| 1 | Anthropic | anthropic/claude-opus-5 | Claude Opus 5 | 90.98% | |
| 2 | Meta | meta/muse_spark_1_1 | Muse Spark 1.1 | 88.89% | |
| 3 | Anthropic | anthropic/claude-fable-5 | Claude Fable 5 | 88.52% | |
| 4 | GPT-5.1 | OpenAI | 88.09% | | |
| 5 | Kimi K3 | Moonshot AI | 87.96% | | |
| 6 | MiniMax M3 | MiniMax | 87.25% | | |
| 7 | Grok 4.5 | xAI | 86.88% | | |
| 8 | GPT-5.5 | OpenAI | 86.87% | | |
| 9 | Claude Opus 4.6 | Anthropic | 86.74% | | |
| 10 | Claude Opus 4.6 Thinking | Anthropic | 86.13% | | |
| 11 | Muse Spark | Meta | 85.90% | | |
| 12 | Claude Opus 4.8 | Anthropic | 85.75% | | |
| 13 | Inkling | Thinkingmachines | 85.41% | | |
| 14 | Claude Opus 4.5 20251101 Thinking | Anthropic | 85.32% | | |
| 15 | GPT-5.6 Sol | OpenAI | 85.23% | | |
| 16 | Claude Haiku 4.5 20251001 Thinking | Anthropic | 85.23% | | |
| 17 | Claude Sonnet 4.5 | Anthropic | 84.52% | | |
| 18 | GPT-5.6 Luna | OpenAI | 84.39% | | |
| 19 | GPT-5.2 | OpenAI | 84.39% | | |
| 20 | Claude Sonnet 4.5 20250929 Thinking | Anthropic | 84.10% | | |
| 21 | Mimo V2.5 Pro | Xiaomi | 83.73% | | |
| 22 | GPT-5 | OpenAI | 83.65% | | |
| 23 | GLM 5.2 | Zhipu AI | 83.53% | | |
| 24 | Claude Opus 4.5 | Anthropic | 83.25% | | |
| 25 | Gemini 2.5 Flash Thinking | Google | 82.98% | | |
| 26 | Claude Opus 4.7 | Anthropic | 82.95% | | |
| 27 | Gemini 2.5 Flash | Google | 82.87% | | |
| 28 | GPT-5.6 Terra | OpenAI | 82.87% | | |
| 29 | Grok 4 Fast Reasoning | xAI | 81.63% | | |
| 30 | MiniMax M2.1 | MiniMax | 80.78% | | |
| 31 | GPT-5 Mini | OpenAI | 80.58% | | |
| 32 | MiniMax M2.7 | MiniMax | 79.87% | | |
| 33 | Grok 4 Fast Non Reasoning | xAI | 79.72% | | |
| 34 | Gemini 3.6 Flash | Google | 79.66% | | |
| 35 | Qwen3.7 Max | Alibaba | 79.40% | | |
| 36 | Grok 4.1 Fast Reasoning | xAI | 78.73% | | |
| 37 | Gemini 2.5 Flash Preview 09 2025 Thinking | Google | 78.50% | | |
| 38 | Grok 4 0709 | xAI | 78.15% | | |
| 39 | Kimi K2.6 | Moonshot AI | 78.15% | | |
| 40 | Gemini 2.5 Flash Preview 09 2025 | Google | 77.95% | | |
| 41 | GPT-5.4 | OpenAI | 77.55% | | |
| 42 | Grok 4.1 Fast Non Reasoning | xAI | 77.46% | | |
| 43 | Qwen3 VL Plus | Alibaba | 77.13% | | |
| 44 | GPT-5.4 Nano | OpenAI | 77.09% | | |
| 45 | Qwen3.6 Plus | Alibaba | 76.96% | | |
| 46 | O3 | OpenAI | 76.65% | | |
| 47 | Gemini 3.5 Flash | Google | 76.57% | | |
| 48 | Kimi K2.5 Thinking | Moonshot AI | 76.44% | | |
| 49 | Gemini 3.1 Pro Preview | Google | 76.11% | | |
| 50 | Claude Sonnet 5 | Anthropic | 76.05% | | |
| 51 | Gemini 2.5 Flash Lite Preview 09 2025 | Google | 75.82% | | |
| 52 | DeepSeek V4 Pro | DeepSeek | 75.14% | | |
| 53 | Grok 4.3 | xAI | 74.40% | | |
| 54 | Claude Opus 4.1 20250805 Thinking | Anthropic | 73.90% | | |
| 55 | Gemini 2.5 Pro | Google | 73.55% | | |
| 56 | GPT-5 Nano | OpenAI | 72.86% | | |
| 57 | Gemini 2.5 Flash Lite | Google | 72.83% | | |
| 58 | Qwen3 Max | Alibaba | 72.71% | | |
| 59 | Claude Sonnet 4 | Anthropic | 72.41% | | |
| 60 | GLM 5.1 | Zhipu AI | 72.27% | | |
| 61 | Mimo V2.5 | Xiaomi | 72.15% | | |
| 62 | Gemini 3 Pro Preview | Google | 72.04% | | |
| 63 | Claude Opus 4.1 | Anthropic | 71.75% | | |
| 64 | Gemini 3.5 Flash Lite | Google | 70.89% | | |
| 65 | Qwen3.5 Flash | Alibaba | 70.62% | | |
| 66 | Gemini 3 Flash Preview | Google | 69.92% | | |
| 67 | Claude Sonnet 4 20250514 Thinking | Anthropic | 69.35% | | |
| 68 | O4 Mini | OpenAI | 69.14% | | |
| 69 | GLM 4.7 | Zhipu AI | 68.63% | | |
| 70 | Mistral Medium 3.5 | Mistral AI | 67.73% | | |
| 71 | Gemini 2.5 Flash Lite Preview 09 2025 Thinking | Google | 66.88% | | |
| 72 | Gemini 3.1 Flash Lite Preview | Google | 63.90% | | |
| 73 | Grok 4.20 0309 Reasoning | xAI | 63.41% | | |
| 74 | Llama4 Maverick Instruct Basic | Fireworks AI | 54.22% | | |
| 75 | Meta Llama Llama 4 Scout 17B 16E Instruct | Together AI | 50.59% | | |