| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | GLM-5.2 | Z.AI | Open weights | 91.0% | |
| 2 | Kimi K2.6 | Moonshot AI | Open weights | 86.0% | |
| 3 | Claude Opus 4.5 | Anthropic | Proprietary | 84.0% | |
| 4 | GLM-5.1 | Z.AI · Open weight | 83.8% | ||
| 5 | Qwen3.6 Plus | Alibaba · Closed | 83.8% | ||
| 6 | GLM-5 | Z.AI · Open weight | 82.5% | ||
| 7 | Kimi K2.5 | Moonshot AI · Open weight | 81.8% | ||
| 8 | Qwen3.5 397B | Alibaba · Open weight | 80.9% | ||
| 9 | Qwen3.6-27B | Alibaba · Open weight | 80.8% | ||
| 10 | Qwen3.6-35B-A3B | Alibaba · Open weight | 78.9% |