| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | Anthropic | 89.7 | 1 | 2026-07-07 |
| 2 | Claude Sonnet 5 | Anthropic | 86.7 | 1 | 2026-07-07 |
| 3 | Claude Sonnet 4.6 | Anthropic | 80.9 | 1 | 2026-07-07 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.