| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Qwen3.5 397B | Alibaba | Open | qwen3-5-397b | |
| 2 | Qwen3.7 Max | Alibaba | Closed | qwen3-7-max | |
| 3 | Qwen3.7 Plus | Alibaba | Closed | qwen3-7-plus | |
| 4 | Qwen3.6 Plus | Alibaba · Closed | 57.9% | ||
| 5 | Claude Opus 4.5 | Anthropic · Closed | 56.7% | ||
| 6 | Kimi K2.5 | Moonshot AI · Open weight | 56.0% | ||
| 7 | GLM-5 | Z.AI · Open weight | 55.1% |