{"run":{"id":922,"source_url":"https://artificialanalysis.ai/models","status":"success","started_at":"2026-07-14T08:00:47.536Z","completed_at":"2026-07-14T08:00:48.722Z","duration_ms":1186,"http_status":200,"html_bytes":1346785,"html_sha256":"57d3f95481b538f4a0c755ff5f491d014eb41997c4e1f99d1244b88fd4ab73b2","html_gzip_bytes":148590,"raw_html_encoding":"pruned","parser_version":"aa-next-rsc-manifest-aes-gcm-v4","model_count":573,"result_count":573,"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":224.42713771754205,"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\":224.42713771754205,\"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":224.42713771754205,"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\":224.42713771754205,\"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":318.18864560189706,"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\":318.18864560189706,\"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-sol-xhigh","sourceId":"d998db47-9b67-4727-a2bb-2e1261020ac0","slug":"gpt-5-6-sol-xhigh","name":"GPT-5.6 Sol (xhigh)","shortName":"GPT-5.6 Sol (xhigh)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":1542.5249316860813,"inputCost":480.5761416860813,"outputCost":1061.94879,"reasoningCost":894.22575,"answerCost":167.72304,"costPerTask":0.6824768594725414,"inputCostPerTask":0.38426016744059444,"outputCostPerTask":0.298216692031947,"reasoningCostPerTask":0.16646290497225233,"answerCostPerTask":0.13175378705969473,"timePerTask":148.58677232107786,"intelligence":57.653836996095,"coding":78.3482452489943,"agentic":51.7983493699885,"mmmu":0.826589595375723,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"d998db47-9b67-4727-a2bb-2e1261020ac0\",\"slug\":\"gpt-5-6-sol-xhigh\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Sol (xhigh)\",\"short_name\":\"GPT-5.6 Sol (xhigh)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":57.653836996095,\"coding_index\":78.3482452489943,\"agentic_index\":51.7983493699885,\"mmmu_pro\":0.826589595375723,\"intelligence_index_cost\":{\"total\":1542.5249316860813,\"input\":480.5761416860813,\"nonCacheInput\":61.12972,\"cacheRead\":245.37851550555814,\"cacheWrite\":174.06790618052318,\"output\":1061.94879,\"reasoning\":894.22575,\"answer\":167.72304},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.6824768594725414,\"input\":0.38426016744059444,\"nonCacheInput\":0.032323895035726066,\"cacheRead\":0.20047578205198746,\"cacheWrite\":0.151460490352881,\"output\":0.298216692031947,\"reasoning\":0.16646290497225233,\"answer\":0.13175378705969473},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.35235707320050863},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.1287881740955396},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.08858966369700716},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.005413680555555555},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.026589518072289157},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.003447578914141415},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.04063615624999999},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0061931834375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.030461831249999998}]},\"intelligence_index_time_per_task\":148.58677232107786,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":62.6001438716926,"costForScoring":0.6824768594725414,"costPenalty":18.34087930476516,"pointsPerK":91724.93250551191,"costPerQuality":0.010902161197446596,"deltaTop":-0.8270123612956581,"costVsTop":0.6579167250953394,"calculated":62.6001438716926,"frontier":true},{"modelKey":"gpt-5-6-sol-high","sourceId":"8afc250d-b538-45a2-812a-4605f4ffd87e","slug":"gpt-5-6-sol-high","name":"GPT-5.6 Sol (high)","shortName":"GPT-5.6 Sol (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":955.5499374665286,"inputCost":318.0878574665286,"outputCost":637.46208,"reasoningCost":500.39054999999996,"answerCost":137.07153,"costPerTask":0.45300942735621286,"inputCostPerTask":0.25230017070177935,"outputCostPerTask":0.20070925665443357,"reasoningCostPerTask":0.09561803680761782,"answerCostPerTask":0.10509121984681576,"timePerTask":99.24077603400306,"intelligence":55.8665067971861,"coding":77.158759883479,"agentic":48.5313974799542,"mmmu":0.81849710982659,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"8afc250d-b538-45a2-812a-4605f4ffd87e\",\"slug\":\"gpt-5-6-sol-high\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Sol (high)\",\"short_name\":\"GPT-5.6 Sol (high)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":55.8665067971861,\"coding_index\":77.158759883479,\"agentic_index\":48.5313974799542,\"mmmu_pro\":0.81849710982659,\"intelligence_index_cost\":{\"total\":955.5499374665286,\"input\":318.0878574665286,\"nonCacheInput\":59.712125,\"cacheRead\":156.2965998942149,\"cacheWrite\":102.0791325723137,\"output\":637.46208,\"reasoning\":500.39054999999996,\"answer\":137.07153},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.45300942735621286,\"input\":0.25230017070177935,\"nonCacheInput\":0.031962530985016495,\"cacheRead\":0.13004241928024557,\"cacheWrite\":0.09029522043651722,\"output\":0.20070925665443357,\"reasoning\":0.09561803680761782,\"answer\":0.10509121984681576},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.22845999328632668},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.08178121341061724},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.0643861028438556},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.004211102430555555},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.015486708178869324},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00226401672979798},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.022776357142857143},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0033616145833333328},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.030282318750000006}]},\"intelligence_index_time_per_task\":99.24077603400306,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":60.51888805353976,"costForScoring":0.45300942735621286,"costPenalty":16.561072399955698,"pointsPerK":133592.9991716314,"costPerQuality":0.007485422186796379,"deltaTop":-2.9082681794484984,"costVsTop":0.4367070835395936,"calculated":60.51888805353976,"frontier":true},{"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":140.2474616593675,"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\":140.2474616593675,\"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":false},{"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":439.9482477870585,"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\":439.9482477870585,\"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":212.10867464249,"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\":212.10867464249,\"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":"gpt-5-6-sol-medium","sourceId":"6f174934-5b7d-4333-86cb-f5ebf4a862e3","slug":"gpt-5-6-sol-medium","name":"GPT-5.6 Sol (medium)","shortName":"GPT-5.6 Sol (medium)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":593.0381807024285,"inputCost":233.73205070242852,"outputCost":359.30613,"reasoningCost":253.22747999999999,"answerCost":106.07865,"costPerTask":0.3139844979499344,"inputCostPerTask":0.1879028548426671,"outputCostPerTask":0.1260816431072673,"reasoningCostPerTask":0.04572794844572658,"answerCostPerTask":0.0803536946615407,"timePerTask":68.1637723931896,"intelligence":53.5888349532218,"coding":76.2553752254127,"agentic":44.5478270332188,"mmmu":0.813872832369942,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"6f174934-5b7d-4333-86cb-f5ebf4a862e3\",\"slug\":\"gpt-5-6-sol-medium\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Sol (medium)\",\"short_name\":\"GPT-5.6 Sol (medium)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":53.5888349532218,\"coding_index\":76.2553752254127,\"agentic_index\":44.5478270332188,\"mmmu_pro\":0.813872832369942,\"intelligence_index_cost\":{\"total\":593.0381807024285,\"input\":233.73205070242852,\"nonCacheInput\":59.24144,\"cacheRead\":79.88266048239751,\"cacheWrite\":94.60795022003099,\"output\":359.30613,\"reasoning\":253.22747999999999,\"answer\":106.07865},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3139844979499344,\"input\":0.1879028548426671,\"nonCacheInput\":0.03191498500888545,\"cacheRead\":0.07098436915718814,\"cacheWrite\":0.08500350067659358,\"output\":0.1260816431072673,\"reasoning\":0.04572794844572658,\"answer\":0.0803536946615407},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.1226594982266548},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.08246629719890503},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.05252244026913613},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0033567795138888883},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.008015598644578313},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0014592787247474748},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.011586263392857142},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0019060044791666666},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.030012337500000003}]},\"intelligence_index_time_per_task\":68.1637723931896,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":58.13067907061777,"costForScoring":0.3139844979499344,"costPenalty":14.969082066050737,"pointsPerK":185138.69140089472,"costPerQuality":0.005401356099220907,"deltaTop":-5.296477162370493,"costVsTop":0.3026852116005502,"calculated":58.13067907061777,"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":123.2420973706246,"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\":123.2420973706246,\"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":552.5997944805375,"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\":552.5997944805375,\"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":"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":385.02351360060766,"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\":385.02351360060766,\"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":-6.25449245974729,"costVsTop":1.9022966298520438,"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":1719.1614806271946,"inputCost":434.27267062719454,"outputCost":1284.88881,"reasoningCost":1166.03919,"answerCost":118.84961999999999,"costPerTask":0.668057792071965,"inputCostPerTask":0.36576396776180237,"outputCostPerTask":0.30229382431016266,"reasoningCostPerTask":0.20798050125698342,"answerCostPerTask":0.09431332305317924,"timePerTask":131.9407010486616,"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\":1719.1614806271946,\"input\":434.27267062719454,\"nonCacheInput\":62.498355,\"cacheRead\":86.94431826364506,\"cacheWrite\":284.82999736354947,\"output\":1284.88881,\"reasoning\":1166.03919,\"answer\":118.84961999999999},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.668057792071965,\"input\":0.36576396776180237,\"nonCacheInput\":0.03167666193854673,\"cacheRead\":0.07872952598782859,\"cacheWrite\":0.2553577798354271,\"output\":0.30229382431016266,\"reasoning\":0.20798050125698342,\"answer\":0.09431332305317924},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.22443538924111855},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.14699677500649885},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1532865837478527},{\"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\":131.9407010486616,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":56.051260065839436,"costForScoring":0.668057792071965,"costPenalty":18.248140338712094,"pointsPerK":83901.81318295504,"costPerQuality":0.011918693554564964,"deltaTop":-7.375896167148824,"costVsTop":0.6440165532851948,"calculated":56.051260065839436,"frontier":false},{"modelKey":"gpt-5-6-terra-xhigh","sourceId":"9e30696f-16fa-4b4f-ba53-161895a85fed","slug":"gpt-5-6-terra-xhigh","name":"GPT-5.6 