| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | GLM-5 | Z.AI | Open weights | 97.5% | |
| 2 | Qwen3.6 Plus | Alibaba | Proprietary | 96.7% | |
| 3 | Kimi K2.5 | Moonshot AI | Open weights | 95.4% | |
| 4 | Qwen3.5 397B | Alibaba · Open weight | 94.8% | ||
| 5 | Qwen3.6-27B | Alibaba · Open weight | 93.8% | ||
| 6 | Claude Opus 4.5 | Anthropic · Closed | 92.9% | ||
| 7 | Qwen3.6-35B-A3B | Alibaba · Open weight | 90.7% | ||
| 8 | Granite 4.2 30B | IBM · Open weight | 89.2% | ||
| 9 | Granite 4.2 8B | IBM · Open weight | 78.3% | ||
| 10 | Granite 4.2 3B | IBM · Open weight | 66.7% |