| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Opus 5 | Anthropic | 70.6 | 3 | 2026-08-23 |
| 2 | Claude Fable 5 | Anthropic | 66.1 | 2 | 2026-08-24 |
| 3 | GPT-5.6 Sol | OpenAI | 62.6 | 3 | 2026-08-24 |
| 4 | Kimi K3 | Moonshot | 58.3 | 1 | 2026-08-24 |
| 5 | Claude Opus 4.8 | Anthropic | 55.7 | 2 | 2026-08-24 |
| 6 | GPT-5.6 Terra | OpenAI | 50.2 | 2 | 2026-08-23 |
| 7 | Gemini 3.7 Flash | 47.9 | 3 | 2026-08-24 | |
| 8 | GPT-5.6 Luna | OpenAI | 45.6 | 1 | 2026-08-23 |
| 9 | Gemini 3.6 Flash | 33.8 | 1 | 2026-08-14 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.