Contact for pricing · Free plan🇺🇸
Public AI arena, formerly LMArena, that ranks models for text, code, vision, search, images and video from anonymous side-by-side votes.
Artificial Analysis AI features and pricing (October 2026)
Independent benchmarking of AI models and API providers on intelligence, speed, latency and price, with image, video and coding arenas.
FreemiumFree plan
Pricing: Freemium
Leaderboards, arenas and methodology are free to view. Commercial products such as the Optima insights platform, MicroEvals and the Model Recommender are sold without public prices, as of September 2026.
What is Artificial Analysis?
Artificial Analysis benchmarks AI models and the providers that serve them, comparing quality, speed and price. Teams use it to pick a model and an API provider for a given budget and latency need.
The company benchmarks language, image, video, speech and music models, agents with tools, inference providers and accelerator chips. It covers more than 500 models, 100 inference providers and 1,000 endpoints, according to its about page. Leaderboards, arenas and methodology are free; commercial products include Optima, MicroEvals, a Model Recommender and a Data Playground. Artificial Analysis is based in San Francisco with an office in Melbourne.
Artificial Analysis AI features and use cases
- Compares model quality in one scoreThe Intelligence Index (version 4.3.2 in September 2026) combines ten evaluations, among them Humanity's Last Exam, SciCode and Terminal-Bench, weighted across agents, coding, scientific reasoning and general tasks. Decision makers get a single comparison point before looking at details. The composition and weights are documented on the methodology page.
- Chooses the fastest providerFor the same open model, speeds differ by provider. Output speed and time to first token per endpoint help IT teams pick a provider for chatbots where users wait for answers.
- Estimates cost per taskA blended price and the cost per task, based on actual token use, show that verbose models cost more. Budget owners can compare real running costs with list prices. This supports budget planning.
What sets Artificial Analysis apart
- Measures API providers and endpoints alongside models, including speed and latency.
- Covers language, image, video, speech and music models and hardware accelerators.
Where Artificial Analysis is strongest
United States Available internationally
Artificial Analysis is headquartered in San Francisco and has an office in Melbourne.
Questions to ask before you buy Artificial Analysis
Benchmarks show general performance; test the shortlisted models on your own tasks and languages before deciding. Speed and price data are snapshots and change often. For the paid products, ask about pricing and terms, which are not public. Also check whether the fastest provider for a model offers the data protection terms you need.
Artificial Analysis reviews
No reviews yet. Be the first to share how your team uses it.
Every review shows its verification level. We read each one before it goes live. How we check reviews
Questions about Artificial Analysis
Is Artificial Analysis free?
The leaderboards, arenas and methodology are free to use. Optima, MicroEvals, the Model Recommender and the Data Playground are commercial products.
How is speed measured?
It measures what customers experience: time to first token, output tokens per second and end-to-end response time including reasoning.
How are prices compared?
A blended price uses a 7:2:1 ratio of cache hit, input and output tokens. Cost per task reflects the tokens a model actually uses.
Artificial Analysis update historyno updates yet
No changes recorded for Artificial Analysis yet.
Changes the vendor made and confirmed user reports, each checked against the vendor's own pages. We review every tool monthly.
Alternatives to Artificial Analysis
Tools in the same category (Model leaderboards) with the most overlapping markets.
Contact for pricing · Free plan🇺🇸
Scale AI's leaderboards with expert-built and partly private evaluations such as Humanity's Last Exam, SWE-Bench Pro and safety tests.
Contact for pricing🇺🇸
Independent evaluator that benchmarks AI models on professional work in law, finance, tax, healthcare, coding and other fields.
Free🇺🇸
Public leaderboard of how often language models add hallucinations when summarizing documents, scored with Vectara's open HHEM model.