BigLaw Bench — Harvey's published legal-AI benchmark, cited in Anthropic announcements; not the 'bbh' acronym
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.7 | Anthropic | 90.9 | 2 | 2026-06-21 |
| 2 | Claude Opus 4.6 | Anthropic | 90.2 | 1 | 2026-06-03 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.