Legal Research Bench

Measures: An agent researches expert-written US legal questions (8 practice areas) with case-law search, web search and document retrieval, then writes an answer graded by an LLM judge against a lawyer-written rubric; primary metric is all-pass (every required rubric item must be met).

Maintainer: Vals AI (questions and rubrics authored by practicing lawyers)
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.