| 1 | Muse Spark 1.1 | Meta | Proprietary | 88.1% | |
| 2 | Claude Opus 5 | Anthropic | Proprietary | 85.8% | |
| 3 | Step 5 Preview | StepFun | Proprietary | 85.6% | |
| 4 | Kimi K3 | Moonshot AI · Closed | 84.2% | | |
| 5 | Hy4 preview | Tencent · Open weight | 83.7% | | |
| 6 | Gemini 3.5 Flash | Google · Closed | 83.6% | | |
| 7 | Claude Opus 4.8 | Anthropic · Closed | 82.2% | | |
| 8 | Ornith-1.5-397B | Ornith AI · Open weight | 80% | | |
| 9 | Inkling-Small | Thinking Machines Lab · Open weight | 79.6% | | |
| 10 | Claude Opus 4.7 (Adaptive) | Anthropic · Closed | 77.3% | | |
| 11 | GLM-5.2 | Z.AI · Open weight | 76.8% | | |
| 12 | Qwen3.7 Max | Alibaba · Closed | 76.4% | | |
| 13 | Kimi K2.7 Code | Moonshot AI · Open weight | 76% | | |
| 14 | Muse Glimmer 30B | Meta · Open weight | 75.5% | | |
| 15 | GPT-5.5 | OpenAI · Closed | 75.3% | | |
| 16 | MiniMax M3 | MiniMax · Open weight | 74.2% | | |
| 18 | Inkling | Thinking Machines Lab · Open weight | 74.1% | | |
| 19 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | 73.6% | | |
| 20 | Qwen3.7 Plus | Alibaba · Closed | 73.2% | | |
| 21 | GLM-5.1 | Z.AI · Open weight | 71.8% | | |
| 22 | GPT-5.4 | OpenAI · Closed | 70.6% | | |
| 23 | Ornith-1.5-35B-A3B | Ornith AI · Open weight | 70.2% | | |
| 25 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | 69% | | |
| 27 | Ling 3.0 Flash | InclusionAI · Open weight | 65.5% | | |
| 29 | Qwen3.6-35B-A3B | Alibaba · Open weight | 62.8% | | |
| 30 | Solar Pro 4 | Upstage · Closed | 61.4% | | |
| 31 | Solar Open 2 | Upstage · Open weight | 58.2% | | |
| 32 | GPT-5.4 mini | OpenAI · Closed | 57.7% | | |
| 33 | GPT-5.4 nano | OpenAI · Closed | 56.1% | | |
| 34 | Kimi K2.6 | Moonshot AI · Open weight | 55.9% | | |
| 35 | Ornith-1.5-9B | Ornith AI · Open weight | 54.2% | | |
| 36 | Qwen3.6 Plus | Alibaba · Closed | 48.2% | | |
| 37 | LLaDA2.2-flash | InclusionAI · Open weight | 46.2% | | |
| 38 | Qwen3.5 397B | Alibaba · Open weight | 46.1% | | |
| 39 | LongCat-Flash-Lite-Sparse | Meituan · Open weight | 45.6% | | |
| 40 | Claude Opus 4.5 | Anthropic · Closed | 42.3% | | |
| 41 | GLM-5 | Z.AI · Open weight | 31.1% | | |
| 42 | Kimi K2.5 | Moonshot AI · Open weight | 29.5% | | |