| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.6 | Anthropic | Closed | claude-opus-4-6 | |
| 2 | GLM-5 | Z.AI | Open | glm-5 | |
| 3 | GLM-5.1 | Z.AI | Open | glm-5-1 | |
| 4 | DeepSeek V3.2 | DeepSeek · Open weight | 60.9% | ||
| 5 | Claude Sonnet 4.6 | Anthropic · Closed | 60.7% | ||
| 6 | Qwen3.5-27B | Alibaba · Open weight | 58.9% | ||
| 7 | GLM-4.7 | Z.AI · Open weight | 58.7% | ||
| 8 | Kimi K2.5 | Moonshot AI · Open weight | 58.5% | ||
| 9 | GPT-5.3 Codex | OpenAI · Closed | 58.2% | ||
| 10 | Composer 2 | Cursor · Closed | 58% | ||
| 11 | Qwen3.5-35B-A3B | Alibaba · Open weight | 53.7% | ||
| 12 | MiniMax M2.7 | MiniMax · Open weight | 51.9% | ||
| 13 | Gemma 4 31B | Google · Open weight | 41.6% |