The AI arena is free today

Open Superagent
AI OrganizationMaintains 23 benchmarks

Artificial Analysis: AI benchmarks & research

Independent AI model evaluator. Maintains the Artificial Analysis Intelligence Index and its own runs of third-party benchmarks.

Maintained by Artificial Analysis

23 benchmarks

In one line

Artificial Analysis maintains AA-Briefcase (counts toward the LLM Stats Score, 5 models scored), AA-Briefcase v1.1 (counts toward the LLM Stats Score, 7 models scored), AA Controlled Voice Arena (counts toward the LLM Stats Score, 1 model scored), AA-Index (counts toward the LLM Stats Score, 4 models scored), AA Intelligence Index v4.3 (counts toward the LLM Stats Score, 3 models scored), AA-LCR (counts toward the LLM Stats Score, 32 models scored), AA-Omniscience Index (counts toward the LLM Stats Score, 6 models scored), AA Provider Voice Arena (counts toward the LLM Stats Score, 1 model scored), Artificial Analysis (counts toward the LLM Stats Score, 14 models scored), AutomationBench-AA (counts toward the LLM Stats Score, 6 models scored), Big Bench Audio (counts toward the LLM Stats Score, 2 models scored), Coding Agent Index (counts toward the LLM Stats Score, 1 model scored), GDPval-AA (counts toward the LLM Stats Score, 18 models scored), GDPval-AA 2.1 (counts toward the LLM Stats Score, 7 models scored), Harvey LAB-AA (counts toward the LLM Stats Score, 5 models scored), OmniScience (counts toward the LLM Stats Score, 10 models scored), OmniScience (non-hallucination rate) (counts toward the LLM Stats Score, 4 models scored), Pronunciation Robustness (counts toward the LLM Stats Score, 1 model scored), Pronunciation Robustness (Context) (counts toward the LLM Stats Score, 1 model scored), Pronunciation Robustness (Exact Sequences) (counts toward the LLM Stats Score, 1 model scored), Pronunciation Robustness (Names) (counts toward the LLM Stats Score, 1 model scored), Pronunciation Robustness (Shorthand) (counts toward the LLM Stats Score, 1 model scored) and Terminal-Bench 4.0-AA (counts toward the LLM Stats Score, 5 models scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about Artificial Analysis.

What is Artificial Analysis?

Independent AI model evaluator. Maintains the Artificial Analysis Intelligence Index and its own runs of third-party benchmarks. On LLM Stats it maintains 23 benchmarks, led by AA-LCR, GDPval-AA and Artificial Analysis. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Artificial Analysis benchmarks count toward the LLM Stats Score?

AA-LCR, GDPval-AA, Artificial Analysis, OmniScience, AA-Briefcase v1.1, GDPval-AA 2.1 and 17 more count toward the LLM Stats Score. Only benchmarks admitted to the core set move the main leaderboard; the rest are shown for transparency.

Which models lead Artificial Analysis's benchmarks?

Solar Mini 4 leads AA-LCR at 83.3% (32 models scored), Claude Fable 5.1 leads GDPval-AA at 1853 (18 models scored) and GPT-5.6 Sol leads Artificial Analysis at 59.0% (14 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Artificial Analysis's official benchmark results?

Artificial Analysis's official site is https://artificialanalysis.ai. Each benchmark page on LLM Stats links to that benchmark's own paper or leaderboard, and shows the scores next to every other benchmark so models can be compared on one page.