Terra (xhigh)","shortName":"GPT-5.6 Terra (xhigh)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":740.2127921059758,"inputCost":194.7244721059758,"outputCost":545.48832,"reasoningCost":466.70544,"answerCost":78.78288,"costPerTask":0.3272368361728899,"inputCostPerTask":0.1617008978584035,"outputCostPerTask":0.16553593831448635,"reasoningCostPerTask":0.1023817943539,"answerCostPerTask":0.06315414396058631,"timePerTask":88.35195426332383,"intelligence":51.6046369461818,"coding":70.6399986128451,"agentic":44.7046323024055,"mmmu":0.794797687861272,"priceInput1m":2.5,"priceOutput1m":15,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"9e30696f-16fa-4b4f-ba53-161895a85fed\",\"slug\":\"gpt-5-6-terra-xhigh\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Terra (xhigh)\",\"short_name\":\"GPT-5.6 Terra (xhigh)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":51.6046369461818,\"coding_index\":70.6399986128451,\"agentic_index\":44.7046323024055,\"mmmu_pro\":0.794797687861272,\"intelligence_index_cost\":{\"total\":740.2127921059758,\"input\":194.7244721059758,\"nonCacheInput\":32.62652,\"cacheRead\":103.67821584948038,\"cacheWrite\":58.419736256495426,\"output\":545.48832,\"reasoning\":466.70544,\"answer\":78.78288},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3272368361728899,\"input\":0.1617008978584035,\"nonCacheInput\":0.016205361093234495,\"cacheRead\":0.09158455803983181,\"cacheWrite\":0.05391097872533722,\"output\":0.16553593831448635,\"reasoning\":0.1023817943539,\"answer\":0.06315414396058631},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.15381934111000783},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.042532758381071845},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.06990907506591353},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0033887109374999996},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.015118658480074145},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.002004992897727273},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.02271244419642857},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0025306176041666665},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.015220237500000003}]},\"intelligence_index_time_per_task\":88.35195426332383,\"price_1m_input_tokens\":2.5,\"price_1m_output_tokens\":15,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":55.6497559538108,"costForScoring":0.3272368361728899,"costPenalty":15.148621851159572,"pointsPerK":170059.5709353736,"costPerQuality":0.005880292385190258,"deltaTop":-7.777400279177456,"costVsTop":0.3154606410418373,"calculated":55.6497559538108,"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":218.13515105003495,"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\":218.13515105003495,\"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":-8.917541357667531,"costVsTop":0.8549157174935296,"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":826.5058202762576,"inputCost":207.34691947625768,"outputCost":619.1589008,"reasoningCost":586.2232948,"answerCost":32.935606,"costPerTask":0.3758425161131201,"inputCostPerTask":0.18756259496559693,"outputCostPerTask":0.18827992114752315,"reasoningCostPerTask":0.16148805597970656,"answerCostPerTask":0.026791865167816648,"timePerTask":207.35493853793378,"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\":826.5058202762576,\"input\":207.34691947625768,\"nonCacheInput\":17.707790799999998,\"cacheRead\":126.80458876155525,\"cacheWrite\":62.83453991470244,\"output\":619.1589008,\"reasoning\":586.2232948,\"answer\":32.935606},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3758425161131201,\"input\":0.18756259496559693,\"nonCacheInput\":0.009786523802333615,\"cacheRead\":0.11935932672192043,\"cacheWrite\":0.05841674444134293,\"output\":0.18827992114752315,\"reasoning\":0.16148805597970656,\"answer\":0.026791865167816648},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.15338149640443965},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.03816125652487307},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.1109779625982118},{\"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\":207.35493853793378,\"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":0.3758425161131201,"costPenalty":15.750059068685726,"pointsPerK":144473.28734275725,"costPerQuality":0.006921694787961313,"deltaTop":-9.127952406952595,"costVsTop":0.36231715979915213,"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":935.7674958905204,"inputCost":296.7807258905204,"outputCost":638.9867700000001,"reasoningCost":540.2006700000001,"answerCost":98.7861,"costPerTask":0.4061167899400016,"inputCostPerTask":0.2521440877981879,"outputCostPerTask":0.1539727021418136,"reasoningCostPerTask":0.07859751210021937,"answerCostPerTask":0.07537519004159425,"timePerTask":83.94886733171072,"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\":935.7674958905204,\"input\":296.7807258905204,\"nonCacheInput\":61.61127,\"cacheRead\":50.9530699010533,\"cacheWrite\":184.21638598946708,\"output\":638.9867700000001,\"reasoning\":540.2006700000001,\"answer\":98.7861},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.4061167899400016,\"input\":0.2521440877981879,\"nonCacheInput\":0.03226918379648743,\"cacheRead\":0.047958578958377754,\"cacheWrite\":0.17191632504332277,\"output\":0.1539727021418136,\"reasoning\":0.07859751210021937,\"answer\":0.07537519004159425},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.1281609965107507},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.10383995721605613},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.09604498182928857},{\"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\":83.94886733171072,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":53.235680870968366,"costForScoring":0.4061167899400016,"costPenalty":16.08650944741358,"pointsPerK":131084.65887074807,"costPerQuality":0.007628657759151044,"deltaTop":-10.191475362019894,"costVsTop":0.391501960447507,"calculated":53.235680870968366,"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":177.36325807133994,"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\":177.36325807133994,\"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":true},{"modelKey":"gpt-5-6-sol-low","sourceId":"0904b596-8932-43bd-9b21-324f128e1723","slug":"gpt-5-6-sol-low","name":"GPT-5.6 Sol (low)","shortName":"GPT-5.6 Sol (low)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":353.48821704247973,"inputCost":155.95762704247971,"outputCost":197.53059,"reasoningCost":120.67415999999999,"answerCost":76.85643,"costPerTask":0.1974662438526612,"inputCostPerTask":0.12223363245499196,"outputCostPerTask":0.0752326113976693,"reasoningCostPerTask":0.01849075082392351,"answerCostPerTask":0.05674186057374579,"timePerTask":40.63265609250366,"intelligence":49.444040367728,"coding":69.6659557497573,"agentic":39.9962084765178,"mmmu":0.809826589595376,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"0904b596-8932-43bd-9b21-324f128e1723\",\"slug\":\"gpt-5-6-sol-low\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Sol (low)\",\"short_name\":\"GPT-5.6 Sol (low)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":49.444040367728,\"coding_index\":69.6659557497573,\"agentic_index\":39.9962084765178,\"mmmu_pro\":0.809826589595376,\"intelligence_index_cost\":{\"total\":353.48821704247973,\"input\":155.95762704247971,\"nonCacheInput\":59.16245,\"cacheRead\":35.97200906152351,\"cacheWrite\":60.82316798095621,\"output\":197.53059,\"reasoning\":120.67415999999999,\"answer\":76.85643},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.1974662438526612,\"input\":0.12223363245499196,\"nonCacheInput\":0.03185883283461296,\"cacheRead\":0.034101808160375,\"cacheWrite\":0.05627299146000397,\"output\":0.0752326113976693,\"reasoning\":0.01849075082392351,\"answer\":0.05674186057374579},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.05516506123110897},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.058582096664020526},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.03800566610579768},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.002809085648148148},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0041588296455050975},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0009355287247474748},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0068356875},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0010883820833333332},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.029885906250000007}]},\"intelligence_index_time_per_task\":40.63265609250366,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":53.03540153133437,"costForScoring":0.1974662438526612,"costPenalty":12.954928652207338,"pointsPerK":268579.5835105192,"costPerQuality":0.003723291200802811,"deltaTop":-10.391754701653888,"costVsTop":0.1903600725346609,"calculated":53.03540153133437,"frontier":true},{"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":168.76704159152692,"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\":168.76704159152692,\"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":"gpt-5-6-terra-high","sourceId":"81972fba-1219-477e-bbfb-18c656a63ff7","slug":"gpt-5-6-terra-high","name":"GPT-5.6 Terra (high)","shortName":"GPT-5.6 Terra (high)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":495.7738956390539,"inputCost":141.2463456390539,"outputCost":354.52754999999996,"reasoningCost":288.50906999999995,"answerCost":66.01848000000001,"costPerTask":0.23590588524864192,"inputCostPerTask":0.11983105412350942,"outputCostPerTask":0.11607483112513248,"reasoningCostPerTask":0.06341885989600403,"answerCostPerTask":0.052655971229128434,"timePerTask":67.58923768580885,"intelligence":48.9549359759828,"coding":67.1422007213206,"agentic":41.3273470790378,"mmmu":0.790751445086705,"priceInput1m":2.5,"priceOutput1m":15,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"81972fba-1219-477e-bbfb-18c656a63ff7\",\"slug\":\"gpt-5-6-terra-high\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Terra (high)\",\"short_name\":\"GPT-5.6 Terra (high)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":48.9549359759828,\"coding_index\":67.1422007213206,\"agentic_index\":41.3273470790378,\"mmmu_pro\":0.790751445086705,\"intelligence_index_cost\":{\"total\":495.7738956390539,\"input\":141.2463456390539,\"nonCacheInput\":29.7497325,\"cacheRead\":66.69734206399531,\"cacheWrite\":44.79927107505862,\"output\":354.52754999999996,\"reasoning\":288.50906999999995,\"answer\":66.01848000000001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.23590588524864192,\"input\":0.11983105412350942,\"nonCacheInput\":0.015998302207231706,\"cacheRead\":0.06146348802679035,\"cacheWrite\":0.04236926388948736,\"output\":0.11607483112513248,\"reasoning\":0.06341885989600403,\"answer\":0.052655971229128434},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.10125676302067828},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.033776742036446324},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.05715669142572115},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0024162355324074073},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.009668303261121409},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0014413707386363636},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.013598933035714286},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0015230743229166666},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.015067771875000002}]},\"intelligence_index_time_per_task\":67.58923768580885,\"price_1m_input_tokens\":2.5,\"price_1m_output_tokens\":15,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":52.474827925447066,"costForScoring":0.23590588524864192,"costPenalty":13.727387755576073,"pointsPerK":222439.67279637489,"costPerQuality":0.004495600930484273,"deltaTop":-10.952328307541194,"costVsTop":0.2274163955880587,"calculated":52.474827925447066,"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":654.4979070535921,"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\":654.4979070535921,\"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":-13.09161980374406,"costVsTop":1.0946968135304451,"calculated":50.3355364292442,"frontier":false},{"modelKey":"gpt-5-6-terra-medium","sourceId":"26e0f83a-ca98-4f34-94ac-7c5e251ee410","slug":"gpt-5-6-terra-medium","name":"GPT-5.6 