwen3-next-80b-a3b-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3 Next 80B A3B (Reasoning)\",\"short_name\":\"Qwen3 Next 80B A3B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2025-09-11\",\"knowledge_cutoff_date\":null,\"intelligence_index\":16.7202061501106,\"coding_index\":17.4187647385213,\"agentic_index\":2.06185567010309,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":392.29834,\"input\":36.071554,\"nonCacheInput\":5.807819,\"cacheRead\":19.531510436639767,\"cacheWrite\":10.732224563360232,\"output\":356.226786,\"reasoning\":340.34169,\"answer\":15.885096},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.16240749676309754,\"input\":0.03289467010953409,\"nonCacheInput\":0.0031630848700636297,\"cacheRead\":0.019082677640509707,\"cacheWrite\":0.010648907598960752,\"output\":0.12951282665356345,\"reasoning\":0.11836843366620856,\"answer\":0.011144392987354883},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.04914222765151515},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.02072964475945017},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.060138883895131084},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0036473294270833335},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.010169524762511583},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004121837752525253},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.009282808035714284},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0011051761041666664},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.004070064375}]},\"intelligence_index_time_per_task\":109.96210647310687,\"price_1m_input_tokens\":0.5,\"price_1m_output_tokens\":6,\"activeParams\":3,\"is_open_weights\":true,\"reasoning_model\":true}","quality":12.066942186244999,"costForScoring":0.16240749676309754,"costPenalty":12.10606072489516,"pointsPerK":74300.40131612241,"costPerQuality":0.013458877506533877,"deltaTop":-50.98857307762444,"costVsTop":0.059061053586366145,"calculated":12.066942186244999,"frontier":false},{"modelKey":"llama-4-maverick","sourceId":"922c69c7-9037-43c6-8bcf-a1c555e7f3eb","slug":"llama-4-maverick","name":"Llama 4 Maverick","shortName":"Llama 4 Maverick","creatorName":"Meta","creatorSlug":"meta","releaseDate":"2025-04-05","cutoffDate":"2024-08-01","totalCost":38.21278355670585,"inputCost":34.17524275670585,"outputCost":4.0375407999999995,"reasoningCost":0,"answerCost":4.0375407999999995,"costPerTask":0.031591080063049636,"inputCostPerTask":0.029815546974458755,"outputCostPerTask":0.00177553308859089,"reasoningCostPerTask":0,"answerCostPerTask":0.00177553308859089,"timePerTask":18.84637109628951,"intelligence":14.2657978659374,"coding":16.2773963101678,"agentic":1.30584192439863,"mmmu":0.621387283236994,"priceInput1m":0.35,"priceOutput1m":0.85,"activeParams":17,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"922c69c7-9037-43c6-8bcf-a1c555e7f3eb\",\"slug\":\"llama-4-maverick\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Llama 4 Maverick\",\"short_name\":\"Llama 4 Maverick\",\"creator_name\":\"Meta\",\"creator_slug\":\"meta\",\"release_date\":\"2025-04-05\",\"knowledge_cutoff_date\":\"2024-08-01\",\"intelligence_index\":14.2657978659374,\"coding_index\":16.2773963101678,\"agentic_index\":1.30584192439863,\"mmmu_pro\":0.621387283236994,\"intelligence_index_cost\":{\"total\":38.21278355670585,\"input\":34.17524275670585,\"nonCacheInput\":4.14102255,\"cacheRead\":22.59012727111777,\"cacheWrite\":7.4440929355880785,\"output\":4.0375407999999995,\"reasoning\":0,\"answer\":4.0375407999999995},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.031591080063049636,\"input\":0.029815546974458755,\"nonCacheInput\":0.0022471750842818143,\"cacheRead\":0.020562347210783018,\"cacheWrite\":0.007006024679393917,\"output\":0.00177553308859089,\"reasoning\":0,\"answer\":0.00177553308859089},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.016759332182743114},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.004514322374730665},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.007759537792693712},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00008977180266203702},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00012983371466635774},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000055139094065656565},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00017049580357142855},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000008504922916666666},