| 1 | Anthropic | anthropic/claude-opus-5 | Claude Opus 5 | 63.57% | |
| 2 | Google | google/gemini-3.1-pro-preview | Gemini 3.1 Pro Preview | 59.06% | |
| 3 | Anthropic | anthropic/claude-fable-5 | Claude Fable 5 | 56.07% | |
| 4 | Gemini 3 Flash Preview | Google | 55.92% | | |
| 5 | Gemini 3.5 Flash | Google | 55.83% | | |
| 6 | Claude Opus 4.7 | Anthropic | 54.86% | | |
| 7 | Claude Opus 4.8 | Anthropic | 53.22% | | |
| 8 | Gemini 3.6 Flash | Google | 53.15% | | |
| 9 | GPT-5.1 | OpenAI | 52.73% | | |
| 10 | Gemini 3 Pro Preview | Google | 52.20% | | |
| 11 | Muse Spark | Meta | 51.31% | | |
| 12 | Gemini 2.5 Pro | Google | 50.59% | | |
| 13 | GPT-5.2 | OpenAI | 49.75% | | |
| 14 | GPT-5 | OpenAI | 49.63% | | |
| 15 | Claude Opus 4.5 20251101 Thinking | Anthropic | 49.16% | | |
| 16 | Claude Opus 4.6 Thinking | Anthropic | 49.13% | | |
| 17 | GPT-5.5 | OpenAI | 49.10% | | |
| 18 | Kimi K3 | Moonshot AI | 48.88% | | |
| 19 | Claude Opus 4.6 | Anthropic | 48.24% | | |
| 20 | Gemini 3.1 Flash Lite Preview | Google | 47.60% | | |
| 21 | O3 | OpenAI | 47.29% | | |
| 22 | Claude Opus 4.1 20250805 Thinking | Anthropic | 47.23% | | |
| 23 | MiniMax M3 | MiniMax | 46.29% | | |
| 24 | Claude Opus 4.5 | Anthropic | 45.17% | | |
| 25 | Claude Sonnet 4.5 20250929 Thinking | Anthropic | 44.13% | | |
| 26 | GPT-5.6 Sol | OpenAI | 43.97% | | |
| 27 | Gemini 3.5 Flash Lite | Google | 43.49% | | |
| 28 | GPT-5.6 Terra | OpenAI | 43.41% | | |
| 29 | Grok 4.5 | xAI | 43.29% | | |
| 30 | GPT-5 Mini | OpenAI | 43.05% | | |
| 31 | GPT-5.6 Luna | OpenAI | 42.39% | | |
| 32 | GLM 5.1 | Zhipu AI | 41.60% | | |
| 33 | Claude Opus 4.1 | Anthropic | 41.37% | | |
| 34 | GPT-5.4 | OpenAI | 41.29% | | |
| 35 | Inkling | Thinkingmachines | 41.19% | | |
| 36 | GPT-5.4 Nano | OpenAI | 41.03% | | |
| 37 | GLM 5.2 | Zhipu AI | 40.77% | | |
| 38 | Claude Sonnet 4.5 | Anthropic | 40.57% | | |
| 39 | Gemini 2.5 Flash Preview 09 2025 | Google | 40.54% | | |
| 40 | DeepSeek V4 Pro | DeepSeek | 40.45% | | |
| 41 | Gemini 2.5 Flash Thinking | Google | 40.36% | | |
| 42 | Gemini 2.5 Flash Preview 09 2025 Thinking | Google | 40.33% | | |
| 43 | Kimi K2.6 | Moonshot AI | 40.14% | | |
| 44 | Kimi K2.5 Thinking | Moonshot AI | 39.32% | | |
| 45 | Qwen3.7 Max | Alibaba | 38.75% | | |
| 46 | Nemotron 3 Ultra 550b A55b | Nvidia | 38.62% | | |
| 47 | Gemini 2.5 Flash | Google | 38.42% | | |
| 48 | Grok 4 0709 | xAI | 38.08% | | |
| 49 | Grok 4.3 | xAI | 38.07% | | |
| 50 | Grok 4 Fast Reasoning | xAI | 37.38% | | |
| 51 | Qwen3.6 Plus | Alibaba | 36.89% | | |
| 52 | Llama4 Maverick Instruct Basic | Fireworks AI | 36.51% | | |
| 53 | Claude Sonnet 4 20250514 Thinking | Anthropic | 34.96% | | |
| 54 | MiniMax M2.7 | MiniMax | 34.44% | | |
| 55 | Gemini 2.5 Flash Lite Preview 09 2025 Thinking | Google | 34.19% | | |
| 56 | MiniMax M2.1 | MiniMax | 34.08% | | |
| 57 | Claude Sonnet 4 | Anthropic | 33.94% | | |
| 58 | O4 Mini | OpenAI | 33.79% | | |
| 59 | Mistral Medium 3.5 | Mistral AI | 33.75% | | |
| 60 | Qwen3.5 Flash | Alibaba | 33.00% | | |
| 61 | GLM 4.7 | Zhipu AI | 32.77% | | |
| 62 | Claude Haiku 4.5 20251001 Thinking | Anthropic | 32.68% | | |
| 63 | Mimo V2.5 Pro | Xiaomi | 32.48% | | |
| 64 | Grok 4.20 0309 Reasoning | xAI | 32.16% | | |
| 65 | Mimo V2.5 | Xiaomi | 31.89% | | |
| 66 | Qwen3 VL Plus | Alibaba | 31.65% | | |
| 67 | Qwen3 Max | Alibaba | 31.37% | | |
| 68 | GPT-5 Nano | OpenAI | 30.44% | | |
| 69 | Grok 4 Fast Non Reasoning | xAI | 30.04% | | |
| 70 | Grok 4.1 Fast Non Reasoning | xAI | 28.35% | | |
| 71 | Grok 4.1 Fast Reasoning | xAI | 28.08% | | |
| 72 | Gemini 2.5 Flash Lite | Google | 27.11% | | |
| 73 | Gemini 2.5 Flash Lite Preview 09 2025 | Google | 27.08% | | |
| 74 | Laguna M.1 | Poolside | 25.24% | | |
| 75 | Meta Llama Llama 4 Scout 17B 16E Instruct | Together AI | 23.31% | | |
| 76 | Laguna Xs.2 | Poolside | 20.70% | | |