Legal Agent Benchmark, Full Public Set — Same subset as 'Legal Agent Full Public Benchmark Set' (both incl. Mythos 5) - reworded dup.
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Mythos 5 | Anthropic | 16.9 | 2 | 2026-06-12 |
| 2 | Claude Opus 4.8 | Anthropic | 9.6 | 1 | 2026-06-12 |
| 3 | Claude Sonnet 5 | Anthropic | 8.9 | 1 | 2026-07-07 |
| 4 | Claude Sonnet 4.6 | Anthropic | 8 | 1 | 2026-06-30 |
| 5 | Claudes | Anthropic | 8 | 1 | 2026-08-12 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.