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0021041423749999996}]},\"intelligence_index_time_per_task\":18.84637109628951,\"price_1m_input_tokens\":0.35,\"price_1m_output_tokens\":0.85,\"activeParams\":17,\"is_open_weights\":true,\"reasoning_model\":false}","quality":10.61634536683461,"costForScoring":0.031591080063049636,"costPenalty":4.995644741927104,"pointsPerK":336055.1568875282,"costPerQuality":0.0029757019926781917,"deltaTop":-52.43916989703483,"costVsTop":0.011488401149219042,"calculated":10.61634536683461,"frontier":false},{"modelKey":"nvidia-nemotron-3-nano-30b-a3b-reasoning","sourceId":"76dcf6ef-39ea-4be0-b693-b88da25b4caf","slug":"nvidia-nemotron-3-nano-30b-a3b-reasoning","name":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","shortName":"NVIDIA Nemotron 3 Nano","creatorName":"NVIDIA","creatorSlug":"nvidia","releaseDate":"2025-12-15","cutoffDate":null,"totalCost":38.9196747,"inputCost":14.285591699999998,"outputCost":24.634083,"reasoningCost":23.9759914,"answerCost":0.6580916000000001,"costPerTask":0.018312323602596187,"inputCostPerTask":0.01295698422883603,"outputCostPerTask":0.005355339373760156,"reasoningCostPerTask":0.004733157506981963,"answerCostPerTask":0.0006221818667781927,"timePerTask":140.6638360951615,"intelligence":14.1772902141795,"coding":14.3709252323484,"agentic":1.99312714776632,"mmmu":null,"priceInput1m":0.05,"priceOutput1m":0.2,"activeParams":3.6,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"76dcf6ef-39ea-4be0-b693-b88da25b4caf\",\"slug\":\"nvidia-nemotron-3-nano-30b-a3b-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)\",\"short_name\":\"NVIDIA Nemotron 3 Nano\",\"creator_name\":\"NVIDIA\",\"creator_slug\":\"nvidia\",\"release_date\":\"2025-12-15\",\"knowledge_cutoff_date\":null,\"intelligence_index\":14.1772902141795,\"coding_index\":14.3709252323484,\"agentic_index\":1.99312714776632,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":38.9196747,\"input\":14.285591699999998,\"nonCacheInput\":0.5891819,\"cacheRead\":10.218873530235125,\"cacheWrite\":3.4775362697648733,\"output\":24.634083,\"reasoning\":23.9759914,\"answer\":0.6580916000000001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.018312323602596187,\"input\":0.01295698422883603,\"nonCacheInput\":0.00031826012441290305,\"cacheRead\":0.009433155368487257,\"cacheWrite\":0.0032055687359358698,\"output\":0.005355339373760156,\"reasoning\":0.004733157506981963,\"answer\":0.0006221818667781927},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.004623464924242424},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.008069928737113402},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.003463152528089887},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00010239105902777777},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0007651598210148286},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000249004292929293},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0005645651339285715},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00012564198125000002},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.000349015125}]},\"intelligence_index_time_per_task\":140.6638360951615,\"price_1m_input_tokens\":0.05,\"price_1m_output_tokens\":0.2,\"activeParams\":3.6,\"is_open_weights\":true,\"reasoning_model\":true}","quality":10.180447531431406,"costForScoring":0.018312323602596187,"costPenalty":2.6274345428313644,"pointsPerK":555934.230541235,"costPerQuality":0.001798773928754919,"deltaTop":-52.87506773243803,"costVsTop":0.006659453209610464,"calculated":10.180447531431406,"frontier":false},{"modelKey":"qwen3-30b-a3b-2507-reasoning","sourceId":"5e0164b3-d902-4bcb-a1b2-83b4f4cd6143","slug":"qwen3-30b-a3b-2507-reasoning","name":"Qwen3 30B A3B 2507 (Reasoning)","shortName":"Qwen3 30B A3B 2507","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2025-07-30","cutoffDate":null,"totalCost":151.6472494,"inputCost":23.1084046,"outputCost":128.5388448,"reasoningCost":120.92009999999999,"answerCost":7.6187448,"costPerTask":0.07145918657495168,"inputCostPerTask":0.02489249496079474,"outputCostPerTask":0.046566691614156934,"reasoningCostPerTask":0.04191128072599758,"answerCostPerTask":0.00465541088815937,"timePerTask":150.4651728039001,"intelligence":14.4377762633027,"coding":12.1098626716604,"agentic":1.78694158075601,"mmmu":null,"priceInput1m":0.2,"priceOutput1m":2.4,"activeParams":3.3,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"5e0164b3-d902-4bcb-a1b2-83b4f4cd6143\",\"slug\":\"qwen3-30b-a3b-2507-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3 