| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Qwen3.7 Max | Alibaba | Closed | 47.9% | |
| 2 | Qwen3.6 Plus | Alibaba | Closed | 44.3% | |
| 3 | Qwen3.5 397B | Alibaba | Open | 43.7% | |
| 4 | Qwen3.6-35B-A3B | Alibaba | Open | 35.6% | |
| 5 | Claude Opus 4.5 | Anthropic | Closed | 23.3% | |
| 6 | DeepSeek V3.2 | DeepSeek | Open | 18.5% | |
| 7 | Claude Sonnet 4.5 | Anthropic | Closed | 17.0% | |
| 8 | GLM-4.7 | Z.AI | Open | 15.5% |