| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Fable 5 | Anthropic | 57.4 | 2 | 2026-08-12 |
| 2 | Muse Spark 1.1 | Meta | 54.7 | 2 | 2026-08-23 |
| 3 | Kimi K3 | Moonshot | 54.3 | 2 | 2026-08-23 |
| 4 | Qwen3.8 Max Preview | Alibaba | 53.4 | 2 | 2026-08-23 |
| 5 | Claude Opus 4.8 | Anthropic | 48.4 | 2 | 2026-08-12 |
| 6 | GPT-5.6 Sol | OpenAI | 45.4 | 2 | 2026-08-12 |
| 7 | GLM-5.2 Full Open Source | Z.ai | 43.4 | 1 | 2026-07-27 |
| 8 | GPT-5.5 | OpenAI | 38.3 | 1 | 2026-07-27 |
| 9 | Qwen3.8 27B | Alibaba | 33.4 | 2 | 2026-08-23 |
| 10 | Qwen3.7 Max | Alibaba | 31.3 | 1 | 2026-08-12 |
| 11 | Qwen3.7 Plus Preview | Alibaba | 27.6 | 1 | 2026-08-14 |
| 12 | Qwen3.6 27B | Alibaba | 21.8 | 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.