| 1 | Atria Dawn Preview | Shanghai Artificial Intelligence Laboratory | Open weights | 92.5% | |
| 2 | GPT-5.6 Sol | OpenAI | Proprietary | 92.2% | |
| 3 | GPT-6 Astra | OpenAI | Proprietary | 91.5% | |
| 4 | Kimi K3 | Moonshot AI · Closed | 91.2% | | |
| 5 | Claude Opus 5 | Anthropic · Closed | 90.8% | | |
| 6 | GPT-5.5 Pro | OpenAI · Closed | 90.1% | | |
| 7 | GPT-5.4 Pro | OpenAI · Closed | 89.3% | | |
| 8 | Step 5 Preview | StepFun · Closed | 88.7% | | |
| 9 | Claude Mythos 5 | Anthropic · Closed | 88% | | |
| 10 | GPT-5.6 Terra | OpenAI · Closed | 87.5% | | |
| 11 | Ornith-1.5-397B | Ornith AI · Open weight | 86.6% | | |
| 12 | Claude Sonnet 5 | Anthropic · Closed | 84.7% | | |
| 13 | GPT-5.5 | OpenAI · Closed | 84.4% | | |
| 14 | Claude Opus 4.8 | Anthropic · Closed | 84.3% | | |
| 15 | Claude Opus 4.6 | Anthropic · Closed | 83.7% | | |
| 16 | MiniMax M3 | MiniMax · Open weight | 83.5% | | |
| 17 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | 83.4% | | |
| 18 | GPT-5.6 Luna | OpenAI · Closed | 83.3% | | |
| 19 | dots3-note Preview | Dots Studio · Open weight | 83.3% | | |
| 20 | Kimi K2.6 | Moonshot AI · Open weight | 83.2% | | |
| 21 | GPT-5.4 | OpenAI · Closed | 82.7% | | |
| 23 | Claude Opus 4.7 (Adaptive) | Anthropic · Closed | 79.3% | | |
| 24 | Inkling-Small | Thinking Machines Lab · Open weight | 77.4% | | |
| 25 | Inkling | Thinking Machines Lab · Open weight | 77.1% | | |
| 26 | Step 3.7 Flash | StepFun · Open weight | 75.8% | | |
| 27 | Agents-A1 | InternScience · Open weight | 75.5% | | |
| 28 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | 73.2% | | |
| 29 | Ling 3.0 Flash | InclusionAI · Open weight | 72.2% | | |
| 30 | GLM-5.1 | Z.AI · Open weight | 68% | | |
| 31 | Ornith-1.5-35B-A3B | Ornith AI · Open weight | 67.6% | | |
| 32 | Agents-A1-4B | InternScience · Open weight | 66.8% | | |
| 33 | GPT-5.2 | OpenAI · Closed | 65.8% | | |
| 34 | Qwen3.5-122B-A10B | Alibaba · Open weight | 63.8% | | |
| 35 | Qwen3.5 397B | Alibaba · Open weight | 62% | | |
| 36 | Qwen3.5-27B | Alibaba · Open weight | 61% | | |
| 37 | Qwen3.5-35B-A3B | Alibaba · Open weight | 61% | | |
| 38 | Kimi K2.5 | Moonshot AI · Open weight | 60.6% | | |
| 39 | Kimi K2.5 (Reasoning) | Moonshot AI · Closed | 60.6% | | |
| 40 | Ornith-1.5-9B | Ornith AI · Open weight | 56.4% | | |
| 42 | GLM-4.7 | Z.AI · Open weight | 52% | | |
| 43 | Solar Pro 4 | Upstage · Closed | 49.2% | | |
| 44 | LongCat-Flash-Lite-Sparse | Meituan · Open weight | 48.6% | | |
| 45 | Nemotron 3 Ultra | NVIDIA · Open weight | 44.4% | | |
| 46 | Nemotron 3.5 Lightning 30B A3B NVFP4 | NVIDIA · Open weight | 36.8% | | |