Terra (medium)","shortName":"GPT-5.6 Terra (medium)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":240.22771707940757,"inputCost":83.88736707940758,"outputCost":156.34035,"reasoningCost":112.251045,"answerCost":44.089305,"costPerTask":0.1276399207309507,"inputCostPerTask":0.07110362412176216,"outputCostPerTask":0.05653629660918855,"reasoningCostPerTask":0.021642154342575264,"answerCostPerTask":0.03489414226661329,"timePerTask":34.12592807479361,"intelligence":45.5742165575207,"coding":64.7406887224303,"agentic":37.037147766323,"mmmu":0.767630057803468,"priceInput1m":2.5,"priceOutput1m":15,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"26e0f83a-ca98-4f34-94ac-7c5e251ee410\",\"slug\":\"gpt-5-6-terra-medium\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Terra (medium)\",\"short_name\":\"GPT-5.6 Terra (medium)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":45.5742165575207,\"coding_index\":64.7406887224303,\"agentic_index\":37.037147766323,\"mmmu_pro\":0.767630057803468,\"intelligence_index_cost\":{\"total\":240.22771707940757,\"input\":83.88736707940758,\"nonCacheInput\":29.5973875,\"cacheRead\":27.96191509092108,\"cacheWrite\":26.328064488486504,\"output\":156.34035,\"reasoning\":112.251045,\"answer\":44.089305},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.1276399207309507,\"input\":0.07110362412176216,\"nonCacheInput\":0.01596181809968082,\"cacheRead\":0.029107833264009123,\"cacheWrite\":0.026033972758072215,\"output\":0.05653629660918855,\"reasoning\":0.021642154342575264,\"answer\":0.03489414226661329},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03822060021100771},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.024026979236271815},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.03800147653531274},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0015573936631944443},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.003987514915430954},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0007262918244949495},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.005440602678571429},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0007287210416666665},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.014950340625000001}]},\"intelligence_index_time_per_task\":34.12592807479361,\"price_1m_input_tokens\":2.5,\"price_1m_output_tokens\":15,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":49.117351015424674,"costForScoring":0.1276399207309507,"costPenalty":11.059865258088326,"pointsPerK":384811.8263796013,"costPerQuality":0.002598672731574368,"deltaTop":-14.309805217563586,"costVsTop":0.12304657289572833,"calculated":49.117351015424674,"frontier":true},{"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":98.11070042863805,"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\":98.11070042863805,\"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":"claude-sonnet-5-non-reasoning","sourceId":"d58b9ada-fd9d-4fff-a086-242034657963","slug":"claude-sonnet-5-non-reasoning","name":"Claude Sonnet 5 (Non-reasoning, High Effort)","shortName":"Claude Sonnet 5 (Non-reasoning)","creatorName":"Anthropic","creatorSlug":"anthropic","releaseDate":"2026-06-30","cutoffDate":null,"totalCost":427.3276306773449,"inputCost":286.56853067734494,"outputCost":140.7591,"reasoningCost":0,"answerCost":140.7591,"costPerTask":0.3745280868419511,"inputCostPerTask":0.27743747349677994,"outputCostPerTask":0.09709061334517116,"reasoningCostPerTask":0,"answerCostPerTask":0.09709061334517116,"timePerTask":93.25164150029387,"intelligence":41.7305068119089,"coding":66.3909696213067,"agentic":33.6958728522337,"mmmu":0.71907514450867,"priceInput1m":2,"priceOutput1m":10,"activeParams":null,"isOpenWeights":false,"isReasoning":false,"rawResultJson":"{\"id\":\"d58b9ada-fd9d-4fff-a086-242034657963\",\"slug\":\"claude-sonnet-5-non-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Claude Sonnet 5 (Non-reasoning, High Effort)\",\"short_name\":\"Claude Sonnet 5 (Non-reasoning)\",\"creator_name\":\"Anthropic\",\"creator_slug\":\"anthropic\",\"release_date\":\"2026-06-30\",\"knowledge_cutoff_date\":null,\"intelligence_index\":41.7305068119089,\"coding_index\":66.3909696213067,\"agentic_index\":33.6958728522337,\"mmmu_pro\":0.71907514450867,\"intelligence_index_cost\":{\"total\":427.3276306773449,\"input\":286.56853067734494,\"nonCacheInput\":35.984948,\"cacheRead\":185.16319020197,\"cacheWrite\":65.42039247537497,\"output\":140.7591,\"reasoning\":0,\"answer\":140.7591},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.3745280868419511,\"input\":0.27743747349677994,\"nonCacheInput\":0.019748179033501418,\"cacheRead\":0.19393647804296277,\"cacheWrite\":0.06375281642031572,\"output\":0.09709061334517116,\"reasoning\":0,\"answer\":0.09709061334517116},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.1691869733244918},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.030251516667059823},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.14794773874261832},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0010941840277777777},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0025129519230769233},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0005432746212121212},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.004580964285714285},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00013599824999999997},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.018274485}]},\"intelligence_index_time_per_task\":93.25164150029387,\"price_1m_input_tokens\":2,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":47.27244976181643,"costForScoring":0.3745280868419511,"costPenalty":15.734843921371768,"pointsPerK":126218.70407749996,"costPerQuality":0.007922756039279145,"deltaTop":-16.154706471171828,"costVsTop":0.3610500325853074,"calculated":47.27244976181643,"frontier":false},{"modelKey":"gpt-5-6-sol-non-reasoning","sourceId":"7c4d1e30-6ecb-46cf-880c-41446d7b51f1","slug":"gpt-5-6-sol-non-reasoning","name":"GPT-5.6 Sol (Non-reasoning)","shortName":"GPT-5.6 Sol (Non-reasoning)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":241.50767053376404,"inputCost":162.05585053376404,"outputCost":79.45182,"reasoningCost":0,"answerCost":79.45182,"costPerTask":0.2004446148307233,"inputCostPerTask":0.13822775806942794,"outputCostPerTask":0.06221685676129538,"reasoningCostPerTask":0,"answerCostPerTask":0.06221685676129538,"timePerTask":64.61693336494632,"intelligence":41.2034183649356,"coding":65.1403627410182,"agentic":34.8531580756014,"mmmu":0.71907514450867,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":false,"rawResultJson":"{\"id\":\"7c4d1e30-6ecb-46cf-880c-41446d7b51f1\",\"slug\":\"gpt-5-6-sol-non-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Sol (Non-reasoning)\",\"short_name\":\"GPT-5.6 Sol (Non-reasoning)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":41.2034183649356,\"coding_index\":65.1403627410182,\"agentic_index\":34.8531580756014,\"mmmu_pro\":0.71907514450867,\"intelligence_index_cost\":{\"total\":241.50767053376404,\"input\":162.05585053376404,\"nonCacheInput\":59.28798,\"cacheRead\":44.274081910107476,\"cacheWrite\":58.49378862365656,\"output\":79.45182,\"reasoning\":0,\"answer\":79.45182},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.2004446148307233,\"input\":0.13822775806942794,\"nonCacheInput\":0.031931646119996555,\"cacheRead\":0.04899350841464103,\"cacheWrite\":0.057302603534790345,\"output\":0.06221685676129538,\"reasoning\":0,\"answer\":0.06221685676129538},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.05372474311232321},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.04541468125605973},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.06387794127985744},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.002156688368055555},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0009988985750695087},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00032350220959595965},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0042033348214285705},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00012057520833333332},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.02962425}]},\"intelligence_index_time_per_task\":64.61693336494632,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":47.06564639385173,"costForScoring":0.2004446148307233,"costPenalty":13.019943929351696,"pointsPerK":234806.24028537236,"costPerQuality":0.004258830594896658,"deltaTop":-16.36150983913653,"costVsTop":0.1932312615761766,"calculated":47.06564639385173,"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":517.3051697991125,"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\":517.3051697991125,\"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":246.6639075844068,"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\":246.6639075844068,\"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":97.36021431848093,"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\":97.36021431848093,\"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":"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":375.23018994095116,"inputCost":171.33830994095118,"outputCost":203.89188000000001,"reasoningCost":138.69840000000002,"answerCost":65.19348,"costPerTask":0.21087234510039837,"inputCostPerTask":0.14667007372905344,"outputCostPerTask":0.06420227137134495,"reasoningCostPerTask":0.016734277970007316,"answerCostPerTask":0.047467993401337644,"timePerTask":35.50043318033259,"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\":375.23018994095116,\"input\":171.33830994095118,\"nonCacheInput\":59.498810000000006,\"cacheRead\":22.541079451005423,\"cacheWrite\":89.29842048994576,\"output\":203.89188000000001,\"reasoning\":138.69840000000002,\"answer\":65.19348},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.21087234510039837,\"input\":0.14667007372905344,\"nonCacheInput\":0.032056295655332655,\"cacheRead\":0.023604847262240054,\"cacheWrite\":0.09100893081148073,\"output\":0.06420227137134495,\"reasoning\":0.016734277970007316,\"answer\":0.047467993401337644},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03195167926109161},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.06929213255714856},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.06148099441908117},{\"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\":35.50043318033259,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":44.92667678062327,"costForScoring":0.21087234510039837,"costPenalty":13.240196278295222,"pointsPerK":213051.53484793485,"costPerQuality":0.004693700051087396,"deltaTop":-18.500479452364992,"costVsTop":0.20328373156688723,"calculated":44.92667678062327,"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":325.5651742763938,"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\":325.5651742763938,\"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":"gpt-5-6-terra-low","sourceId":"cc4a20cd-09fe-4962-a430-119c815e85fa","slug":"gpt-5-6-terra-low","name":"GPT-5.6 