{"run":{"id":949,"source_url":"https://artificialanalysis.ai/models","status":"success","started_at":"2026-07-15T11:00:58.585Z","completed_at":"2026-07-15T13:00:59.600Z","duration_ms":2629,"http_status":200,"html_bytes":1348348,"html_sha256":"6cbaec5df5b40181943ccf42451df9b95801012b37fb2c54b1c000dc9a6e915f","html_gzip_bytes":148808,"raw_html_encoding":"pruned","parser_version":"aa-next-rsc-manifest-aes-gcm-v4","model_count":28,"result_count":28,"error":null},"options":{"mode":"combined","calc":"raw","sort":"score","costWeight":10,"costFloor":0.01,"costPower":1,"frontierOnly":false,"frontierMetric":"cost","limit":100},"effectiveSortBy":"score","topQualityModel":{"modelKey":"gpt-5-6-sol","sourceId":"d93edfe8-bf35-49ad-b56e-b18116142a1c","slug":"gpt-5-6-sol","name":"GPT-5.6 Sol (max)","shortName":"GPT-5.6 Sol (max)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":2824.1811935690976,"inputCost":721.6095335690973,"outputCost":2102.57166,"reasoningCost":1903.65387,"answerCost":198.91779,"costPerTask":1.0373301565994435,"inputCostPerTask":0.5769395891879086,"outputCostPerTask":0.4603905674115349,"reasoningCostPerTask":0.3022853845225849,"answerCostPerTask":0.15810518288894992,"timePerTask":244.9484235724925,"intelligence":58.889831189723,"coding":77.3880739353586,"agentic":54.0035635738832,"mmmu":0.834104046242775,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"d93edfe8-bf35-49ad-b56e-b18116142a1c\",\"slug\":\"gpt-5-6-sol\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Sol (max)\",\"short_name\":\"GPT-5.6 Sol (max)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":58.889831189723,\"coding_index\":77.3880739353586,\"agentic_index\":54.0035635738832,\"mmmu_pro\":0.834104046242775,\"intelligence_index_cost\":{\"total\":2824.1811935690976,\"input\":721.6095335690973,\"nonCacheInput\":60.973839999999996,\"cacheRead\":470.423742407035,\"cacheWrite\":190.21195116206226,\"output\":2102.57166,\"reasoning\":1903.65387,\"answer\":198.91779},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.0373301565994435,\"input\":0.5769395891879086,\"nonCacheInput\":0.032056685117526525,\"cacheRead\":0.37980914031185004,\"cacheWrite\":0.165073763758532,\"output\":0.4603905674115349,\"reasoning\":0.3022853845225849,\"answer\":0.15810518288894992},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.5822473800503873},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.13468492177295008},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.12545736509152094},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.009765866608796296},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.05027046860518999},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.006837875631313131},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.08031500446428572},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.015995899375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.031755375}]},\"intelligence_index_time_per_task\":244.9484235724925,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":63.42715623298826,"costForScoring":1.0373301565994435,"costPenalty":20.159170036107348,"pointsPerK":61144.61806539394,"costPerQuality":0.01635466917023676,"deltaTop":0,"costVsTop":1,"calculated":63.42715623298826,"frontier":true},"rows":[{"modelKey":"gpt-5-6-sol","sourceId":"d93edfe8-bf35-49ad-b56e-b18116142a1c","slug":"gpt-5-6-sol","name":"GPT-5.6 Sol (max)","shortName":"GPT-5.6 Sol (max)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":2824.1811935690976,"inputCost":721.6095335690973,"outputCost":2102.57166,"reasoningCost":1903.65387,"answerCost":198.91779,"costPerTask":1.0373301565994435,"inputCostPerTask":0.5769395891879086,"outputCostPerTask":0.4603905674115349,"reasoningCostPerTask":0.3022853845225849,"answerCostPerTask":0.15810518288894992,"timePerTask":244.9484235724925,"intelligence":58.889831189723,"coding":77.3880739353586,"agentic":54.0035635738832,"mmmu":0.834104046242775,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"d93edfe8-bf35-49ad-b56e-b18116142a1c\",\"slug\":\"gpt-5-6-sol\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Sol (max)\",\"short_name\":\"GPT-5.6 Sol (max)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":58.889831189723,\"coding_index\":77.3880739353586,\"agentic_index\":54.0035635738832,\"mmmu_pro\":0.834104046242775,\"intelligence_index_cost\":{\"total\":2824.1811935690976,\"input\":721.6095335690973,\"nonCacheInput\":60.973839999999996,\"cacheRead\":470.423742407035,\"cacheWrite\":190.21195116206226,\"output\":2102.57166,\"reasoning\":1903.65387,\"answer\":198.91779},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.0373301565994435,\"input\":0.5769395891879086,\"nonCacheInput\":0.032056685117526525,\"cacheRead\":0.37980914031185004,\"cacheWrite\":0.165073763758532,\"output\":0.4603905674115349,\"reasoning\":0.3022853845225849,\"answer\":0.15810518288894992},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.5822473800503873},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.13468492177295008},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.12545736509152094},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.009765866608796296},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.05027046860518999},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.006837875631313131},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.08031500446428572},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.015995899375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.031755375}]},\"intelligence_index_time_per_task\":244.9484235724925,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":63.42715623298826,"costForScoring":1.0373301565994435,"costPenalty":20.159170036107348,"pointsPerK":61144.61806539394,"costPerQuality":0.01635466917023676,"deltaTop":0,"costVsTop":1,"calculated":63.42715623298826,"frontier":true},{"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":309.220120930251,"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\":309.220120930251,\"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":-0.37164096911882183,"costVsTop":2.650866634299942,"calculated":63.05551526386944,"frontier":false},{"modelKey":"gpt-5-6-terra","sourceId":"bcf8db0a-3bb6-4d82-9516-0f57370c85a6","slug":"gpt-5-6-terra","name":"GPT-5.6 Terra (max)","shortName":"GPT-5.6 Terra (max)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":1753.9430217187164,"inputCost":321.30323671871633,"outputCost":1432.639785,"reasoningCost":1340.054355,"answerCost":92.58543,"costPerTask":0.5544595173072254,"inputCostPerTask":0.26391258942341755,"outputCostPerTask":0.29054692788380787,"reasoningCostPerTask":0.21275887641723704,"answerCostPerTask":0.07778805146657078,"timePerTask":132.09091661966525,"intelligence":54.9528567569231,"coding":76.6550492440005,"agentic":47.3835257731959,"mmmu":0.806936416184971,"priceInput1m":2.5,"priceOutput1m":15,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"bcf8db0a-3bb6-4d82-9516-0f57370c85a6\",\"slug\":\"gpt-5-6-terra\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Terra (max)\",\"short_name\":\"GPT-5.6 Terra (max)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":54.9528567569231,\"coding_index\":76.6550492440005,\"agentic_index\":47.3835257731959,\"mmmu_pro\":0.806936416184971,\"intelligence_index_cost\":{\"total\":1753.9430217187164,\"input\":321.30323671871633,\"nonCacheInput\":48.7876975,\"cacheRead\":187.56417023098118,\"cacheWrite\":84.95136898773518,\"output\":1432.639785,\"reasoning\":1340.054355,\"answer\":92.58543},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.5544595173072254,\"input\":0.26391258942341755,\"nonCacheInput\":0.01888942270065116,\"cacheRead\":0.16534451881188975,\"cacheWrite\":0.07967864791087664,\"output\":0.29054692788380787,\"reasoning\":0.21275887641723704,\"answer\":0.07778805146657078},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.2399004192326113},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.06585795417904476},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.11941945162408484},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.011915960648148146},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.03650495945319741},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00570076388888889},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.04753184375},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.010990127031250001},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0166380375}]},\"intelligence_index_time_per_task\":132.09091661966525,\"price_1m_input_tokens\":2.5,\"price_1m_output_tokens\":15,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":59.66381059137317