30B A3B 2507 (Reasoning)\",\"short_name\":\"Qwen3 30B A3B 2507\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2025-07-30\",\"knowledge_cutoff_date\":null,\"intelligence_index\":14.4377762633027,\"coding_index\":12.1098626716604,\"agentic_index\":1.78694158075601,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":151.6472494,\"input\":23.1084046,\"nonCacheInput\":2.34722,\"cacheRead\":15.471445508945678,\"cacheWrite\":5.289739091054322,\"output\":128.5388448,\"reasoning\":120.92009999999999,\"answer\":7.6187448},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.07145918657495168,\"input\":0.02489249496079474,\"nonCacheInput\":0.0012791262173016632,\"cacheRead\":0.017687960182830274,\"cacheWrite\":0.005925408560662804,\"output\":0.046566691614156934,\"reasoning\":0.04191128072599758,\"answer\":0.00465541088815937},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.028437679242424244},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.003955168556701031},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.027830194382022472},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0011140605324074073},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.003751006197868397},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001014227840909091},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.003439978214285714},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00034275785833333335},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0015741137499999999}]},\"intelligence_index_time_per_task\":150.4651728039001,\"price_1m_input_tokens\":0.2,\"price_1m_output_tokens\":2.4,\"activeParams\":3.3,\"is_open_weights\":true,\"reasoning_model\":true}","quality":9.44486017190637,"costForScoring":0.07145918657495168,"costPenalty":8.540580682893074,"pointsPerK":132171.3921554355,"costPerQuality":0.007565933775018313,"deltaTop":-53.61065509196307,"costVsTop":0.02598682284782518,"calculated":9.44486017190637,"frontier":false},{"modelKey":"ministral-3-14b","sourceId":"713fae11-c75c-4f10-ae2c-8e4074cd58af","slug":"ministral-3-14b","name":"Ministral 3 14B","shortName":"Ministral 3 14B","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-12-02","cutoffDate":null,"totalCost":119.5711532,"inputCost":116.5773202,"outputCost":2.9938330000000004,"reasoningCost":0,"answerCost":2.9938330000000004,"costPerTask":0.1491862542281139,"inputCostPerTask":0.14683707189337664,"outputCostPerTask":0.0023491823347372804,"reasoningCostPerTask":0,"answerCostPerTask":0.0023491823347372804,"timePerTask":159.2138589013754,"intelligence":11.0525122563915,"coding":14.3622555139409,"agentic":2.19931271477663,"mmmu":0.498265895953757,"priceInput1m":0.2,"priceOutput1m":0.2,"activeParams":null,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"713fae11-c75c-4f10-ae2c-8e4074cd58af\",\"slug\":\"ministral-3-14b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Ministral 3 14B\",\"short_name\":\"Ministral 3 14B\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-12-02\",\"knowledge_cutoff_date\":null,\"intelligence_index\":11.0525122563915,\"coding_index\":14.3622555139409,\"agentic_index\":2.19931271477663,\"mmmu_pro\":0.498265895953757,\"intelligence_index_cost\":{\"total\":119.5711532,\"input\":116.5773202,\"nonCacheInput\":2.4527068,\"cacheRead\":62.45311985117297,\"cacheWrite\":51.67149354882703,\"output\":2.9938330000000004,\"reasoning\":0,\"answer\":2.9938330000000004},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.1491862542281139,\"input\":0.14683707189337664,\"nonCacheInput\":0.00133201953115835,\"cacheRead\":0.07963236643592653,\"cacheWrite\":0.06587268592629175,\"output\":0.0023491823347372804,\"reasoning\":0,\"answer\":0.0023491823347372804},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03986575984848485},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.008567567182130585},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.09924978089887641},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00006229079861111111},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00008348225208526415},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00001602241161616162},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00015496785714285715},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0000042514791666666665},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0011821315000000003}]},\"intelligence_index_time_per_task\":159.2138589013754,\"price_1m_input_tokens\":0.2,\"price_1m_output_tokens\":0.2,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":false}","quality":9.204693495036343,"costForScoring":0.1491862542281139,"costPenalty":11.737288098129849,"pointsPerK":61699.34048321815,"costPerQuality":0.016207628674280466,"deltaTop":-53.85082176883309,"costVsTop":0.054253021140819334,"calculated":9.204693495036343,"frontier":false},{"modelKey":"magistral-small-2509","sourceId":"70152cb0-fb36-4732-a925-89ef40994be1","slug":"magistral-small-2509","name":"Magistral