Harvey Legal Agent Benchmark (LAB)

Measures: An agent gets a partner-style instruction plus case documents in a sandbox (file tools, docx/xlsx/pptx skills) and must produce a legal deliverable (memo, disclosure schedule, redline); graded criterion-by-criterion against expert rubrics, headline is the share of tasks where every criterion passes.

Maintainer: Harvey
Introduced: 2026
Status: Active
Saturation: Headroom
Typical provenance: Independent
In scoring set: Yes

Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.