Apps
4 apps for AI and large language model benchmarks. Prices come from each vendor site.
LMArenaFeatured
Crowdsourced side-by-side model comparisons.
Free to compare models; no paid tier on the public arena.
Artificial Analysis
Independent speed, price, and quality benchmarks.
Free public leaderboards; API access is a paid product (see vendor pricing).
Open LLM Leaderboard
Hugging Face aggregate of open-model evals.
Free on Hugging Face Spaces; submission queue is public.
SWE-bench
Real GitHub issues as coding-agent tasks.
Open benchmark and evaluation harness; compute is yours.
Published by AI Benchmark Index. How we check each benchmark.