Small 1.2","shortName":"Magistral Small 1.2","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-09-17","cutoffDate":null,"totalCost":294.64357249999995,"inputCost":246.53219449999995,"outputCost":48.111378,"reasoningCost":39.9438465,"answerCost":8.167531499999999,"costPerTask":0.2539985763538183,"inputCostPerTask":0.23906013152574002,"outputCostPerTask":0.014938444828078304,"reasoningCostPerTask":0.007902667902867701,"answerCostPerTask":0.007035776925210604,"timePerTask":115.2400494705337,"intelligence":11.2923034993806,"coding":14.7246497433763,"agentic":1.44329896907216,"mmmu":0.554913294797688,"priceInput1m":0.5,"priceOutput1m":1.5,"activeParams":null,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"70152cb0-fb36-4732-a925-89ef40994be1\",\"slug\":\"magistral-small-2509\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Magistral Small 1.2\",\"short_name\":\"Magistral Small 1.2\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-09-17\",\"knowledge_cutoff_date\":null,\"intelligence_index\":11.2923034993806,\"coding_index\":14.7246497433763,\"agentic_index\":1.44329896907216,\"mmmu_pro\":0.554913294797688,\"intelligence_index_cost\":{\"total\":294.64357249999995,\"input\":246.53219449999995,\"nonCacheInput\":5.8156105,\"cacheRead\":192.9885152154131,\"cacheWrite\":47.728068784586874,\"output\":48.111378,\"reasoning\":39.9438465,\"answer\":8.167531499999999},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.2539985763538183,\"input\":0.23906013152574002,\"nonCacheInput\":0.003150628576652807,\"cacheRead\":0.18863367647212004,\"cacheWrite\":0.04727582647696714,\"output\":0.014938444828078304,\"reasoning\":0.007902667902867701,\"answer\":0.007035776925210604},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.1428814053030303},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.01127674355670103},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.09183674719101122},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0008219010416666665},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0018817296107506954},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00037619333964646463},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0019433066964285714},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000008821802083333334},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0029717278125000004}]},\"intelligence_index_time_per_task\":115.2400494705337,\"price_1m_input_tokens\":0.5,\"price_1m_output_tokens\":1.5,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":true}","quality":9.153417403943019,"costForScoring":0.2539985763538183,"costPenalty":14.048312824332703,"pointsPerK":36037.27837904245,"costPerQuality":0.027749043351219107,"deltaTop":-53.90209785992642,"costVsTop":0.0923690336214961,"calculated":9.153417403943019,"frontier":false},{"modelKey":"mistral-small-3-2","sourceId":"43da3718-3d6e-40dd-901a-05664179ff7f","slug":"mistral-small-3-2","name":"Mistral Small 3.2","shortName":"Mistral Small 3.2","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-06-20","cutoffDate":null,"totalCost":127.5115878,"inputCost":124.9936353,"outputCost":2.5179525,"reasoningCost":0,"answerCost":2.5179525,"costPerTask":0.12378644187922402,"inputCostPerTask":0.12136605291913355,"outputCostPerTask":0.0024203889600904614,"reasoningCostPerTask":0,"answerCostPerTask":0.0024203889600904614,"timePerTask":53.41934620901343,"intelligence":10.557101536401,"coding":12.5416146483562,"agentic":1.99312714776632,"mmmu":0.479768786127168,"priceInput1m":0.1,"priceOutput1m":0.3,"activeParams":null,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"43da3718-3d6e-40dd-901a-05664179ff7f\",\"slug\":\"mistral-small-3-2\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Mistral Small 3.2\",\"short_name\":\"Mistral Small 