Terra (low)","shortName":"GPT-5.6 Terra (low)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-07-09","cutoffDate":null,"totalCost":160.65181576963076,"inputCost":71.57601076963076,"outputCost":89.075805,"reasoningCost":56.383559999999996,"answerCost":32.692245,"costPerTask":0.10115788470701273,"inputCostPerTask":0.06728209497870424,"outputCostPerTask":0.0338757897283085,"reasoningCostPerTask":0.008767694531921923,"answerCostPerTask":0.025108095196386584,"timePerTask":19.93834745100439,"intelligence":40.4657478147168,"coding":58.0944825912054,"agentic":30.604824742268,"mmmu":0.761271676300578,"priceInput1m":2.5,"priceOutput1m":15,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"cc4a20cd-09fe-4962-a430-119c815e85fa\",\"slug\":\"gpt-5-6-terra-low\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.6 Terra (low)\",\"short_name\":\"GPT-5.6 Terra (low)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-07-09\",\"knowledge_cutoff_date\":null,\"intelligence_index\":40.4657478147168,\"coding_index\":58.0944825912054,\"agentic_index\":30.604824742268,\"mmmu_pro\":0.761271676300578,\"intelligence_index_cost\":{\"total\":160.65181576963076,\"input\":71.57601076963076,\"nonCacheInput\":29.5821375,\"cacheRead\":24.058445530901672,\"cacheWrite\":17.935427738729086,\"output\":89.075805,\"reasoning\":56.383559999999996,\"answer\":32.692245},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.10115788470701273,\"input\":0.06728209497870424,\"nonCacheInput\":0.015938583592072394,\"cacheRead\":0.032446751897624686,\"cacheWrite\":0.018896759489007157,\"output\":0.0338757897283085,\"reasoning\":0.008767694531921923,\"answer\":0.025108095196386584},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.018964306380106606},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.017183521051815257},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.042346161692091905},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0012401765046296297},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.002215193031742354},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0004719357638888889},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0033926808035714285},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00044461572916666665},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.014899293750000002}]},\"intelligence_index_time_per_task\":19.93834745100439,\"price_1m_input_tokens\":2.5,\"price_1m_output_tokens\":15,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":43.05501838273006,"costForScoring":0.10115788470701273,"costPenalty":10.049997393192939,"pointsPerK":425621.9721026382,"costPerQuality":0.002349502764295381,"deltaTop":-20.3721378502582,"costVsTop":0.0975175396795815,"calculated":43.05501838273006,"frontier":false},{"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":392.95958103974016,"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\":392.95958103974016,\"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":"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":1095.4286040534348,"inputCost":121.45829705343488,"outputCost":973.9703069999999,"reasoningCost":952.0490295,"answerCost":21.9212775,"costPerTask":0.45222268374819774,"inputCostPerTask":0.10067613100720277,"outputCostPerTask":0.35154655274099506,"reasoningCostPerTask":0.3300396390286433,"answerCostPerTask":0.02150691371235167,"timePerTask":462.1126355024655,"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\":1095.4286040534348,\"input\":121.45829705343488,\"nonCacheInput\":8.81514675,\"cacheRead\":45.74112432739613,\"cacheWrite\":66.90202597603874,\"output\":973.9703069999999,\"reasoning\":952.0490295,\"answer\":21.9212775},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.45222268374819774,\"input\":0.10067613100720277,\"nonCacheInput\":0.0047302123966912225,\"cacheRead\":0.03869381381677307,\"cacheWrite\":0.05725210479373846,\"output\":0.35154655274099506,\"reasoning\":0.3300396390286433,\"answer\":0.02150691371235167},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.09850361842926063},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.05060540401453323},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.2140368393331351},{\"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\":462.1126355024655,\"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":0.45222268374819774,"costPenalty":16.553523430150694,"pointsPerK":93039.84032344092,"costPerQuality":0.010748083794250182,"deltaTop":-21.35242994641802,"costVsTop":0.4359486522889354,"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":284.0262247268695,"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\":284.0262247268695,\"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":-21.48969460422586,"costVsTop":0.21776359285132918,"calculated":41.9374616287624,"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":384.6174283559,"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\":384.6174283559,\"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":-22.879761617691656,"costVsTop":0.3025415479546455,"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":240.9447679391534,"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\":240.9447679391534,\"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":-23.664263466370556,"costVsTop":0.2042853415463821,"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":404.421859055453,"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\":404.421859055453,\"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":-24.161056120451562,"costVsTop":0.2557293292442678,"calculated":39.2661001125367,"frontier":false},{"modelKey":"mimo-v2-5-0424","sourceId":"22d09131-343b-4adf-8760-533e20a2155f","slug":"mimo-v2-5-0424","name":"MiMo-V2.5","shortName":"MiMo-V2.5","creatorName":"Xiaomi","creatorSlug":"xiaomi","releaseDate":"2026-04-22","cutoffDate":null,"totalCost":25.192869198091103,"inputCost":5.197242358091103,"outputCost":19.99562684,"reasoningCost":18.54370896,"answerCost":1.45191788,"costPerTask":0.009753224056302287,"inputCostPerTask":0.004931717579916409,"outputCostPerTask":0.004821506476385878,"reasoningCostPerTask":0.003518953578607954,"answerCostPerTask":0.0013025528977779245,"timePerTask":179.42090649853372,"intelligence":37.2025847113282,"coding":56.7987931751977,"agentic":23.7079793814433,"mmmu":0.754335260115607,"priceInput1m":0.14,"priceOutput1m":0.28,"activeParams":15,"isOpenWeights":true,"isReasoning":true,"rawResultJson":"{\"id\":\"22d09131-343b-4adf-8760-533e20a2155f\",\"slug\":\"mimo-v2-5-0424\",\"model_url\":null,\"hosts_url\":null,\"name\":\"MiMo-V2.5\",\"short_name\":\"MiMo-V2.5\",\"creator_name\":\"Xiaomi\",\"creator_slug\":\"xiaomi\",\"release_date\":\"2026-04-22\",\"knowledge_cutoff_date\":null,\"intelligence_index\":37.2025847113282,\"coding_index\":56.7987931751977,\"agentic_index\":23.7079793814433,\"mmmu_pro\":0.754335260115607,\"intelligence_index_cost\":{\"total\":25.192869198091103,\"input\":5.197242358091103,\"nonCacheInput\":2.01017194,\"cacheRead\":0.7580192408552836,\"cacheWrite\":2.429051177235819,\"output\":19.99562684,\"reasoning\":18.54370896,\"answer\":1.45191788},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.009753224056302287,\"input\":0.004931717579916409,\"nonCacheInput\":0.001052506942934785,\"cacheRead\":0.001029304222970439,\"cacheWrite\":0.0028499064140111853,\"output\":0.004821506476385878,\"reasoning\":0.003518953578607954,\"answer\":0.0013025528977779245},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.001582646979495404},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0008824074522597351},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.004200471106230033},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0002929022395833333},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0007186378324837814},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00026044958333333335},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.000765575125},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00006577597541666668},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0009843577625000001}]},\"intelligence_index_time_per_task\":179.42090649853372,\"price_1m_input_tokens\":0.14,\"price_1m_output_tokens\":0.28,\"activeParams\":15,\"is_open_weights\":true,\"reasoning_model\":true}","quality":39.236452422656406,"costForScoring":0.009753224056302287,"costPenalty":0,"pointsPerK":4022921.2613343787,"costPerQuality":0.00024857558352218555,"deltaTop":-24.190703810331854,"costVsTop":0.009402237073946761,"calculated":39.236452422656406,"frontier":true},{"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":211.108561232046,"inputCost":144.982501232046,"outputCost":66.12606,"reasoningCost":0,"answerCost":66.12606,"costPerTask":0.17101364725394147,"inputCostPerTask":0.1234252969522245,"outputCostPerTask":0.047588350301716965,"reasoningCostPerTask":0,"answerCostPerTask":0.047588350301716965,"timePerTask":26.578401471355317,"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\":211.108561232046,\"input\":144.982501232046,\"nonCacheInput\":59.49731,\"cacheRead\":18.47954875199489,\"cacheWrite\":67.0056424800511,\"output\":66.12606,\"reasoning\":0,\"answer\":66.12606},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.17101364725394147,\"input\":0.1234252969522245,\"nonCacheInput\":0.0320902418121363,\"cacheRead\":0.019850490369912262,\"cacheWrite\":0.07148456477017594,\"output\":0.047588350301716965,\"reasoning\":0,\"answer\":0.047588350301716965},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.025205629283579493},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.049951227284269116},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.056854610522156915},{\"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\":26.578401471355317,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":39.2209977517538,"costForScoring":0.17101364725394147,"costPenalty":12.330307694014106,"pointsPerK":229344.25633010318,"costPerQuality":0.0043602574400671505,"deltaTop":-24.20615848123446,"costVsTop":0.16485941931405448,"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":302.65069437049306,"inputCost":120.96213277049307,"outputCost":181.6885616,"reasoningCost":174.16782880000002,"answerCost":7.520732800000001,"costPerTask":0.19519718362030988,"inputCostPerTask":0.15972222359897012,"outputCostPerTask":0.0354749600213398,"reasoningCostPerTask":0.029495446582286897,"answerCostPerTask":0.005979513439052893,"timePerTask":398.35852298070114,"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\":302.65069437049306,\"input\":120.96213277049307,\"nonCacheInput\":5.3356580000000005,\"cacheRead\":2.4449092373484276,\"cacheWrite\":113.18156553314465,\"output\":181.6885616,\"reasoning\":174.16782880000002,\"answer\":7.520732800000001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.19519718362030988,\"input\":0.15972222359897012,\"nonCacheInput\":0.0029128941887433734,\"cacheRead\":0.003350439203663123,\"cacheWrite