,"costForScoring":0.5544595173072254,"costPenalty":17.43869842546669,"pointsPerK":107607.15386604775,"costPerQuality":0.009293062441227901,"deltaTop":-3.763345641615089,"costVsTop":0.5345063129417199,"calculated":59.66381059137317,"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":429.41546695854834,"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\":429.41546695854834,\"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":-4.386756253725963,"costVsTop":1.732545337124926,"calculated":59.0403999792623,"frontier":false},{"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":2777.91267321098,"inputCost":608.8605932109801,"outputCost":2169.05208,"reasoningCost":2037.2752500000001,"answerCost":131.77683,"costPerTask":0.9924637781010264,"inputCostPerTask":0.5105294976772461,"outputCostPerTask":0.4819342804237804,"reasoningCostPerTask":0.37475954041009674,"answerCostPerTask":0.10717474001368364,"timePerTask":231.533198704953,"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\":2777.91267321098,\"input\":608.8605932109801,\"nonCacheInput\":62.47511,\"cacheRead\":134.5888774210022,\"cacheWrite\":411.7966057899779,\"output\":2169.05208,\"reasoning\":2037.2752500000001,\"answer\":131.77683},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.9924637781010264,\"input\":0.5105294976772461,\"nonCacheInput\":0.0318362333929463,\"cacheRead\":0.11809864721018444,\"cacheWrite\":0.3605946170741154,\"output\":0.4819342804237804,\"reasoning\":0.37475954041009674,\"answer\":0.10717474001368364},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.35063300982938234},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.1914720217137599},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.2277409868190616},{\"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\":231.533198704953,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":58.19995405971696,"costForScoring":0.9924637781010264,"costPenalty":19.967146653012374,"pointsPerK":58641.892373217255,"costPerQuality":0.01705265569595972,"deltaTop":-5.227202173271301,"costVsTop":0.956748217322152,"calculated":58.19995405971696,"frontier":false},{"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":126.39450239779705,"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\":126.39450239779705,\"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":-6.1052772151341514,"costVsTop":0.2998889288536858,"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":585.0783353470767,"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\":585.0783353470767,\"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":-6.230591468687962,"costVsTop":1.4705303208606215,"calculated":57.1965647643003,"frontier":false},{"modelKey":"gpt-5-6-luna","sourceId":"426d24c8-49ae-482a-b4a8-20f1c53f21c1","slug":"gpt-5-6-luna","name":"GPT-5.6 Luna (max)","shortName":"GPT-5.6 Luna (max)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":870.2972898705949,"inputCost":120.23017987059492,"outputCost":750.06711,"reasoningCost":714.989334,"answerCost":35.077776,"costPerTask":0.20941332352935085,"inputCostPerTask":0.09594129198465387,"outputCostPerTask":0.11347203154469693,"reasoningCostPerTask":0.08343309665608682,"answerCostPerTask":0.030038934888610133,"timePerTask":85.12472271271676,"intelligence":51.2359331798034,"coding":71.4480163684284,"agentic":45.5974982817869,"mmmu":0.785549132947977,"priceInput1m":1,"priceOutput1m":6,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"426d24c8-49ae-482a-b4a8-20f1c53f21c1\",\"slug\":\"gpt-5-6-luna\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Luna (max)\",\"short_name\":\"GPT-5.6 Luna (max)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":51.2359331798034,\"coding_index\":71.4480163684284,\"agentic_index\":45.5974982817869,\"mmmu_pro\":0.785549132947977,\"intelligence_index_cost\":{\"total\":870.2972898705949,\"input\":120.23017987059492,\"nonCacheInput\":22.5512,\"cacheRead\":68.95756696777435,\"cacheWrite\":28.721412902820557,\"output\":750.06711,\"reasoning\":714.989334,\"answer\":35.077776},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.20941332352935085,\"input\":0.09594129198465387,\"nonCacheInput\":0.008057825371244023,\"cacheRead\":0.06228959558577041,\"cacheWrite\":0.025593871027639426,\"output\":0.11347203154469693,\"reasoning\":0.08343309665608682,\"answer\":0.030038