Updated daily at 05:00 UTC
Benchmark
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
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results