| 1 | Anthropic | 93.5% | anthropic/claude-opus-4.8-fast | Overall | |
| 2 | Qwen3.7 Max | Alibaba | Closed | qwen/qwen3.7-max | |
| 5 | MiMo-V2.5 | Xiaomi · Closed | 89.7% | | |
| 6 | Grok Build 0.1 | xAI · Closed | 88.9% | | |
| 7 | GPT-5.6 Luna | OpenAI · Closed | 88.7% | | |
| 9 | MiMo-V2.5-Pro | Xiaomi · Closed | 87.5% | | |
| 10 | GLM-5.2 | Z.AI · Open weight | 87.0% | | |
| 11 | GPT-5.6 Sol | OpenAI · Closed | 84.2% | | |
| 13 | DeepSeek V4 Flash | DeepSeek · Open weight | 81.7% | | |
| 14 | Gemini 3.1 Pro | Google · Closed | 81.0% | | |
| 15 | Gemini 3.1 Flash-Lite | Google · Closed | 80.5% | | |
| 16 | Grok 4.20 | xAI · Closed | 80.3% | | |
| 17 | Step 3.5 Flash | StepFun · Open weight | 79.4% | | |
| 18 | GPT-5.4 mini | OpenAI · Closed | 79.2% | | |
| 19 | Kimi K2.7 Code | Moonshot AI · Open weight | 76.1% | | |
| 20 | Claude Opus 4.7 | Anthropic · Closed | 76.0% | | |
| 21 | GPT-5.6 Terra | OpenAI · Closed | 75.9% | | |
| 22 | GPT-5.4 | OpenAI · Closed | 75.7% | | |
| 23 | GPT-5.5 | OpenAI · Closed | 75.5% | | |
| 24 | Grok 4.5 | xAI · Closed | 75.2% | | |
| 25 | Seed-2.0-Lite | ByteDance · Closed | 75.0% | | |
| 26 | Gemini 3.5 Flash | Google · Closed | 74.2% | | |
| 27 | Grok 4.3 | xAI · Closed | 73.7% | | |
| 28 | Qwen3.6 Plus | Alibaba · Closed | 72.5% | | |
| 29 | Gemini 3 Flash | Google · Closed | 72.1% | | |
| 30 | GLM-5-Turbo | Z.AI · Closed | 71.8% | | |
| 31 | Claude Opus 4.6 | Anthropic · Closed | 69.9% | | |
| 34 | GPT-5.4 nano | OpenAI · Closed | 69.0% | | |
| 35 | Claude Haiku 4.5 | Anthropic · Closed | 67.7% | | |
| 36 | GLM-5V-Turbo | Z.AI · Closed | 67.6% | | |
| 37 | MiniMax M2.7 | MiniMax · Open weight | 66.8% | | |
| 38 | Trinity-Large-Preview | Arcee AI · Open weight | 65.7% | | |
| 40 | Claude Sonnet 4.6 | Anthropic · Closed | 62.7% | | |
| 42 | DeepSeek V4 Pro | DeepSeek · Open weight | 61.1% | | |
| 43 | GLM-5.1 | Z.AI · Open weight | 59.9% | | |
| 45 | Claude Fable 5 | Anthropic · Closed | 54.8% | | |
| 46 | Kimi K2.5 | Moonshot AI · Open weight | 54.6% | | |
| 51 | GPT-OSS 120B | OpenAI · Open weight | 44.8% | | |
| 52 | Nemotron 3 Super 120B A12B | NVIDIA · Open weight | 42.2% | | |
| 53 | Mercury 2 | Inception · Closed | 39.6% | | |
| 55 | GPT-OSS 20B | OpenAI · Open weight | 36.3% | | |
| 56 | GPT-5.5 Pro | OpenAI · Closed | 21.4% | | |
| 58 | Llama 4 Scout | Meta · Open weight | 3.2% | | |