CritPt — CritPt physics benchmark, explicit no-tools mode; separate from base critpt (diff range/source)
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Kimi K2.6 1T A32B | Moonshot | 9.1 | 1 | 2026-06-06 |
| 2 | GLM-5.1-744B-A40B | Z.ai | 3.7 | 1 | 2026-06-06 |
| 3 | nvidia-nemotron-3-ultra-550b-a55b | NVIDIA | 3.1 | 1 | 2026-08-24 |
| 4 | Nemotron 3 Ultra 550B A55B | NVIDIA | 3.1 | 1 | 2026-06-06 |
| 5 | Qwen 3.5 397B 17B | Alibaba | 2.4 | 1 | 2026-06-06 |
| 6 | MiniMax 2.7 230B A10B | MiniMax | 0.6 | 1 | 2026-06-06 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.