| 1 | Anthropic | anthropic/claude-opus-5 | Claude Opus 5 | 78.00% | |
| 2 | OpenAI | openai/gpt-5.6-sol | GPT-5.6 Sol | 77.00% | |
| 3 | Anthropic | anthropic/claude-fable-5 | Claude Fable 5 | 77.00% | |
| 4 | GPT-5.6 Terra | OpenAI | 71.00% | | |
| 5 | Aristotle | Harmonic | 71.00% | | |
| 6 | Kimi K3 | Moonshot AI | 70.00% | | |
| 7 | Claude Opus 4.8 | Anthropic | 69.00% | | |
| 8 | Claude Sonnet 5 | Anthropic | 66.00% | | |
| 9 | GPT-5.4 | OpenAI | 56.00% | | |
| 10 | GPT-5.6 Luna | OpenAI | 54.00% | | |
| 11 | Claude Opus 4.7 | Anthropic | 54.00% | | |
| 12 | GPT-5.5 | OpenAI | 50.00% | | |
| 13 | Claude Opus 4.6 Thinking | Anthropic | 50.00% | | |
| 14 | Claude Sonnet 4.6 | Anthropic | 45.00% | | |
| 15 | Muse Spark 1.1 | Meta | 39.00% | | |
| 16 | Gemini 3.6 Flash | Google | 36.00% | | |
| 17 | Claude Opus 4.5 20251101 Thinking | Anthropic | 36.00% | | |
| 18 | GLM 5.2 | Zhipu AI | 35.00% | | |
| 19 | Grok 4.5 | xAI | 30.00% | | |
| 20 | Gemini 3.5 Flash | Google | 29.00% | | |
| 21 | Qwen3.7 Max | Alibaba | 26.00% | | |
| 22 | Gemini 3.1 Pro Preview | Google | 26.00% | | |
| 23 | Mimo V2.5 Pro | Xiaomi | 24.00% | | |
| 24 | GLM 5.1 | Zhipu AI | 22.22% | | |
| 25 | GPT-5.4 Mini | OpenAI | 21.00% | | |
| 26 | Gemini 3 Pro Preview | Google | 20.00% | | |
| 27 | MiniMax M3 | MiniMax | 19.00% | | |
| 28 | Claude Sonnet 4.5 20250929 Thinking | Anthropic | 19.00% | | |
| 29 | GPT-5 | OpenAI | 18.00% | | |
| 30 | Muse Spark | Meta | 17.00% | | |
| 31 | Kimi K2.6 | Moonshot AI | 16.00% | | |
| 32 | Mimo V2.5 | Xiaomi | 16.00% | | |
| 33 | Gemini 3 Flash Preview | Google | 15.00% | | |
| 34 | GPT-5.2 | OpenAI | 15.00% | | |
| 35 | Grok 4.20 0309 Reasoning | xAI | 14.00% | | |
| 36 | Gemini 3.5 Flash Lite | Google | 13.00% | | |
| 37 | GPT-5 Nano | OpenAI | 12.00% | | |
| 38 | Grok 4.3 | xAI | 11.00% | | |
| 39 | Mistral Medium 3.5 | Mistral AI | 10.00% | | |
| 40 | DeepSeek V4 Pro | DeepSeek | 10.00% | | |
| 41 | GPT-5.1 Codex Max | OpenAI | 9.00% | | |
| 42 | GPT-5 Mini | OpenAI | 9.00% | | |
| 43 | Qwen3.6 27b | Alibaba | 8.00% | | |
| 44 | DeepSeek V3p2 | Fireworks AI | 8.00% | | |
| 45 | GLM 4.7 | Zhipu AI | 6.00% | | |
| 46 | GPT-5.4 Nano | OpenAI | 5.00% | | |
| 47 | Grok 4.1 Fast Reasoning | xAI | 4.00% | | |
| 48 | DeepSeek V3p2 Thinking | Fireworks AI | 4.00% | | |
| 49 | MiniMax M2.5 | MiniMax | 4.00% | | |
| 50 | MiniMax M2.7 | MiniMax | 3.00% | | |
| 51 | Inkling | Thinkingmachines | 2.00% | | |
| 52 | Nemotron 3 Ultra 550b A55b | Nvidia | 2.00% | | |
| 53 | Laguna Xs.2 | Poolside | 0.00% | | |
| 54 | Laguna M.1 | Poolside | 0.00% | | |