934888610133},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0851974417091458},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.021194712676832705},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.04410638812488613},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0038628796296296293},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.01875303515987025},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0030966871843434345},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.019788399107142855},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.006876623687500001},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00653715625}]},\"intelligence_index_time_per_task\":85.12472271271676,\"price_1m_input_tokens\":1,\"price_1m_output_tokens\":6,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":56.093815943339564,"costForScoring":0.20941332352935085,"costPenalty":13.210043093924906,"pointsPerK":267861.73390480375,"costPerQuality":0.003733269345428015,"deltaTop":-7.333340289648696,"costVsTop":0.20187721546228418,"calculated":56.093815943339564,"frontier":true},{"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":924.7118407048374,"inputCost":305.5529399048374,"outputCost":619.1589008,"reasoningCost":586.2232948,"answerCost":32.935606,"costPerTask":0.46828242379214147,"inputCostPerTask":0.28000250264461835,"outputCostPerTask":0.18827992114752315,"reasoningCostPerTask":0.16148805597970656,"answerCostPerTask":0.026791865167816648,"timePerTask":236.44452665892234,"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\":924.7118407048374,\"input\":305.5529399048374,\"nonCacheInput\":17.707790799999998,\"cacheRead\":104.4067244532827,\"cacheWrite\":183.4384246515547,\"output\":619.1589008,\"reasoning\":586.2232948,\"answer\":32.935606},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.46828242379214147,\"input\":0.28000250264461835,\"nonCacheInput\":0.009786523802333615,\"cacheRead\":0.09827654076003836,\"cacheWrite\":0.17193943808224635,\"output\":0.18827992114752315,\"reasoning\":0.16148805597970656,\"answer\":0.026791865167816648},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.20301321567369693},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.053768523798438286},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.13817888373441067},{\"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\":236.44452665892234,\"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":0.46828242379214147,"costPenalty":16.70507857561421,"pointsPerK":115953.96510149115,"costPerQuality":0.008624112156274509,"deltaTop":-9.127952406952595,"costVsTop":0.4514304542415466,"calculated":54.299203826035665,"frontier":false},{"modelKey":"muse-spark-1-1","sourceId":"d61493e2-43ff-460c-9054-eaf6ba317360","slug":"muse-spark-1-1","name":"Muse Spark 1.1 (xhigh)","shortName":"Muse Spark 1.1 (xhigh)","creatorName":"Meta","creatorSlug":"meta","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":548.07210067,"inputCost":150.47064792,"outputCost":397.60145275,"reasoningCost":360.0511685,"answerCost":37.550284250000004,"costPerTask":0.2610220700233032,"inputCostPerTask":0.16917823348099445,"outputCostPerTask":0.09184383654230872,"reasoningCostPerTask":0.06432170980229805,"answerCostPerTask":0.027522126740010682,"timePerTask":179.6443052835513,"intelligence":50.6229899483333,"coding":71.3409453460951,"agentic":37.5402130584192,"mmmu":null,"priceInput1m":1.25,"priceOutput1m":4.25,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"d61493e2-43ff-460c-9054-eaf6ba317360\",\"slug\":\"muse-spark-1-1\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Muse Spark 1.1 (xhigh)\",\"short_name\":\"Muse Spark 1.1 (xhigh)\",\"creator_name\":\"Meta\",\"creator_slug\":\"meta\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":50.6229899483333,\"coding_index\":71.3409453460951,\"agentic_index\":37.5402130584192,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":548.07210067,\"input\":150.47064792,\"nonCacheInput\":16.668215,\"cacheRead\":71.85111829499999,\"cacheWrite\":61.951314625000016,\"output\":397.60145275,\"reasoning\":360.0511685,\"answer\":37.550284250000004},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.2610220700233032,\"input\":0.16917823348099445,\"nonCacheInput\":0.008335214463509147,\"cacheRead\":0.089173670716431,\"cacheWrite\":