| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Kimi K3 | Moonshot AI | Closed | kimi-3 | |
| 2 | Qwen3.7 Plus | Alibaba | Closed | qwen3-7-plus | |
| 3 | Qwen3.5 397B | Alibaba | Open | qwen3-5-397b | |
| 4 | Qwen3.6 Plus | Alibaba · Closed | 88.0% | ||
| 5 | Kimi K2.6 | Moonshot AI · Open weight | 87.4% | ||
| 6 | Gemini 3 Pro | Google · Closed | 86.6% | ||
| 7 | Qwen3.5-122B-A10B | Alibaba · Open weight | 86.2% | ||
| 8 | Qwen3.5-27B | Alibaba · Open weight | 86.0% | ||
| 9 | Qwen3.5-35B-A3B | Alibaba · Open weight | 83.9% | ||
| 10 | GPT-5.2 | OpenAI · Closed | 83.0% | ||
| 11 | Gemma 4 12B | Google · Open weight | 79.7% | ||
| 12 | Claude Opus 4.5 | Anthropic · Closed | 74.3% |