\":0.15345889020656361,\"output\":0.0354749600213398,\"reasoning\":0.029495446582286897,\"answer\":0.005979513439052893},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.022079237526159052},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.028554696676890163},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.11832419457689694},{\"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\":398.35852298070114,\"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":0.19519718362030988,"costPenalty":12.904735472088376,"pointsPerK":197482.12363014955,"costPerQuality":0.00506374947573903,"deltaTop":-24.879201885025225,"costVsTop":0.18817266843971997,"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":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":108.78473444163214,"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\":108.78473444163214,\"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":"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":305.92580568093706,"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\":305.92580568093706,\"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":-25.72793268997313,"costVsTop":0.39804473243972693,"calculated":37.69922354301513,"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":603.0250448,"inputCost":226.38297239999997,"outputCost":376.6420724000001,"reasoningCost":360.0404192000001,"answerCost":16.6016532,"costPerTask":0.32265601503451746,"inputCostPerTask":0.27120212478057665,"outputCostPerTask":0.05145389025394071,"reasoningCostPerTask":0.035720758473479795,"answerCostPerTask":0.015733131780460922,"timePerTask":184.48780680349947,"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\":603.0250448,\"input\":226.38297239999997,\"nonCacheInput\":7.175616,\"cacheRead\":168.14192311881064,\"cacheWrite\":51.06543328118934,\"output\":376.6420724000001,\"reasoning\":360.0404192000001,\"answer\":16.6016532},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.32265601503451746,\"input\":0.27120212478057665,\"nonCacheInput\":0.003887268194274768,\"cacheRead\":0.2058869003609347,\"cacheWrite\":0.06142795622536726,\"output\":0.05145389025394071,\"reasoning\":0.035720758473479795,\"answer\":0.015733131780460922},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.08873619106060605},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.029997742955326458},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.17786802134831456},{\"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\":184.48780680349947,\"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":0.32265601503451746,"costPenalty":15.08739765745483,"pointsPerK":107808.68503035548,"costPerQuality":0.009275690541243798,"deltaTop":-28.642035534982327,"costVsTop":0.31104466883739545,"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":125.03437783189881,"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\":125.03437783189881,\"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":248.12441509060272,"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\":248.12441509060272,\"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":"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":356.12757059999996,"inputCost":266.77127579999996,"outputCost":89.3562948,"reasoningCost":0,"answerCost":89.3562948,"costPerTask":0.35928391524532766,"inputCostPerTask":0.31715576627678005,"outputCostPerTask":0.04212814896854764,"reasoningCostPerTask":0,"answerCostPerTask":0.04212814896854764,"timePerTask":195.54357620436627,"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\":356.12757059999996,\"input\":266.77127579999996,\"nonCacheInput\":8.4112362,\"cacheRead\":201.8359450950702,\"cacheWrite\":56.524094504929785,\"output\":89.3562948,\"reasoning\":0,\"answer\":89.3562948},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.35928391524532766,\"input\":0.31715576627678005,\"nonCacheInput\":0.004623398756324749,\"cacheRead\":0.24513492215794488,\"cacheWrite\":0.06739744536251041,\"output\":0.04212814896854764,\"reasoning\":0,\"answer\":0.04212814896854764},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.10267234681818181},{\"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\":195.54357620436627,\"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":0.35928391524532766,"costPenalty":15.554377747427463,"pointsPerK":93129.08332617636,"costPerQuality":0.010737784205365673,"deltaTop":-29.96737455235126,"costVsTop":0.34635444940994053,"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":110.9462572698417,"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\":110.9462572698417,\"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":-30.523304978642088,"costVsTop":0.23251633445953235,"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":813.0461276711862,"inputCost":98.82370767118633,"outputCost":714.2224199999999,"reasoningCost":668.35943,"answerCost":45.86299,"costPerTask":0.23800170775318213,"inputCostPerTask":0.07933975849902687,"outputCostPerTask":0.15866194925415525,"reasoningCostPerTask":0.12171040953607823,"answerCostPerTask":0.036951539718077055,"timePerTask":169.1756240153337,"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\":813.0461276711862,\"input\":98.82370767118633,\"nonCacheInput\":15.23766375,\"cacheRead\":20.16078553653485,\"cacheWrite\":63.42525838465147,\"output\":714.2224199999999,\"reasoning\":668.35943,\"answer\":45.86299},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.23800170775318213,\"input\":0.07933975849902687,\"nonCacheInput\":0.008221474081220542,\"cacheRead\":0.016812425759387604,\"cacheWrite\":0.05430585865841872,\"output\":0.15866194925415525,\"reasoning\":0.12171040953607823,\"answer\":0.036951539718077055},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.06752360404118385},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.048236080520982494},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.05406939861498135},{\"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\":169.1756240153337,\"price_1m_input_tokens\":1.25,\"price_1m_output_tokens\":10,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":32.73529214302853,"costForScoring":0.23800170775318213,"costPenalty":13.765800732965229,"pointsPerK":137542.25737311272,"costPerQuality":0.007270492858694959,"deltaTop":-30.69186408995973,"costVsTop":0.2294367962205928,"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":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":176.4115620168882,"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\":176.4115620168882,\"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":"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":167.82130844647713,"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\":167.82130844647713,\"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":-31.778249913733358,"costVsTop":0.17238092520338272,"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":197.44026580551872,"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\":197.44026580551872,\"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":-32.67133220091259,"costVsTop":0.332761698961989,"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":394.78896550692923,"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\":394.78896550692923,\"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":-32.720552078931824,"costVsTop":0.2727653290080234,"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":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":201.00108200228345,"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\":201.00108200228345,\"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":"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":216.01344400000005,"inputCost":112.76382480000002,"outputCost":103.24961920000001,"reasoningCost":0,"answerCost":103.24961920000001,"costPerTask":0.17743046041328747,"inputCostPerTask":0.14889797486912196,"outputCostPerTask":0.028532485544165466,"reasoningCostPerTask":0,"answerCostPerTask":0.028532485544165466,"timePerTask":53.27856246620966,"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\":216.01344400000005,\"input\":112.76382480000002,\"nonCacheInput\":4.9825756000000005,\"cacheRead\":82.66347141001182,\"cacheWrite\":25.117777789988192,\"output\":103.24961920000001,\"reasoning\":0,\"answer\":103.24961920000001},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.17743046041328747,\"input\":0.14889797486912196,\"nonCacheInput\":0.0026043095528057955,\"cacheRead\":0.11328408186991187,\"cacheWrite\":0.0330095834464043,\"output\":0.028532485544165466,\"reasoning\":0,\"answer\":0.028532485544165466},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0334515793939394},{\"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\":53.27856246620966,\"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":0.17743046041328747,"costPenalty":12.490281794969171,"pointsPerK":163016.66422389774,"costPerQuality":0.006134342183732423,"deltaTop":-34.50303444470379,"costVsTop":0.17104531212602236,"calculated":28.924121788284467,"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":83.65445868074991,"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\":83.65445868074991,\"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":-35.844568389439125,"costVsTop":0.2824092411505775,"calculated":27.582587843549135,"frontier":false},{"modelKey":"gpt-5-5-instant-06-26","sourceId":"c4169d75-9d24-4794-a9c3-69e1fe364de5","slug":"gpt-5-5-instant-06-26","name":"GPT-5.5 Instant (June 2026)","shortName":"GPT-5.5 Instant (June 2026)","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2026-06-25","cutoffDate":"2025-08-31","totalCost":528.0811447088156,"inputCost":401.3106847088156,"outputCost":126.77046,"reasoningCost":38.036730000000006,"answerCost":88.73373,"costPerTask":0.7108087581976272,"inputCostPerTask":0.6360093366929683,"outputCostPerTask":0.07479942150465903,"reasoningCostPerTask":0.002995374198677195,"answerCostPerTask":0.07180404730598183,"timePerTask":null,"intelligence":28.8603469587486,"coding":39.4246774864752,"agentic":11.0214639175258,"mmmu":null,"priceInput1m":5,"priceOutput1m":30,"activeParams":null,"isOpenWeights":false,"isReasoning":true,"rawResultJson":"{\"id\":\"c4169d75-9d24-4794-a9c3-69e1fe364de5\",\"slug\":\"gpt-5-5-instant-06-26\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-5.5 Instant (June 2026)\",\"short_name\":\"GPT-5.5 Instant (June 