| # | Model | Provider | Type | Score | |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | Proprietary | 67.7% | |
| 2 | Claude Opus 5 | Anthropic | Proprietary | 64.7% | |
| 3 | DeepSeek V4.1 Flash | DeepSeek | Open weights | 63.9% | |
| 4 | GLM-5.3 | Z.AI · Open weight | 62.5% | ||
| 5 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | 60.0% | ||
| 6 | Claude Sonnet 5 | Anthropic · Closed | 57.4% | ||
| 7 | GPT-6 Astra | OpenAI · Closed | 57.2% | ||
| 8 | Qwen3.8 Max | Alibaba · Open weight | 56.2% | ||
| 9 | Apodex 1.1 | Apodex · Closed | 56.1% | ||
| 10 | Ornith-1.5-397B | Ornith AI · Open weight | 56.1% | ||
| 11 | Hy4 preview | Tencent · Open weight | 55.4% | ||
| 12 | GLM-5.3-Flash | Z.AI · Open weight | 55.3% | ||
| 13 | Qwen3.7 Max | Alibaba · Closed | 53.5% | ||
| 14 | dots3-note Preview | Dots Studio · Open weight | 52.6% | ||
| 15 | Agents-A1 | InternScience · Open weight | 47.6% | ||
| 16 | Step 3.7 Flash | StepFun · Open weight | 47.2% | ||
| 17 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | 45.1% | ||
| 20 | Nemotron 3 Ultra | NVIDIA · Open weight | 37.4% | ||
| 21 | Ornith-1.5-35B-A3B | Ornith AI · Open weight | 33.4% | ||
| 22 | Ornith-1.5-9B | Ornith AI · Open weight | 30.5% |