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