2026)\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2026-06-25\",\"knowledge_cutoff_date\":\"2025-08-31\",\"intelligence_index\":28.8603469587486,\"coding_index\":39.4246774864752,\"agentic_index\":11.0214639175258,\"mmmu_pro\":null,\"intelligence_index_cost\":{\"total\":528.0811447088156,\"input\":401.3106847088156,\"nonCacheInput\":58.94536000000001,\"cacheRead\":87.88435336568716,\"cacheWrite\":254.48097134312843,\"output\":126.77046,\"reasoning\":38.036730000000006,\"answer\":88.73373},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.7108087581976272,\"input\":0.6360093366929683,\"nonCacheInput\":0.031706656504866315,\"cacheRead\":0.15938273100859426,\"cacheWrite\":0.44491994917950783,\"output\":0.07479942150465903,\"reasoning\":0.002995374198677195,\"answer\":0.07180404730598183},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.012195465242875032},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.027663181804896797},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.6303284587403007},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.002152735821759259},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0029889373841519924},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.0011378772095959598},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0037181830357142856},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.0005900752083333332},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.030033843750000004}]},\"intelligence_index_time_per_task\":null,\"price_1m_input_tokens\":5,\"price_1m_output_tokens\":30,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":true}","quality":26.435496120916536,"costForScoring":0.7108087581976272,"costPenalty":18.517527703058406,"pointsPerK":37190.72931508061,"costPerQuality":0.02688842134629789,"deltaTop":-36.99166011207173,"costVsTop":0.6852290504382783,"calculated":26.435496120916536,"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":51.92143109372129,"inputCost":22.185739493721286,"outputCost":29.735691600000003,"reasoningCost":27.4816284,"answerCost":2.2540632,"costPerTask":0.02941342816635502,"inputCostPerTask":0.02130035942764653,"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\":51.92143109372129,\"input\":22.185739493721286,\"nonCacheInput\":1.52308663,\"cacheRead\":14.453758617415348,\"cacheWrite\":6.2088942463059364,\"output\":29.735691600000003,\"reasoning\":27.4816284,\"answer\":2.2540632},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.02941342816635502,\"input\":0.02130035942764653,\"nonCacheInput\":0.0008185234149300485,\"cacheRead\":0.014291382947331382,\"cacheWrite\":0.006190453065385108,\"output\":0.008113068738708479,\"reasoning\":0.006171652418566655,\"answer\":0.0019414163201418235},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.009831012599800732},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.005527526500978795},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.010049643042780904},{\"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":0.02941342816635502,"costPenalty":4.685456449411081,"pointsPerK":861036.486873044,"costPerQuality":0.0011613909691929763,"deltaTop":-38.10112137773729,"costVsTop":0.028354934038337005,"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":106.69471541723105,"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\":106.69471541723105,\"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":-39.47861729783213,"costVsTop":0.1981160029390873,"calculated":23.948538935156133,"frontier":false},{"modelKey":"qwen3-6-35b-a3b-non-reasoning","sourceId":"66938aab-78fa-49d7-8461-b48b6833e837","slug":"qwen3-6-35b-a3b-non-reasoning","name":"Qwen3.6 35B A3B (Non-reasoning)","shortName":"Qwen3.6 35B A3B","creatorName":"Alibaba","creatorSlug":"alibaba","releaseDate":"2026-04-16","cutoffDate":null,"totalCost":495.83998837499996,"inputCost":433.602067875,"outputCost":62.237920499999994,"reasoningCost":0,"answerCost":62.237920499999994,"costPerTask":0.5978996209071737,"inputCostPerTask":0.5597645293524005,"outputCostPerTask":0.038135091554772994,"reasoningCostPerTask":0,"answerCostPerTask":0.038135091554772994,"timePerTask":97.06888397551624,"intelligence":24.1629373266649,"coding":28.1397385212928,"agentic":19.1415463917526,"mmmu":0.710404624277457,"priceInput1m":0.375,"priceOutput1m":2.25,"activeParams":3,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"66938aab-78fa-49d7-8461-b48b6833e837\",\"slug\":\"qwen3-6-35b-a3b-non-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Qwen3.6 35B A3B (Non-reasoning)\",\"short_name\":\"Qwen3.6 35B A3B\",\"creator_name\":\"Alibaba\",\"creator_slug\":\"alibaba\",\"release_date\":\"2026-04-16\",\"knowledge_cutoff_date\":null,\"intelligence_index\":24.1629373266649,\"coding_index\":28.1397385212928,\"agentic_index\":19.1415463917526,\"mmmu_pro\":0.710404624277457,\"intelligence_index_cost\":{\"total\":495.83998837499996,\"input\":433.602067875,\"nonCacheInput\":4.8576236250000004,\"cacheRead\":327.7971181752621,\"cacheWrite\":100.94732607473794,\"output\":62.237920499999994,\"reasoning\":0,\"answer\":62.237920499999994},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.5978996209071737,\"input\":0.5597645293524005,\"nonCacheInput\":0.0027642235533985758,\"cacheRead\":0.41897128425002633,\"cacheWrite\":0.13802902154897562,\"output\":0.038135091554772994,\"reasoning\":0,\"answer\":0.038135091554772994},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.16125729630681818},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.023989197164948454},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.40636888272471905},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.000058561414930555556},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.0017452106840824839},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00047792589962121214},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0014178746651785713},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000010488765624999997},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0025741832812499997}]},\"intelligence_index_time_per_task\":97.06888397551624,\"price_1m_input_tokens\":0.375,\"price_1m_output_tokens\":2.25,\"activeParams\":3,\"is_open_weights\":true,\"reasoning_model\":false}","quality":23.8147407465701,"costForScoring":0.5978996209071737,"costPenalty":17.76628278059764,"pointsPerK":39830.66707825766,"costPerQuality":0.02510628300638905,"deltaTop":-39.61241548641816,"costVsTop":0.5763831477407321,"calculated":23.8147407465701,"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":115.1550515476034,"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\":115.1550515476034,\"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},{"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":81.71682452124249,"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\":81.71682452124249,\"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":-41.370707058495285,"costVsTop":0.19070621597705814,"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":247.25668894999998,"inputCost":208.44684454999998,"outputCost":38.8098444,"reasoningCost":0,"answerCost":38.8098444,"costPerTask":0.32902581609337966,"inputCostPerTask":0.31038044816969573,"outputCostPerTask":0.018645367923683865,"reasoningCostPerTask":0,"answerCostPerTask":0.018645367923683865,"timePerTask":146.85373589185494,"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\":247.25668894999998,\"input\":208.44684454999998,\"nonCacheInput\":4.903409,\"cacheRead\":155.7541771287836,\"cacheWrite\":47.78925842121639,\"output\":38.8098444,\"reasoning\":0,\"answer\":38.8098444},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.32902581609337966,\"input\":0.31038044816969573,\"nonCacheInput\":0.0026098707778037652,\"cacheRead\":0.23740513564475893,\"cacheWrite\":0.07036544174713312,\"output\":0.018645367923683865,\"reasoning\":0,\"answer\":0.018645367923683865},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.04689568602272727},{\"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\":146.85373589185494,\"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":0.32902581609337966,"costPenalty":15.172299749926392,"pointsPerK":66992.93177972437,"costPerQuality":0.014926947865008248,"deltaTop":-41.38475218167633,"costVsTop":0.317185241362293,"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":65.79867477527543,"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\":65.79867477527543,\"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":-41.460422871419716,"costVsTop":0.04007559222196002,"calculated":21.966733361568544,"frontier":false},{"modelKey":"gemma-4-31b-non-reasoning","sourceId":"d0aa27aa-4705-4184-9a1d-483b78c9331c","slug":"gemma-4-31b-non-reasoning","name":"Gemma 4 31B (Non-reasoning)","shortName":"Gemma 4 31B","creatorName":"Google","creatorSlug":"google","releaseDate":"2026-04-02","cutoffDate":null,"totalCost":28.97847402,"inputCost":26.24282122,"outputCost":2.7356528000000004,"reasoningCost":0,"answerCost":2.7356528000000004,"costPerTask":0.034332261679026484,"inputCostPerTask":0.03251755007865703,"outputCostPerTask":0.0018147116003694459,"reasoningCostPerTask":0,"answerCostPerTask":0.0018147116003694459,"timePerTask":86.29927246538053,"intelligence":21.7687676184792,"coding":33.1716430850326,"agentic":10.9585360824742,"mmmu":0.703468208092486,"priceInput1m":0.14,"priceOutput1m":0.4,"activeParams":null,"isOpenWeights":true,"isReasoning":false,"rawResultJson":"{\"id\":\"d0aa27aa-4705-4184-9a1d-483b78c9331c\",\"slug\":\"gemma-4-31b-non-reasoning\",\"model_url\":null,\"hosts_url\":null,\"name\":\"Gemma 4 31B (Non-reasoning)\",\"short_name\":\"Gemma 4 31B\",\"creator_name\":\"Google\",\"creator_slug\":\"google\",\"release_date\":\"2026-04-02\",\"knowledge_cutoff_date\":null,\"intelligence_index\":21.7687676184792,\"coding_index\":33.1716430850326,\"agentic_index\":10.9585360824742,\"mmmu_pro\":0.703468208092486,\"intelligence_index_cost\":{\"total\":28.97847402,\"input\":26.24282122,\"nonCacheInput\":1.8825030000000003,\"cacheRead\":19.24297941742536,\"cacheWrite\":5.117338802574641,\"output\":2.7356528000000004,\"reasoning\":0,\"answer\":2.7356528000000004},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.034332261679026484,\"input\":0.03251755007865703,\"nonCacheInput\":0.0010054703768415853,\"cacheRead\":0.02498815179360713,\"cacheWrite\":0.006523927908208316,\"output\":0.0018147116003694459,\"reasoning\":0,\"answer\":0.0018147116003694459},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.007591241469696969},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0029931012027491414},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.022486812883895133},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.000057573038194444446},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00006966624420759962},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000020617266414141415},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.0001643133392857143},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000006395959583333334},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.000942540275}]},\"intelligence_index_time_per_task\":86.29927246538053,\"price_1m_input_tokens\":0.14,\"price_1m_output_tokens\":0.4,\"activeParams\":null,\"is_open_weights\":true,\"reasoning_model\":false}","quality":21.966315595328666,"costForScoring":0.034332261679026484,"costPenalty":5.357024140394228,"pointsPerK":639815.5705759358,"costPerQuality":0.0015629503969399195,"deltaTop":-41.460840637659594,"costVsTop":0.03309675464518825,"calculated":21.966315595328666,"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":93.08865315519593,"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\":93.08865315519593,\"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":-42.51897140251944,"costVsTop":0.16661721222878909,"calculated":20.908184830468816,"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":179.09621755000003,"inputCost":148.09391170000004,"outputCost":31.00230585,"reasoningCost":28.42221345,"answerCost":2.5800924,"costPerTask":0.1638454723745099,"inputCostPerTask":0.15895208090697904,"outputCostPerTask":0.004893391467530842,"reasoningCostPerTask":0.003108458162029565,"answerCostPerTask":0.0017849333055012765,"timePerTask":405.5375019401855,"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\":179.09621755000003,\"input\":148.09391170000004,\"nonCacheInput\":1.1930614000000002,\"cacheRead\":129.27655997361651,\"cacheWrite\":17.624290326383502,\"output\":31.00230585,\"reasoning\":28.42221345,\"answer\":2.5800924},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.1638454723745099,\"input\":0.15895208090