3.2\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-06-20\",\"knowledge_cutoff_date\":null,\"intelligence_index\":10.557101536401,\"coding_index\":12.5416146483562,\"agentic_index\":1.99312714776632,\"mmmu_pro\":0.479768786127168,\"intelligence_index_cost\":{\"total\":127.5115878,\"input\":124.9936353,\"nonCacheInput\":1.1934921,\"cacheRead\":32.36813113430005,\"cacheWrite\":91.43201206569995,\"output\":2.5179525,\"reasoning\":0,\"answer\":2.5179525},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.12378644187922402,\"input\":0.12136605291913355,\"nonCacheInput\":0.0006473324427638098,\"cacheRead\":0.03146228522824433,\"cacheWrite\":0.0892564352481254,\"output\":0.0024203889600904614,\"reasoning\":0,\"answer\":0.0024203889600904614},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.07461911977272728},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0024356683848797255},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.04600281779026216},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00003034568865740741},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00001987068466172382},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000012021874999999999},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00006645071428571428},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00000200559375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0005981413750000001}]},\"intelligence_index_time_per_task\":53.41934620901343,\"price_1m_input_tokens\":0.1,\"price_1m_output_tokens\":0.3,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":false}","quality":8.36394777750784,"costForScoring":0.12378644187922402,"costPenalty":10.926730797447659,"pointsPerK":67567.559504363,"costPerQuality":0.01480000176616454,"deltaTop":-54.6915674863616,"costVsTop":0.04501613424753958,"calculated":8.36394777750784,"frontier":false},{"modelKey":"llama-3-3-instruct-70b","sourceId":"976cc8ad-7904-4056-83c5-960181f47d5f","slug":"llama-3-3-instruct-70b","name":"Llama 3.3 Instruct 70B","shortName":"Llama 3.3 70B","creatorName":"Meta","creatorSlug":"meta","releaseDate":"2024-12-06","cutoffDate":"2023-12-01","totalCost":77.97532765999999,"inputCost":75.29644796,"outputCost":2.6788797,"reasoningCost":0,"answerCost":2.6788797,"costPerTask":0.07982308899181391,"inputCostPerTask":0.07862608734960927,"outputCostPerTask":0.0011970016422046354,"reasoningCostPerTask":0,"answerCostPerTask":0.0011970016422046354,"timePerTask":19.685000358426237,"intelligence":9.40307621697656,"coding":11.9264981273408,"agentic":0.34364261168385,"mmmu":null,"priceInput1m":0.58,"priceOutput1m":0.71,"activeParams":null,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"976cc8ad-7904-4056-83c5-960181f47d5f\",\"slug\":\"llama-3-3-instruct-70b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Llama 3.3 Instruct 70B\",\"short_name\":\"Llama 3.3 70B\",\"creator_name\":\"Meta\",\"creator_slug\":\"meta\",\"release_date\":\"2024-12-06\",\"knowledge_cutoff_date\":\"2023-12-01\",\"intelligence_index\":9.40307621697656,\"coding_index\":11.9264981273408,\"agentic_index\":0.34364261168385,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":77.97532765999999,\"input\":75.29644796,\"nonCacheInput\":6.92729844,\"cacheRead\":54.52714813736056,\"cacheWrite\":13.842001382639433,\"output\":2.6788797,\"reasoning\":0,\"answer\":2.6788797},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.07982308899181391,\"input\":0.07862608734960927,\"nonCacheInput\":0.0037102166037099975,\"cacheRead\":0.05964230131378653,\"cacheWrite\":0.015273569432112739,\"output\":0.0011970016422046354,\"reasoning\":0,\"answer\":0.0011970016422046354},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03378069502272728},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0035122814604810998},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.03859394501872659},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00014763606770833333},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00010215093257645969},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000041709289772727274},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00019340355357142856},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000011698465},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00343956918125}]},\"intelligence_index_time_per_task\":19.685000358426237,\"price_1m_input_tokens\":0.58,\"price_1m_output_tokens\":0.71,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":false}","quality":7.224405652000403,"costForScoring":0.07982308899181391,"costPenalty":9.021285300897208,"pointsPerK":90505.2127554383,"costPerQuality":0.011049087334916096,"deltaTop":-55.83110961186904,"costVsTop":0.029028436681415654,"calculated":7.224405652000403,"frontier":false},{"modelKey":"ministral-3-8b","sourceId":"9741f3c2-cbb1-4a3f-99ee-7bd7384d9038","slug":"ministral-3-8b","name":"Ministral 