Vals AI LegalBench
Vals AI's continuously updated leaderboard for legal-domain LLM tasks, grounded in the academic LegalBench benchmark plus Vals's own attorney-graded private evaluations.
- Operator
- Vals AI
- Kind
- Aggregated
- Updates
- monthly·updated 4d ago
- Notable for
- The most prominent vertical (legal-domain) leaderboard, used as procurement reference by AmLaw 100 firms and legal-tech buyers.
- Tracks
- 2 evals · aggregated
Cite
Notes
Only stored in your browser.
Per-eval breakdown
5models
| Model | |||
|---|---|---|---|
| GPT-4o-mini OpenAI | 72.0% | - | 72.0% |
| GPT-4.1 Mini OpenAI | 62.4% | - | 62.4% |
| GPT-5 OpenAI | 58.2% | - | 58.2% |
| Claude Sonnet 4.5 Anthropic | 0.0% | - | 0.0% |
| GPT-4o OpenAI | 0.0% | - | 0.0% |
5 / 5 models