| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Qwen 3.5 397B 17B | Alibaba | 98 | 1 | 2026-08-24 |
| 2 | Kimi K2.6 1T A32B | Moonshot | 97.8 | 1 | 2026-08-24 |
| 3 | GLM-5.1-744B-A40B | Z.ai | 96.9 | 1 | 2026-08-24 |
| 4 | nvidia-nemotron-3-ultra-550b-a55b | NVIDIA | 92.9 | 1 | 2026-08-24 |
| 5 | MiniMax 2.7 230B A10B | MiniMax | 89.6 | 1 | 2026-08-24 |
| 6 | NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16 | NVIDIA | 61.5 | 1 | 2026-07-07 |
| 7 | Nemotron 3 Super 120B A12B | NVIDIA | 61.1 | 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.