3 8B","shortName":"Ministral 3 8B","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-12-02","cutoffDate":null,"totalCost":113.47784744999998,"inputCost":110.66038259999999,"outputCost":2.81746485,"reasoningCost":0,"answerCost":2.81746485,"costPerTask":0.18482442028714433,"inputCostPerTask":0.18247149581360883,"outputCostPerTask":0.002352924473535504,"reasoningCostPerTask":0,"answerCostPerTask":0.002352924473535504,"timePerTask":175.18759941249587,"intelligence":8.95728282101135,"coding":9.69101123595506,"agentic":1.23711340206186,"mmmu":0.459537572254335,"priceInput1m":0.15,"priceOutput1m":0.15,"activeParams":null,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"9741f3c2-cbb1-4a3f-99ee-7bd7384d9038\",\"slug\":\"ministral-3-8b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Ministral 3 8B\",\"short_name\":\"Ministral 3 8B\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-12-02\",\"knowledge_cutoff_date\":null,\"intelligence_index\":8.95728282101135,\"coding_index\":9.69101123595506,\"agentic_index\":1.23711340206186,\"mmmu_pro\":0.459537572254335,\"intelligence_index_cost\":{\"total\":113.47784744999998,\"input\":110.66038259999999,\"nonCacheInput\":1.8611035499999997,\"cacheRead\":83.22117901750669,\"cacheWrite\":25.578100032493314,\"output\":2.81746485,\"reasoning\":0,\"answer\":2.81746485},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.18482442028714433,\"input\":0.18247149581360883,\"nonCacheInput\":0.0010182412169369912,\"cacheRead\":0.13994040659284493,\"cacheWrite\":0.041512848003826916,\"output\":0.002352924473535504,\"reasoning\":0,\"answer\":0.002352924473535504},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.011470351136363636},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.004945307989690721},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.16722497415730334},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00004603368055555555},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00007718245481927711},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000011853314393939396},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00015666348214285713},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000003246509375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0008888075625}]},\"intelligence_index_time_per_task\":175.18759941249587,\"price_1m_input_tokens\":0.15,\"price_1m_output_tokens\":0.15,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":false}","quality":6.628469153009423,"costForScoring":0.18482442028714433,"costPenalty":12.66759352681057,"pointsPerK":35863.6003982125,"costPerQuality":0.027883424667252365,"deltaTop":-56.42704611086002,"costVsTop":0.0672131841707471,"calculated":6.628469153009423,"frontier":false},{"modelKey":"llama-4-scout","sourceId":"adf9a85e-abc3-4f28-937b-db6655cc5238","slug":"llama-4-scout","name":"Llama 4 Scout","shortName":"Llama 4 Scout","creatorName":"Meta","creatorSlug":"meta","releaseDate":"2025-04-05","cutoffDate":"2024-08-01","totalCost":11.38710679,"inputCost":8.669219530000001,"outputCost":2.7178872600000004,"reasoningCost":0,"answerCost":2.7178872600000004,"costPerTask":0.008506397458326823,"inputCostPerTask":0.007681930975096026,"outputCostPerTask":0.0008244664832307974,"reasoningCostPerTask":0,"answerCostPerTask":0.0008244664832307974,"timePerTask":12.743604908941974,"intelligence":10.0416226283387,"coding":8.16817519766958,"agentic":1.09965635738832,"mmmu":0.529479768786127,"priceInput1m":0.17,"priceOutput1m":0.66,"activeParams":17,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"adf9a85e-abc3-4f28-937b-db6655cc5238\",\"slug\":\"llama-4-scout\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Llama 4 Scout\",\"short_name\":\"Llama 4 