| 1 | Claude Opus 5 | Anthropic | Proprietary | 63.57% | |
| 2 | Google | 59.06% | Gemini 3.1 Pro Preview | | |
| 3 | Claude Fable 5 | Anthropic | Proprietary | 56.07% | |
| 4 | Gemini 3 Flash Preview | Google | 55.92% | | |
| 5 | Gemini 3.5 Flash | Google · Closed | 55.83% | | |
| 6 | Claude Opus 4.7 | Anthropic · Closed | 54.86% | | |
| 7 | Claude Fable 5.1 | Anthropic · Closed | 53.51% | | |
| 8 | Gemini 3.7 Flash | Google · Closed | 53.39% | | |
| 9 | Claude Opus 4.8 | Anthropic · Closed | 53.22% | | |
| 10 | Gemini 3.6 Flash | Google · Closed | 53.15% | | |
| 11 | GPT-5.1 | OpenAI · Closed | 52.73% | | |
| 12 | Gemini 3 Pro Preview | Google | 52.20% | | |
| 13 | Muse Spark | Meta · Closed | 51.31% | | |
| 14 | Gemini 2.5 Pro | Google · Closed | 50.59% | | |
| 15 | Claude Opus 5.5 | Anthropic · Closed | 49.80% | | |
| 16 | GPT-5.2 | OpenAI · Closed | 49.75% | | |
| 17 | GPT-5 | OpenAI | 49.63% | | |
| 18 | Grok 4.7 | xAI · Closed | 49.55% | | |
| 19 | Muse Spark 1.2 | Meta · Closed | 49.35% | | |
| 20 | Claude Opus 4.5 Thinking | Anthropic · Closed | 49.16% | | |
| 21 | Claude Opus 4.6 (Adaptive) | Anthropic · Closed | 49.13% | | |
| 22 | GPT-5.5 | OpenAI · Closed | 49.10% | | |
| 23 | Kimi K3 | Moonshot AI · Closed | 48.88% | | |
| 24 | GPT-6 Astra | OpenAI · Closed | 48.49% | | |
| 25 | Claude Opus 4.6 | Anthropic · Closed | 48.24% | | |
| 26 | Gemini 3.8 Flash | Google · Closed | 48.13% | | |
| 27 | Gemini 3.1 Flash Lite Preview | Google | 47.60% | | |
| 28 | Claude Sonnet 5 | Anthropic · Closed | 47.54% | | |
| 29 | o3 | OpenAI · Closed | 47.29% | | |
| 30 | Claude Opus 4.1 20250805 Thinking | Anthropic | 47.23% | | |
| 31 | MiniMax M3 | MiniMax · Open weight | 46.29% | | |
| 32 | Claude Opus 4.5 | Anthropic · Closed | 45.17% | | |
| 33 | Grok 4.6 | xAI · Closed | 44.71% | | |
| 34 | Claude Sonnet 4.5 Thinking | Anthropic · Closed | 44.13% | | |
| 35 | GPT-5.6 Sol | OpenAI · Closed | 43.97% | | |
| 36 | Gemini 3.5 Flash-Lite | Google · Closed | 43.49% | | |
| 37 | GPT-5.6 Terra | OpenAI · Closed | 43.41% | | |
| 38 | Grok 4.5 | xAI · Closed | 43.29% | | |
| 39 | Hy4 preview | Tencent · Open weight | 43.25% | | |
| 40 | GPT-5 mini | OpenAI · Closed | 43.05% | | |
| 41 | GLM-5.3 | Z.AI · Open weight | 42.86% | | |
| 42 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | 42.47% | | |
| 43 | GPT-5.6 Luna | OpenAI · Closed | 42.39% | | |
| 44 | GLM-5.1 | Z.AI · Open weight | 41.60% | | |
| 45 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | 41.41% | | |
| 46 | Claude Opus 4.1 | Anthropic | 41.37% | | |
| 47 | GPT-5.4 | OpenAI · Closed | 41.29% | | |