697904,\"nonCacheInput\":0.0006369481258783386,\"cacheRead\":0.13915274969333336,\"cacheWrite\":0.019162383087767333,\"output\":0.004893391467530842,\"reasoning\":0.003108458162029565,\"answer\":0.0017849333055012765},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.07605431844696971},{\"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\":405.5375019401855,\"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":0.1638454723745099,"costPenalty":12.144344448033234,"pointsPerK":116990.710396567,"costPerQuality":0.008547687219013111,"deltaTop":-44.25875802463325,"costVsTop":0.15794920385967096,"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":39.22840749849603,"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\":39.22840749849603,\"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":-46.128874971106924,"costVsTop":0.20511561193954392,"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":35.047044920000005,"inputCost":15.7580426,"outputCost":19.28900232,"reasoningCost":18.212071920000003,"answerCost":1.0769304000000002,"costPerTask":0.017954722750171244,"inputCostPerTask":0.013645245351918881,"outputCostPerTask":0.004309477398252359,"reasoningCostPerTask":0.003494572208925244,"answerCostPerTask":0.0008149051893271147,"timePerTask":78.11469610955338,"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\":35.047044920000005,\"input\":15.7580426,\"nonCacheInput\":0.50318504,\"cacheRead\":10.370051826022387,\"cacheWrite\":4.884805733977614,\"output\":19.28900232,\"reasoning\":18.212071920000003,\"answer\":1.0769304000000002},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.017954722750171244,\"input\":0.013645245351918881,\"nonCacheInput\":0.0002602335473388548,\"cacheRead\":0.009060882221486767,\"cacheWrite\":0.004324129583093263,\"output\":0.004309477398252359,\"reasoning\":0.003494572208925244,\"answer\":0.0008149051893271147},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.009414314651515153},{\"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\":78.11469610955338,\"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":0.017954722750171244,"costPenalty":2.541787033077962,"pointsPerK":886001.9027023223,"costPerQuality":0.0011286657477258021,"deltaTop":-47.519237713843864,"costVsTop":0.01730859036146224,"calculated":15.907918519144395,"frontier":false},{"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":-48.01551114836501,"costVsTop":0.23824385925529784,"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":28.530933342491437,"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\":28.530933342491437,\"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":-48.01939822220941,"costVsTop":0.03952727563471095,"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":286.63231993677425,"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\":286.63231993677425,\"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":-48.647777637206026,"costVsTop":0.23659486054910325,"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":60.82858887445007,"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\":60.82858887445007,\"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":-49.58878591439828,"costVsTop":0.05773410634125957,"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":55.29156544476647,"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\":81.03778676620591,\"cacheWrite\":30.1966584337941,\"output\":17.287956,\"reasoning\":0,\"answer\":17.287956},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.1448042873568494,\"input\":0.13471121090095206,\"nonCacheInput\":0.001528329337290387,\"cacheRead\":0.09716415802671553,\"cacheWrite\":0.0360187235369461,\"output\":0.010093076455897328,\"reasoning\":0,\"answer\":0.010093076455897328},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.036263178181818186},{\"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\":55.29156544476647,\"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":-49.64449735093013,"costVsTop":0.1395932494930487,"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":205.29823298051744,"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\":205.29823298051744,\"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":-49.7443038003122,"costVsTop":0.7202577914972671,"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":19.83829069,"inputCost":16.90068816,"outputCost":2.93760253,"reasoningCost":0,"answerCost":2.93760253,"costPerTask":0.02306532978658411,"inputCostPerTask":0.021047998820521982,"outputCostPerTask":0.0020173309660621295,"reasoningCostPerTask":0,"answerCostPerTask":0.0020173309660621295,"timePerTask":null,"intelligence":14.160584979307,"coding":23.0415106117354,"agentic":1.5807560137457,"mmmu":null,"priceInput1m":0.36,"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\":19.83829069,\"input\":16.90068816,\"nonCacheInput\":4.26948768,\"cacheRead\":4.413318475313981,\"cacheWrite\":8.217882004686018,\"output\":2.93760253,\"reasoning\":0,\"answer\":2.93760253},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.02306532978658411,\"input\":0.021047998820521982,\"nonCacheInput\":0.0022911192422125364,\"cacheRead\":0.006696977740258061,\"cacheWrite\":0.012059901838051383,\"output\":0.0020173309660621295,\"reasoning\":0,\"answer\":0.0020173309660621295},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0012934253636363636},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.003303826331615121},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.01595700161048689},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00009719023726851852},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00008043685820203892},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000038618885732323235},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00015380573214285716},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00000688531125},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0021341394562499998}]},\"intelligence_index_time_per_task\":null,\"price_1m_input_tokens\":0.36,\"price_1m_output_tokens\":0.89,\"activeParams\":37,\"is_open_weights\":true,\"reasoning_model\":false}","quality":12.927617201596034,"costForScoring":0.02306532978658411,"costPenalty":3.629596685029143,"pointsPerK":560478.3162092636,"costPerQuality":0.0017841903443533648,"deltaTop":-50.499539031392224,"costVsTop":0.02223528318331788,"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":89.85610375490444,"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\":89.85610375490444,\"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":-50.53215907161975,"costVsTop":0.01720067446672282,"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":131.71005663,"inputCost":126.00937787999999,"outputCost":5.70067875,"reasoningCost":0,"answerCost":5.70067875,"costPerTask":0.18096457632730614,"inputCostPerTask":0.177626702284978,"outputCostPerTask":0.003337874042328135,"reasoningCostPerTask":0,"answerCostPerTask":0.003337874042328135,"timePerTask":null,"intelligence":15.4301213476181,"coding":21.1597482313774,"agentic":1.51202749140893,"mmmu":null,"priceInput1m":1.14,"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\":131.71005663,\"input\":126.00937787999999,\"nonCacheInput\":13.655366879999999,\"cacheRead\":86.3332860685583,\"cacheWrite\":26.02072493144169,\"output\":5.70067875,\"reasoning\":0,\"answer\":5.70067875},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.18096457632730614,\"input\":0.177626702284978,\"nonCacheInput\":0.007359897425990856,\"cacheRead\":0.13164855190435237,\"cacheWrite\":0.038618252954634794,\"output\":0.003337874042328135,\"reasoning\":0,\"answer\":0.003337874042328135},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.013401702393939393},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.018016419484536084},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.14171365928838947},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.0002695807378472222},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00022729777745597775},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.00007835446022727274},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00042799883928571424},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000018598626875},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.006810964718749999}]},\"intelligence_index_time_per_task\":null,\"price_1m_input_tokens\":1.14,\"price_1m_output_tokens\":1.25,\"activeParams\":37,\"is_open_weights\":true,\"reasoning_model\":false}","quality":12.700632356801476,"costForScoring":0.18096457632730614,"costPenalty":12.575935703873377,"pointsPerK":70182.97511348384,"costPerQuality":0.014248469780356685,"deltaTop":-50.72652387618678,"costVsTop":0.17445224664107026,"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":31.01207367722129,"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\":31.01207367722129,\"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":-50.73757270755211,"costVsTop":0.2367270811922981,"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":74.66657720190258,"inputCost":66.39131800190259,"outputCost":8.2752592,"reasoningCost":0,"answerCost":8.2752592,"costPerTask":0.06370503454354323,"inputCostPerTask":0.05897370441905791,"outputCostPerTask":0.00473133012448532,"reasoningCostPerTask":0,"answerCostPerTask":0.00473133012448532,"timePerTask":41.44225393841085,"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\":74.66657720190258,\"input\":66.39131800190259,\"nonCacheInput\":4.8381108,\"cacheRead\":34.66225506603247,\"cacheWrite\":26.890952135870112,\"output\":8.2752592,\"reasoning\":0,\"answer\":8.2752592},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.06370503454354323,\"input\":0.05897370441905791,\"nonCacheInput\":0.002614104813725431,\"cacheRead\":0.03162890456424131,\"cacheWrite\":0.024730695041091173,\"output\":0.00473133012448532,\"reasoning\":0,\"answer\":0.00473133012448532},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0348319085079796},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.008446362602436346},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.017096812550811993},{\"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\":41.44225393841085,\"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":0.06370503454354323,"costPenalty":8.041737555391187,"pointsPerK":191978.15901975267,"costPerQuality":0.005208925875245578,"deltaTop":-51.19718098102908,"costVsTop":0.06141249643448128,"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":400.538382,"inputCost":39.273641999999995,"outputCost":361.26474,"reasoningCost":344.898726,"answerCost":16.366014,"costPerTask":0.1686499528237036,"inputCostPerTask":0.035320494351958324,"outputCostPerTask":0.13332945847174527,"reasoningCostPerTask":0.12182073366620857,"answerCostPerTask":0.0115087248055367,"timePerTask":110.50359144851443,"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\":400.538382,\"input\":39.273641999999995,\"nonCacheInput\":5.807819,\"cacheRead\":21.670111838158515,\"cacheWrite\":11.795711161841483,\"output\":361.26474,\"reasoning\":344.898726,\"answer\":16.366014},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.1686499528237036,\"input\":0.035320494351958324,\"nonCacheInput\":0.0031630848700636297,\"cacheRead\":0.02070283021741785,\"cacheWrite\":0.011454579264476853,\"output\":0.13332945847174527,\"reasoning\":0.12182073366620857,\"answer\":0.0115087248055367},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.05538468371212122},{\"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