| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Qwen3.7 Max | Alibaba | Proprietary | 47.9% | |
| 2 | Qwen3.7 Plus | Alibaba | Proprietary | 45.6% | |
| 3 | Qwen3.6 Plus | Alibaba | Proprietary | 44.3% | |
| 4 | Qwen3.5 397B | Alibaba · Open weight | 43.7% | ||
| 5 | Agents-A1-4B | InternScience · Open weight | 40.3% | ||
| 6 | Agents-A1 | InternScience · Open weight | 38.8% | ||
| 7 | Qwen3.6-35B-A3B | Alibaba · Open weight | 35.6% | ||
| 8 | Claude Opus 4.5 | Anthropic · Closed | 23.3% | ||
| 9 | LongCat-Flash-Lite-Sparse | Meituan · Open weight | 21.7% | ||
| 10 | DeepSeek V3.2 | DeepSeek · Open weight | 18.5% | ||
| 11 | Claude Sonnet 4.5 | Anthropic · Closed | 17.0% | ||
| 12 | GLM-4.7 | Z.AI · Open weight | 15.5% |