The AI arena is free today

Open Superagent
AI OrganizationMaintains 4 benchmarks

Harvey: AI benchmarks & research

Legal AI company. Maintains BigLaw Bench and the Legal Agent Benchmark.

Maintained by Harvey

4 benchmarks

In one line

Harvey maintains Harvey LAB (Vals) (counts toward the LLM Stats Score, 2 models scored), Harvey's Legal Agent Benchmark (counts toward the LLM Stats Score, 5 models scored), Legal Agent Benchmark (counts toward the LLM Stats Score, 16 models scored) and Harvey LAB-AA (counts toward the LLM Stats Score, 5 models scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about Harvey.

What is Harvey?

Legal AI company. Maintains BigLaw Bench and the Legal Agent Benchmark. On LLM Stats it maintains 4 benchmarks, led by Legal Agent Benchmark, Harvey LAB-AA and Harvey's Legal Agent Benchmark. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Harvey benchmarks count toward the LLM Stats Score?

Legal Agent Benchmark, Harvey LAB-AA, Harvey's Legal Agent Benchmark and Harvey LAB (Vals) 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 Harvey's benchmarks?

GLM-5.3-FlashX-Legal leads Legal Agent Benchmark at 19.2% (16 models scored), Gemini 3.7 Flash leads Harvey LAB-AA at 90.7% (5 models scored) and Kimi K3.1 Pro leads Harvey's Legal Agent Benchmark at 23.7% (5 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Harvey's official benchmark results?

Harvey's official site is https://www.harvey.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.