0.07166934830105434,\"output\":0.09184383654230872,\"reasoning\":0.06432170980229805,\"answer\":0.027522126740010682},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.04803190751136364},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.04208295806701032},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.11956379693820224},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0025572298177083327},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.013432588783016683},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.001972766493055556},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.02349491049107143},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.001782734265625},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00810317765625}]},\"intelligence_index_time_per_task\":179.6443052835513,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":4.25,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":53.168049450949205,"costForScoring":0.2610220700233032,"costPenalty":14.166772294996306,"pointsPerK":203691.77765773804,"costPerQuality":0.004909378333770023,"deltaTop":-10.259106782039055,"costVsTop":0.2516287301228964,"calculated":53.168049450949205,"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":166.99330511590847,"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\":166.99330511590847,\"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":-10.829528101714793,"costVsTop":0.5644733631644187,"calculated":52.59762813127347,"frontier":false},{"modelKey":"qwen3-7-max","sourceId":"69534bed-2ffd-4235-832b-e20a810333ab","slug":"qwen3-7-max","name":"Qwen3.7 Max","shortName":"Qwen3.7 Max","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-05-19","cutoffDate":null,"totalCost":1559.3787494793073,"inputCost":787.6297844793073,"outputCost":771.7489649999999,"reasoningCost":724.1328599999999,"answerCost":47.616105,"costPerTask":0.9849971557584272,"inputCostPerTask":0.8172003959741965,"outputCostPerTask":0.16779675978423086,"reasoningCostPerTask":0.1334930681431125,"answerCostPerTask":0.03430369164111838,"timePerTask":97.15516598732462,"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\":1559.3787494793073,\"input\":787.6297844793073,\"nonCacheInput\":33.1299275,\"cacheRead\":12.073265425712417,\"cacheWrite\":742.4265915535949,\"output\":771.7489649999999,\"reasoning\":724.1328599999999,\"answer\":47.616105},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.9849971557584272,\"input\":0.8172003959741965,\"nonCacheInput\":0.018014952291583917,\"cacheRead\":0.012804054839293578,\"cacheWrite\":0.7863813888433189,\"output\":0.16779675978423086,\"reasoning\":0.1334930681431125,\"answer\":0.03430369164111838},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.19938575167537187},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.31250419051450967},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.3618133885934965},{\"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\":97.15516598732462,\"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":0.9849971557584272,"costPenalty":19.934349764466436,"pointsPerK":48240.66422561926,"costPerQuality":0.020729399481795033,"deltaTop":-15.910239178855988,"costVsTop":0.9495502945633303,"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":553.4600360024549,"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\":553.4600360024549,\"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":-16.760295144630327,"costVsTop":0.04322995257196322,"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":257.6833792595098,"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\":257.6833792595098,\"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":-17.303828939485797,"costVsTop":0.12006842604451315,"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":110.3281721822632,"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\":110.3281721822632,\"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":-17.866746534215984,"costVsTop":0.2806593715878821,"calculated":45.560409698772276,"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":346.91422126132545,"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\":346.91422126132545,\"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":-19.57997134902689,"costVsTop":0.030265472169288137,"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