Vals Legal Research Bench
vals.ai- Category
- Developer Tools
- Listed in
- Find AI benchmarks
- Type
- TOOL
- Date
About
Evaluates cited US legal research with expert questions and shared research tools. A calibrated model judge scores held-out questions; all-pass and partial-credit results measure different outcomes.
Why it made the leaderboard
Compare the task, benchmark version, harness, and grading method before using model scores to choose a model.
Tags
benchmarkevaluation
Media
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.