| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Opus 5 | Anthropic | 67.1 | 1 | 2026-07-24 |
| 2 | Claude Mythos 5 | Anthropic | 62.5 | 1 | 2026-07-24 |
| 3 | Claude Sonnet 5 | Anthropic | 59.2 | 1 | 2026-07-24 |
| 4 | Claude Opus 4.8 | Anthropic | 58.8 | 1 | 2026-07-24 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.