| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.5 | Anthropic | Closed | claude-opus-4-5 | |
| 2 | Qwen3.7 Max | Alibaba | Closed | qwen3-7-max | |
| 3 | Qwen3.5 397B | Alibaba | Open | qwen3-5-397b | |
| 4 | Qwen3.7 Plus | Alibaba · Closed | 94.5% | ||
| 5 | Qwen3.6 Plus | Alibaba · Closed | 94.5% | ||
| 6 | Qwen3.6-27B | Alibaba · Open weight | 93.5% | ||
| 7 | DeepSeek V4 Pro Base | DeepSeek · Open weight | 90.8% | ||
| 8 | DeepSeek V4 Flash Base | DeepSeek · Open weight | 89.4% | ||
| 9 | Mellum2-12B-A2.5B-Thinking | JetBrains · Open weight | 86.2% | ||
| 10 | Mellum2-12B-A2.5B-Instruct | JetBrains · Open weight | 78.1% | ||
| 11 | MiniCPM5-1B | OpenBMB · Open weight | 70.1% |