Scout\",\"creator_name\":\"Meta\",\"creator_slug\":\"meta\",\"release_date\":\"2025-04-05\",\"knowledge_cutoff_date\":\"2024-08-01\",\"intelligence_index\":10.0416226283387,\"coding_index\":8.16817519766958,\"agentic_index\":1.09965635738832,\"mmmu_pro\":0.529479768786127,\"intelligence_index_cost\":{\"total\":11.38710679,\"input\":8.669219530000001,\"nonCacheInput\":2.0501107500000004,\"cacheRead\":5.039090365346465,\"cacheWrite\":1.5800184146535359,\"output\":2.7178872600000004,\"reasoning\":0,\"answer\":2.7178872600000004},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.008506397458326823,\"input\":0.007681930975096026,\"nonCacheInput\":0.001094422342623377,\"cacheRead\":0.005000039818464343,\"cacheWrite\":0.0015874688140083042,\"output\":0.0008244664832307974,\"reasoning\":0,\"answer\":0.0008244664832307974},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0030227390151515154},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0014591576288659792},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.0026663013857677904},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00007207049768518518},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00010906062615848008},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00003884900252525253},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00011322097321428573},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000005453666458333335},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0010195446625}]},\"intelligence_index_time_per_task\":12.743604908941974,\"price_1m_input_tokens\":0.17,\"price_1m_output_tokens\":0.66,\"activeParams\":17,\"is_open_weights\":true,\"reasoning_model\":false}","quality":6.436484727798867,"costForScoring":0.008506397458326823,"costPenalty":0,"pointsPerK":756664.000163578,"costPerQuality":0.0013215905603858739,"deltaTop":-56.61903053607057,"costVsTop":0.0030934335306332028,"calculated":6.436484727798867,"frontier":true},{"modelKey":"ministral-3-3b","sourceId":"66f4ce73-9a9b-4b49-9c6e-bedb9bfdc720","slug":"ministral-3-3b","name":"Ministral 3 3B","shortName":"Ministral 3 3B","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2025-12-02","cutoffDate":null,"totalCost":91.7844799,"inputCost":89.0492161,"outputCost":2.7352638000000002,"reasoningCost":0,"answerCost":2.7352638000000002,"costPerTask":0.12619350182313843,"inputCostPerTask":0.12414934273719067,"outputCostPerTask":0.0020441590859477435,"reasoningCostPerTask":0,"answerCostPerTask":0.0020441590859477435,"timePerTask":113.1475970843055,"intelligence":6.80100025864863,"coding":4.78395061728395,"agentic":1.5807560137457,"mmmu":0.380924855491329,"priceInput1m":0.1,"priceOutput1m":0.1,"activeParams":null,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"66f4ce73-9a9b-4b49-9c6e-bedb9bfdc720\",\"slug\":\"ministral-3-3b\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Ministral 3 3B\",\"short_name\":\"Ministral 3 3B\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2025-12-02\",\"knowledge_cutoff_date\":null,\"intelligence_index\":6.80100025864863,\"coding_index\":4.78395061728395,\"agentic_index\":1.5807560137457,\"mmmu_pro\":0.380924855491329,\"intelligence_index_cost\":{\"total\":91.7844799,\"input\":89.0492161,\"nonCacheInput\":1.2819872,\"cacheRead\":63.199249838154266,\"cacheWrite\":24.567979061845733,\"output\":2.7352638000000002,\"reasoning\":0,\"answer\":2.7352638000000002},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.12619350182313843,\"input\":0.12414934273719067,\"nonCacheInput\":0.0007059897267287182,\"cacheRead\":0.08916587107495998,\"cacheWrite\":0.03427748193550199,\"output\":0.0020441590859477435,\"reasoning\":0,\"answer\":0.0020441590859477435},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.02550046954545455},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0037415682989690724},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.09607976329588014},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.000037646759259259256},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00006086507182576461},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000009963478535353537},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0001686874107142857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0000023587125},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0005921792500000001}]},\"intelligence_index_time_per_task\":113.1475970843055,\"price_1m_input_tokens\":0.1,\"price_1m_output_tokens\":0.1,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":false}","quality":4.388568963226094,"costForScoring":0.12619350182313843,"costPenalty":11.010369920316258,"pointsPerK":34776.50512763106,"costPerQuality":0.028755045865878785,"deltaTop":-58.666946300643346,"costVsTop":0.045891484826586414,"calculated":4.388568963226094,"frontier":false}]}