":355.18410980772506,"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\":355.18410980772506,\"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":-20.9222655384216,"costVsTop":0.0214799825336697,"calculated":42.50489069456666,"frontier":true},{"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":435.06494722211386,"inputCost":146.60590759711386,"outputCost":288.459039625,"reasoningCost":254.9132797,"answerCost":33.545759925,"costPerTask":0.2339604134365895,"inputCostPerTask":0.17260252472088225,"outputCostPerTask":0.06135788871570717,"reasoningCostPerTask":0.04050174423253931,"answerCostPerTask":0.020856144483167846,"timePerTask":113.85020418712388,"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\":435.06494722211386,\"input\":146.60590759711386,\"nonCacheInput\":8.99135505,\"cacheRead\":68.06500192816833,\"cacheWrite\":69.54955061894552,\"output\":288.459039625,\"reasoning\":254.9132797,\"answer\":33.545759925},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.2339604134365895,\"input\":0.17260252472088225,\"nonCacheInput\":0.004871827724390802,\"cacheRead\":0.08455242237673948,\"cacheWrite\":0.083178274619752,\"output\":0.06135788871570717,\"reasoning\":0.04050174423253931,\"answer\":0.020856144483167846},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0563571561329692},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.02323153770960576},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1188048275423472},{\"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\":113.85020418712388,\"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":0.2339604134365895,"costPenalty":13.691423801432885,"pointsPerK":162972.97474726255,"costPerQuality":0.006135986666199066,"deltaTop":-25.29793168212786,"costVsTop":0.2255409350129704,"calculated":38.1292245508604,"frontier":false},{"modelKey":"grok-4-3","sourceId":"948892b5-db03-4118-a4a8-ccd51ed871ea","slug":"grok-4-3","name":"Grok 4.3 (high)","shortName":"Grok 4.3 (high)","creatorName":"SpaceXAI","creatorSlug":"xai","releaseDate":"2026-04-30","cutoffDate":null,"totalCost":287.6431168111509,"inputCost":79.55449681115093,"outputCost":208.08862,"reasoningCost":195.56833,"answerCost":12.520290000000001,"costPerTask":0.13850067515455958,"inputCostPerTask":0.10258732037383253,"outputCostPerTask":0.035913354780727054,"reasoningCostPerTask":0.025833286911049913,"answerCostPerTask":0.010080067869677146,"timePerTask":133.1573893824764,"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\":133.1573893824764,\"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":-28.78753639858452,"costVsTop":0.13351648390189477,"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":249.12818770353056,"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\":249.12818770353056,\"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":-29.51417940623986,"costVsTop":0.32111837491994094,"calculated":33.9129768267484,"frontier":false},{"modelKey":"mistral-medium-3-5","sourceId":"dd059b25-d82a-4ead-82a4-4adceaaec48b","slug":"mistral-medium-3-5","name":"Mistral Medium 3.5","shortName":"Mistral Medium 3.5","creatorName":"Mistral","creatorSlug":"mistral","releaseDate":"2026-04-29","cutoffDate":null,"totalCost":1483.4021295000002,"inputCost":799.5959220000001,"outputCost":683.8062075000001,"reasoningCost":630.0631350000001,"answerCost":53.7430725,"costPerTask":1.1962136097409157,"inputCostPerTask":1.005376276112074,"outputCostPerTask":0.19083733362884178,"reasoningCostPerTask":0.13797198974531544,"answerCostPerTask":0.05286534388352635,"timePerTask":236.9797885572223,"intelligence":29.947307563003,"coding":46.9023096129838,"agentic":18.9989965635739,"mmmu":0.648554913294798,"priceInput1m":1.5,"priceOutput1m":7.5,"activeParams":null,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"dd059b25-d82a-4ead-82a4-4adceaaec48b\",\"slug\":\"mistral-medium-3-5\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Mistral Medium 3.5\",\"short_name\":\"Mistral Medium 