\":110.50359144851443,\"price_1m_input_tokens\":0.5,\"price_1m_output_tokens\":6,\"activeParams\":3,\"is_open_weights\":true,\"reasoning_model\":true}","quality":12.066942186244999,"costForScoring":0.1686499528237036,"costPenalty":12.269862240404407,"pointsPerK":71550.22568467035,"costPerQuality":0.013976196307292016,"deltaTop":-51.36021404674326,"costVsTop":0.16258078659986974,"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":18.80257855697655,"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\":18.80257855697655,\"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":-52.81081086615365,"costVsTop":0.030454219287917868,"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":242.31340958841378,"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\":242.31340958841378,\"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":-53.246708701556855,"costVsTop":0.017653322316038035,"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":151.8952864,"inputCost":23.1292864,"outputCost":128.766,"reasoningCost":121.1333808,"answerCost":7.632619199999999,"costPerTask":0.07164709339313349,"inputCostPerTask":0.024908314506249286,"outputCostPerTask":0.04673877888688421,"reasoningCostPerTask":0.04207285708963394,"answerCostPerTask":0.00466592179725028,"timePerTask":156.46439793569093,"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\":151.8952864,\"input\":23.1292864,\"nonCacheInput\":2.34722,\"cacheRead\":15.485609109865791,\"cacheWrite\":5.296457290134209,\"output\":128.766,\"reasoning\":121.1333808,\"answer\":7.632619199999999},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.07164709339313349,\"input\":0.024908314506249286,\"nonCacheInput\":0.0012791262173016632,\"cacheRead\":0.01769869018352733,\"cacheWrite\":0.005930498105420293,\"output\":0.04673877888688421,\"reasoning\":0.04207285708963394,\"answer\":0.00466592179725028},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.02862558606060606},{\"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\":156.46439793569093,\"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":0.07164709339313349,"costPenalty":8.551985764650025,"pointsPerK":131824.74995994108,"costPerQuality":0.007585828915312792,"deltaTop":-53.98229606108189,"costVsTop":0.06906874627843239,"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":134.6342759765286,"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\":134.6342759765286,\"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":-54.222462737951915,"costVsTop":0.14381752355216734,"calculated":9.204693495036343,"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":124.99363530000001,"outputCost":2.5179525,"reasoningCost":0,"answerCost":2.5179525,"costPerTask":0.12378644187922404,"inputCostPerTask":0.12136605291913356,"outputCostPerTask":0.0024203889600904614,"reasoningCostPerTask":0,"answerCostPerTask":0.0024203889600904614,"timePerTask":51.26356516398083,"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\":124.99363530000001,\"nonCacheInput\":1.1934921,\"cacheRead\":40.797441537238484,\"cacheWrite\":83.00270166276152,\"output\":2.5179525,\"reasoning\":0,\"answer\":2.5179525},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.12378644187922404,\"input\":0.12136605291913356,\"nonCacheInput\":0.0006473324427638098,\"cacheRead\":0.03965569519294945,\"cacheWrite\":0.0810630252834203,\"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\":0.04600281779026217},{\"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\":51.26356516398083,\"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":0.12378644187922404,"costPenalty":10.926730797447659,"pointsPerK":67567.55950436299,"costPerQuality":0.014800001766164542,"deltaTop":-55.06320845548042,"costVsTop":0.1193317682819696,"calculated":8.36394777750784,"frontier":false},{"modelKey":"gpt-4-1-nano","sourceId":"72c358fd-7d45-4d68-89aa-699743710924","slug":"gpt-4-1-nano","name":"GPT-4.1 nano","shortName":"GPT-4.1 nano","creatorName":"OpenAI","creatorSlug":"openai","releaseDate":"2025-04-14","cutoffDate":"2024-05-31","totalCost":48.66022745977035,"inputCost":45.18142985977035,"outputCost":3.4787976,"reasoningCost":0,"answerCost":3.4787976,"costPerTask":0.03990804499935565,"inputCostPerTask":0.03737722908358822,"outputCostPerTask":0.0025308159157674316,"reasoningCostPerTask":0,"answerCostPerTask":0.0025308159157674316,"timePerTask":40.884407334351856,"intelligence":9.57520479903005,"coding":11.1388542100153,"agentic":1.16838487972509,"mmmu":0.401156069364162,"priceInput1m":0.1,"priceOutput1m":0.4,"activeParams":null,"isOpenWeights":false,"isReasoning":false,"rawResultJson":"{\"id\":\"72c358fd-7d45-4d68-89aa-699743710924\",\"slug\":\"gpt-4-1-nano\",\"model_url\":null,\"hosts_url\":null,\"name\":\"GPT-4.1 nano\",\"short_name\":\"GPT-4.1 nano\",\"creator_name\":\"OpenAI\",\"creator_slug\":\"openai\",\"release_date\":\"2025-04-14\",\"knowledge_cutoff_date\":\"2024-05-31\",\"intelligence_index\":9.57520479903005,\"coding_index\":11.1388542100153,\"agentic_index\":1.16838487972509,\"mmmu_pro\":0.401156069364162,\"intelligence_index_cost\":{\"total\":48.66022745977035,\"input\":45.18142985977035,\"nonCacheInput\":1.1520740999999999,\"cacheRead\":22.12927484674322,\"cacheWrite\":21.900080913027125,\"output\":3.4787976,\"reasoning\":0,\"answer\":3.4787976},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.03990804499935565,\"input\":0.03737722908358822,\"nonCacheInput\":0.0006161152018109874,\"cacheRead\":0.01845778121761676,\"cacheWrite\":0.018303332664160475,\"output\":0.0025308159157674316,\"reasoning\":0,\"answer\":0.0025308159157674316},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.03218354493055431},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0008998376855374764},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.006079240047702308},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00003909675925925926},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00003421155583873957},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000016848832070707073},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00008527973214285714},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.00000210364375},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.0005678818125}]},\"intelligence_index_time_per_task\":40.884407334351856,\"price_1m_input_tokens\":0.1,\"price_1m_output_tokens\":0.4,\"activeParams\":null,\"is_open_weights\":false,\"reasoning_model\":false}","quality":7.294147962923479,"costForScoring":0.03990804499935565,"costPenalty":6.010604532466141,"pointsPerK":182773.87336416126,"costPerQuality":0.005471241494169058,"deltaTop":-56.13300827006478,"costVsTop":0.03847188356133544,"calculated":7.294147962923479,"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":18.902121513400584,"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\":18.902121513400584,\"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":-56.20275058098785,"costVsTop":0.0769505142446533,"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":113.47784745,"inputCost":110.6603826,"outputCost":2.81746485,"reasoningCost":0,"answerCost":2.81746485,"costPerTask":0.18482442028714433,"inputCostPerTask":0.18247149581360883,"outputCostPerTask":0.002352924473535504,"reasoningCostPerTask":0,"answerCostPerTask":0.002352924473535504,"timePerTask":132.81283045696495,"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\":113.47784745,\"input\":110.6603826,\"nonCacheInput\":1.8611035499999997,\"cacheRead\":93.12189607101335,\"cacheWrite\":15.677382978986659,\"output\":2.81746485,\"reasoning\":0,\"answer\":2.81746485},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.18482442028714433,\"input\":0.18247149581360883,\"nonCacheInput\":0.0010182412169369912,\"cacheRead\":0.1565889374882913,\"cacheWrite\":0.024864317108380534,\"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\":132.81283045696495,\"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":-56.79868707997883,"costVsTop":0.17817318730329051,"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":11.49795345,"inputCost":8.924196575,"outputCost":2.573756875,"reasoningCost":0,"answerCost":2.573756875,"costPerTask":0.008688614897209117,"inputCostPerTask":0.007907870121422376,"outputCostPerTask":0.0007807447757867399,"reasoningCostPerTask":0,"answerCostPerTask":0.0007807447757867399,"timePerTask":13.062976623212121,"intelligence":10.0416226283387,"coding":8.16817519766958,"agentic":1.09965635738832,"mmmu":0.529479768786127,"priceInput1m":0.175,"priceOutput1m":0.625,"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\":11.49795345,\"input\":8.924196575,\"nonCacheInput\":2.110408125,\"cacheRead\":5.187298905503713,\"cacheWrite\":1.6264895444962866,\"output\":2.573756875,\"reasoning\":0,\"answer\":2.573756875},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.008688614897209117,\"input\":0.007907870121422376,\"nonCacheInput\":0.0011266112350534763,\"cacheRead\":0.005147099813125058,\"cacheWrite\":0.0016341590732438422,\"output\":0.0007807447757867399,\"reasoning\":0,\"answer\":0.0007807447757867399},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.0030947973863636362},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.0014977351589347079},{\"slug\":\"terminalbench-v2-1\",\"weightedCostPerTask\":0.002719682209737827},{\"slug\":\"scicode\",\"weightedCostPerTask\":0.00007138213975694444},{\"slug\":\"humanitys-last-exam\",\"weightedCostPerTask\":0.00010388913200880446},{\"slug\":\"gpqa-diamond\",\"weightedCostPerTask\":0.000037005894886363636},{\"slug\":\"critpt\",\"weightedCostPerTask\":0.00011013109375},{\"slug\":\"omniscience\",\"weightedCostPerTask\":0.000005386631770833333},{\"slug\":\"artificial-analysis-long-context-reasoning\",\"weightedCostPerTask\":0.00104860525}]},\"intelligence_index_time_per_task\":13.062976623212121,\"price_1m_input_tokens\":0.175,\"price_1m_output_tokens\":0.625,\"activeParams\":17,\"is_open_weights\":true,\"reasoning_model\":false}","quality":6.436484727798867,"costForScoring":0.008688614897209117,"costPenalty":0,"pointsPerK":740795.2595374367,"costPerQuality":0.001349900646805454,"deltaTop":-56.9906715051894,"costVsTop":0.008375939754505906,"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":91.78447990000001,"inputCost":89.04921610000001,"outputCost":2.7352638000000002,"reasoningCost":0,"answerCost":2.7352638000000002,"costPerTask":0.12619350182313843,"inputCostPerTask":0.12414934273719067,"outputCostPerTask":0.0020441590859477435,"reasoningCostPerTask":0,"answerCostPerTask":0.0020441590859477435,"timePerTask":114.79125687908424,"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\":91.78447990000001,\"input\":89.04921610000001,\"nonCacheInput\":1.2819872,\"cacheRead\":77.3736040734019,\"cacheWrite\":10.393624826598101,\"output\":2.7352638000000002,\"reasoning\":0,\"answer\":2.7352638000000002},\"intelligence_index_cost_per_task\":{\"cost\":{\"total\":0.12619350182313843,\"input\":0.12414934273719067,\"nonCacheInput\":0.0007059897267287182,\"cacheRead\":0.1091640300016485,\"cacheWrite\":0.014279323008813464,\"output\":0.0020441590859477435,\"reasoning\":0,\"answer\":0.0020441590859477435},\"evaluations\":[{\"slug\":\"gdpval-aa\",\"weightedCostPerTask\":0.02550046954545455},{\"slug\":\"tau3-banking\",\"weightedCostPerTask\":0.003741568298969073},{\"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\":114.79125687908424,\"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":-59.03858726976217,"costVsTop":0.12165220592527998,"calculated":4.388568963226094,"frontier":false}]}