Comparison of AI Models across Intelligence, Performance, and Price

IntelligenceArtificial Analysis Intelligence IndexArtificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCRReasoning models are indicated by a lightbulb iconArtificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.Artificial Analysis Intelligence Index by Open Weights / ProprietaryArtificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCRReasoning models are indicated by a lightbulb iconArtificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).Intelligence EvaluationsIntelligence evaluations measured independently by Artificial Analysis · Higher is betterAgentic business operationsReasoning models are indicated by a lightbulb iconWhile model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR.

See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.AA-BriefcaseAA-Briefcase EloAA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is betterReasoning models are indicated by a lightbulb iconAA-Briefcase Elo is a combined metric that aggregates analytical quality Elo, presentation Elo, and rubric pass rate, with rubric performance converted into Elo via synthetic head-to-head matches. Elo and 95% confidence interval bounds are clamped at 0.AA-OmniscienceAA-Omniscience IndexAA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.Reasoning models are indicated by a lightbulb iconAA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.OpennessArtificial Analysis Openness Index: ScoreOpenness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)Reasoning models are indicated by a lightbulb iconIntelligence Index ComparisonsIntelligence Index vs. Cost per Intelligence Index TaskArtificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index taskMost attractive quadrantReasoning models are indicated by a lightbulb iconWeighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR.

See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.Token UseOutput Tokens per Intelligence Index TaskWeighted average number of output tokens used to run one task in the Artificial Analysis Intelligence IndexReasoning models are indicated by a lightbulb iconThe number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).Price and CostCost per Intelligence Index TaskWeighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is betterReasoning models are indicated by a lightbulb iconWeighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.Cost to Run Artificial Analysis Intelligence IndexCost (USD) to run all evaluations in the Artificial Analysis Intelligence IndexReasoning models are indicated by a lightbulb iconThe cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).Pricing: Cache Hit, Input, and OutputPrice (USD per M Tokens)Reasoning models are indicated by a lightbulb iconPrice per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.Price per token included in the request/message sent to the API, represented as USD per million Tokens.The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.See Prompt Caching for the full breakdown.

Price per token generated by the model (received from the API), represented as USD per million Tokens.Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).Context WindowContext WindowContext window: tokens limit · Higher is betterReasoning models are indicated by a lightbulb iconLarger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).SpeedMeasured by Output Speed (tokens per second)Output SpeedOutput tokens per second · Higher is betterReasoning models are indicated by a lightbulb iconTokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).Time per Intelligence Index TaskWeighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is betterReasoning models are indicated by a lightbulb iconThe weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.LatencyMeasured by Time (seconds) to First TokenLatency: Time To First Answer TokenSeconds to first answer token received · Accounts for reasoning model 'thinking' timeReasoning models are indicated by a lightbulb iconTime to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.