| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.5 | Anthropic | 37.6 | 1 | 2026-07-29 |
| 2 | Gemini 3 Pro | 31.1 | 1 | 2026-07-29 | |
| 3 | GPT-5.1 | OpenAI | 17.6 | 1 | 2026-07-29 |
| 4 | Claude Sonnet 4.5 | Anthropic | 13.6 | 1 | 2026-07-29 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.