Harvey's Legal Agent Benchmark B
AI benchmark · Legal
Latest from Vals AI on X
@ValsAI ↗What is Harvey's Legal Agent Benchmark?
Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools
Tier B
Established: 15 or more models scored, or curated RL directories rate it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 35 models scored
- in curated RL directories (2 pts)
On X · well regarded, moderate buzz, from 14 posts about Harvey's Legal Agent Benchmark in the last month
Labs like Mistral and Google cite Harvey's legal benchmark in launches; Artificial Analysis added a hallucination gate, and scores remain low, under 20%.
How we got to tier B
- Adoption: 35 models scored. Tier B.
- On X: well regarded, moderate buzz. “Labs like Mistral and Google cite Harvey's legal benchmark in launches; Artificial Analysis added a hallucination gate, and scores remain low, under 20%.” No move.
- In curated RL directories: 2 points, a floor of C.
- Not yet confirmed by a line from its own site or paper.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Not on the map yet: no line from its own site or paper places it in a domain.
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.