3.5\",\"creator_name\":\"Mistral\",\"creator_slug\":\"mistral\",\"release_date\":\"2026-04-29\",\"knowledge_cutoff_date\":null,\"intelligence_index\":29.947307563003,\"coding_index\":46.9023096129838,\"agentic_index\":18.9989965635739,\"mmmu_pro\":0.648554913294798,\"intelligence_index_cost\":{\"total\":1483.4021295000002,\"input\":799.5959220000001,\"nonCacheInput\":19.505827500000002,\"cacheRead\":0,\"cacheWrite\":780.0900945000001,\"output\":683.8062075000001,\"reasoning\":630.0631350000001,\"answer\":53.7430725},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":1.1962136097409157,\"input\":1.005376276112074,\"nonCacheInput\":0.01079570871477184,\"cacheRead\":0,\"cacheWrite\":0.994580567397302,\"output\":0.19083733362884178,\"reasoning\":0.13797198974531544,\"answer\":0.05286534388352635},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.20766154545454546},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.17571209793814435},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.7324246067415731},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.006624554253472221},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.025282815396200184},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.004542096590909091},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.03018673392857143},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0018108431875000002},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.01196831625}]},\"intelligence_index_time_per_task\":236.9797885572223,\"price_1m_input_tokens\":1.5,\"price_1m_output_tokens\":7.5,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":true}","quality":31.949537913186898,"costForScoring":1.1962136097409157,"costPenalty":20.77808739224522,"pointsPerK":26708.89016227357,"costPerQuality":0.03744071707676213,"deltaTop":-31.477618319801362,"costVsTop":1.1531657516468248,"calculated":31.949537913186898,"frontier":false},{"modelKey":"claude-4-5-haiku-reasoning","sourceId":"a6340098-d7ae-462d-b372-0a0a67fc44b4","slug":"claude-4-5-haiku-reasoning","name":"Claude 4.5 Haiku (Reasoning)","shortName":"Claude 4.5 Haiku","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2025-10-15","cutoffDate":"2025-07-01","totalCost":563.5089486807195,"inputCost":122.8408486807195,"outputCost":440.66810000000004,"reasoningCost":402.01882500000005,"answerCost":38.649274999999996,"costPerTask":0.2716109087882064,"inputCostPerTask":0.15392344687164683,"outputCostPerTask":0.11768746191655952,"reasoningCostPerTask":0.08803767257421066,"answerCostPerTask":0.02964978934234885,"timePerTask":208.40966953294094,"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\":563.5089486807195,\"input\":122.8408486807195,\"nonCacheInput\":13.03874,\"cacheRead\":20.57104685385048,\"cacheWrite\":89.23106182686902,\"output\":440.66810000000004,\"reasoning\":402.01882500000005,\"answer\":38.649274999999996},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.2716109087882064,\"input\":0.15392344687164683,\"nonCacheInput\":0.007056618425483764,\"cacheRead\":0.02870167842292957,\"cacheWrite\":0.11816515002323351,\"output\":0.11768746191655952,\"reasoning\":0.08803767257421066,\"answer\":0.02964978934234885},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.04089898046078856},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.021897451125353594},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.164920676708927},{\"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\":208.40966953294094,\"price_1m_input_tokens\":1,\"price_1m_output_tokens\":5,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":29.957157653957466,"costForScoring":0.2716109087882064,"costPenalty":14.339472086547884,"pointsPerK":110294.38319547435,"costPerQuality":0.009066644837459252,"deltaTop":-33.46999857903079,"costVsTop":0.2618365108352737,"calculated":29.957157653957466,"frontier":false},{"modelKey":"gpt-oss-120b","sourceId":"f0083258-8646-45b8-8082-7aaf6c2ea82a","slug":"gpt-oss-120b","name":"gpt-oss-120b (high)","shortName":"gpt-oss-120b (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2025-08-05","cutoffDate":"2024-05-31","totalCost":96.276024,"inputCost":43.8453252,"outputCost":52.4306988,"reasoningCost":48.8940852,"answerCost":3.5366136,"costPerTask":0.06067164425252872,"inputCostPerTask":0.03929974221734161,"outputCostPerTask":0.02137190203518711,"reasoningCostPerTask":0.01682907062489461,"answerCostPerTask":0.0045428314102924985,"timePerTask":126.32360180253298,"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\":126.32360180253298,\"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":-40.945407272027595,"costVsTop":0.058488268047100236,"calculated":22.48174896096066,"frontier":false}]}