| 1 | Claude Fable 5.1 | Anthropic | Proprietary | 65% | |
| 2 | Claude Opus 5 | Anthropic | Proprietary | 64.7% | |
| 3 | Claude Mythos 5 | Anthropic | Proprietary | 64.5% | |
| 4 | Muse Spark 1.1 | Meta · Closed | 62.1% | | |
| 5 | GPT-5.4 Pro | OpenAI · Closed | 58.7% | | |
| 6 | Claude Opus 4.8 | Anthropic · Closed | 57.9% | | |
| 7 | Claude Sonnet 5 | Anthropic · Closed | 57.4% | | |
| 8 | GPT-5.5 Pro | OpenAI · Closed | 57.2% | | |
| 9 | Apodex 1.1 | Apodex · Closed | 56.1% | | |
| 10 | Kimi K3 | Moonshot AI · Closed | 56% | | |
| 11 | Hy4 preview | Tencent · Open weight | 55.4% | | |
| 12 | GLM-5.2 | Z.AI · Open weight | 54.7% | | |
| 13 | Claude Opus 4.7 (Adaptive) | Anthropic · Closed | 54.7% | | |
| 14 | Claude Opus 4.6 | Anthropic · Closed | 53% | | |
| 15 | dots3-note Preview | Dots Studio · Open weight | 52.6% | | |
| 16 | GLM-5.1 | Z.AI · Open weight | 52.3% | | |
| 17 | GPT-5.5 | OpenAI · Closed | 52.2% | | |
| 18 | GPT-5.4 | OpenAI · Closed | 52.1% | | |
| 19 | Muse Spark | Meta · Closed | 50.4% | | |
| 20 | GLM-5 | Z.AI · Open weight | 50.4% | | |
| 21 | Claude Sonnet 4.6 | Anthropic · Closed | 49% | | |
| 22 | MiMo-V2.5-Pro | Xiaomi · Closed | 48% | | |
| 23 | Inkling-Small | Thinking Machines Lab · Open weight | 47.8% | | |
| 24 | Agents-A1 | InternScience · Open weight | 47.6% | | |
| 25 | Step 5 Preview | StepFun · Closed | 46.5% | | |
| 26 | Inkling | Thinking Machines Lab · Open weight | 46% | | |
| 27 | Ornith-1.5-397B | Ornith AI · Open weight | 44.6% | | |
| 28 | Qwen3.8 Max | Alibaba · Open weight | 43.6% | | |
| 29 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | 42.7% | | |
| 30 | GPT-5.4 mini | OpenAI · Closed | 41.5% | | |
| 31 | Qwen3.7 Max | Alibaba · Closed | 41.4% | | |
| 32 | Gemini 3.5 Flash | Google · Closed | 40.2% | | |
| 33 | GPT-5.4 nano | OpenAI · Closed | 37.7% | | |
| 34 | DeepSeek V4.1 Flash | DeepSeek · Open weight | 36.8% | | |
| 35 | Qwen3.8-Omni-Flash | Alibaba · Closed | 36.5% | | |
| 36 | Qwen3.8-Flash-Next | Alibaba · Open weight | 35.9% | | |
| 37 | Grok 4.3 | xAI · Closed | 35% | | |
| 38 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | 34.8% | | |
| 39 | Qwen3.7 Plus | Alibaba · Closed | 34.7% | | |
| 40 | Kimi K2.6 | Moonshot AI · Open weight | 34.7% | | |
| 42 | Claude Opus 4.5 | Anthropic · Closed | 30.8% | | |
| 43 | Qwen3.8-27B | Alibaba · Open weight | 30.8% | | |
| 44 | Kimi K2.5 | Moonshot AI · Open weight | 30.1% | | |
| 46 | Qwen3.6 Plus | Alibaba · Closed | 28.8% | | |
| 47 | Qwen3.5 397B | Alibaba · Open weight | 28.7% | | |
| 48 | A.X K2 | SK Telecom · Open weight | 27.8% | | |
| 49 | Nemotron 3 Ultra | NVIDIA · Open weight | 26.7% | | |
| 50 | Gemma 4 31B | Google · Open weight | 26.5% | | |
| 51 | Ornith-1.5-35B-A3B | Ornith AI · Open weight | 25.6% | | |
| 52 | Hy3 Preview | Tencent · Open weight | 25.5% | | |
| 53 | GLM-4.7 | Z.AI · Open weight | 24.8% | | |
| 54 | Qwen3.6-27B | Alibaba · Open weight | 24% | | |
| 55 | Ling 3.0 Flash | InclusionAI · Open weight | 22.7% | | |
| 56 | Qwen3.6-35B-A3B | Alibaba · Open weight | 21.4% | | |
| 57 | Ornith-1.5-9B | Ornith AI · Open weight | 20.2% | | |
| 58 | Gemini 2.5 Pro | Google · Closed | 18.8% | | |
| 59 | K-EXAONE 2.0 | LG AI Research · Open weight | 18.3% | | |
| 60 | Gemma 4 26B A4B | Google · Open weight | 17.2% | | |
| 61 | MiniCPM5-2B | OpenBMB · Open weight | 8.9% | | |