| 1 | Claude Opus 5.5 | Anthropic | Proprietary | 93.9% | |
| 2 | Claude Opus 5 | Anthropic | Proprietary | 89.5% | |
| 3 | Claude Fable 5.1 | Anthropic | Proprietary | 89.1% | |
| 4 | Claude Opus 4.8 | Anthropic · Closed | 84.4% | | |
| 5 | Hy4 preview | Tencent · Open weight | 82.9% | | |
| 6 | Qwen3.8-Flash-Next | Alibaba · Open weight | 81% | | |
| 7 | Qwen3.8-Omni-Flash | Alibaba · Closed | 80.5% | | |
| 8 | Composer 2.5 | Cursor · Closed | 79.8% | | |
| 9 | Ornith-1.5-397B | Ornith AI · Open weight | 79.6% | | |
| 10 | Ornith-1.0-397B | DeepReinforce AI · Open weight | 78.9% | | |
| 11 | Laguna S 2.1 | Poolside · Open weight | 78.5% | | |
| 12 | Claude Sonnet 5 | Anthropic · Closed | 78.3% | | |
| 13 | Qwen3.7 Max | Alibaba · Closed | 78.3% | | |
| 14 | Grok 4.5 | xAI · Closed | 78% | | |
| 15 | SWE-1.7 | Cognition · Closed | 77.8% | | |
| 16 | Claude Opus 4.5 | Anthropic · Closed | 77.5% | | |
| 17 | Kimi K2.6 | Moonshot AI · Open weight | 76.7% | | |
| 18 | MiniMax M2.7 | MiniMax · Open weight | 76.5% | | |
| 19 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | 76.2% | | |
| 20 | Qwen3.7 Plus | Alibaba · Closed | 75.8% | | |
| 21 | dots3-note Preview | Dots Studio · Open weight | 75.7% | | |
| 23 | Qwen3.6 Plus | Alibaba · Closed | 73.8% | | |
| 24 | Composer 2 | Cursor · Closed | 73.7% | | |
| 25 | GLM-5 | Z.AI · Open weight | 73.3% | | |
| 26 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | 73.3% | | |
| 27 | Kimi K2.5 | Moonshot AI · Open weight | 73% | | |
| 28 | Ling 3.0 Flash | InclusionAI · Open weight | 72.4% | | |
| 29 | Ornith-1.5-35B-A3B | Ornith AI · Open weight | 71.4% | | |
| 30 | Qwen3.6-27B | Alibaba · Open weight | 71.3% | | |
| 34 | Ornith-1.0-35B | DeepReinforce AI · Open weight | 69.3% | | |
| 35 | Nemotron 3 Ultra | NVIDIA · Open weight | 67.7% | | |
| 36 | Qwen3.6-35B-A3B | Alibaba · Open weight | 67.2% | | |
| 37 | Laguna M.1 | Poolside · Closed | 63.1% | | |
| 38 | Laguna XS 2.1 | Poolside · Open weight | 63.1% | | |
| 39 | LongCat-Flash-Lite-Sparse | Meituan · Open weight | 59.3% | | |
| 40 | Laguna XS.2 | Poolside · Open weight | 57.7% | | |
| 41 | Ornith-1.5-9B | Ornith AI · Open weight | 54.4% | | |
| 42 | Ornith-1.0-9B | DeepReinforce AI · Open weight | 52% | | |
| 43 | Granite 4.2 30B | IBM · Open weight | 41.9% | | |
| 44 | Nemotron 3.5 Lightning 30B A3B NVFP4 | NVIDIA · Open weight | 36.5% | | |
| 45 | Granite 4.2 8B | IBM · Open weight | 30.8% | | |
| 46 | LLaDA2.2-flash | InclusionAI · Open weight | 25% | | |