| 48 | Inkling | Thinking Machines Lab · Open weight | 41.19% | | |
| 49 | DeepSeek V4.1 Flash | DeepSeek · Open weight | 41.17% | | |
| 50 | GPT-5.4 nano | OpenAI · Closed | 41.03% | | |
| 51 | GLM-5.2 | Z.AI · Open weight | 40.77% | | |
| 52 | Qwen3.8 Max | Alibaba · Open weight | 40.67% | | |
| 53 | Claude Sonnet 4.5 | Anthropic · Closed | 40.57% | | |
| 54 | Gemini 2.5 Flash Preview 09 2025 | Google | 40.54% | | |
| 56 | Gemini 2.5 Flash Thinking | Google | 40.36% | | |
| 57 | Gemini 2.5 Flash Preview 09 2025 Thinking | Google | 40.33% | | |
| 58 | Kimi K2.6 | Moonshot AI · Open weight | 40.14% | | |
| 59 | Kimi K2.5 Thinking | Moonshot AI | 39.32% | | |
| 60 | Qwen3.7 Max | Alibaba · Closed | 38.75% | | |
| 61 | Nemotron 3 Ultra 550b A55b | nvidia | 38.62% | | |
| 62 | Gemini 2.5 Flash | Google · Closed | 38.42% | | |
| 63 | Grok 4 0709 | xAI | 38.08% | | |
| 64 | Grok 4.3 | xAI · Closed | 38.07% | | |
| 65 | Inkling-Small | Thinking Machines Lab · Open weight | 37.89% | | |
| 66 | Grok 4 Fast (Reasoning) | xAI · Closed | 37.38% | | |
| 67 | Qwen3.6 Plus | Alibaba · Closed | 36.89% | | |
| 68 | Llama4 Maverick Instruct Basic | Fireworks | 36.51% | | |
| 69 | Claude Sonnet 4 20250514 Thinking | Anthropic | 34.96% | | |
| 70 | MiniMax M2.7 | MiniMax · Open weight | 34.44% | | |
| 71 | Gemini 2.5 Flash Lite Preview 09 2025 Thinking | Google | 34.19% | | |
| 72 | MiniMax M2.1 | MiniMax | 34.08% | | |
| 73 | Claude Sonnet 4 | Anthropic | 33.94% | | |
| 74 | O4 Mini | OpenAI | 33.79% | | |
| 75 | Mistral Medium 3.5 | Mistral | 33.75% | | |
| 76 | Qwen3.5 Flash | Alibaba · Closed | 33.00% | | |
| 77 | GLM-4.7 | Z.AI · Open weight | 32.77% | | |
| 78 | Claude Haiku 4.5 Thinking | Anthropic · Closed | 32.68% | | |
| 79 | MiMo-V2.5-Pro | Xiaomi · Closed | 32.48% | | |
| 80 | Ling 3.0 Flash 2607 | ant | 32.27% | | |
| 81 | Grok 4.20 0309 Reasoning | xAI | 32.16% | | |
| 82 | MiMo-V2.5 | Xiaomi · Closed | 31.89% | | |
| 83 | Qwen3 VL Plus | Alibaba | 31.65% | | |
| 84 | Qwen3 Max | Alibaba · Closed | 31.37% | | |
| 85 | Mercury 2.5 | Inception · Closed | 31.33% | | |
| 86 | GPT-5 nano | OpenAI · Closed | 30.44% | | |
| 87 | Grok 4 Fast Non Reasoning | xAI | 30.04% | | |
| 88 | Qwen3.8-27B | Alibaba · Open weight | 28.70% | | |
| 89 | Grok 4.1 Fast Non Reasoning | xAI | 28.35% | | |
| 90 | Grok 4.1 Fast (Reasoning) | xAI · Closed | 28.08% | | |
| 91 | Gemini 2.5 Flash Lite | Google | 27.11% | | |
| 92 | Gemini 2.5 Flash Lite Preview 09 2025 | Google | 27.08% | | |
| 93 | Meta Llama Llama 4 Scout 17B 16E Instruct | Together AI | 23.31% | | |
| 94 | Laguna M.1 | Poolside · Closed | 23.11% | | |
| 95 | Laguna XS.2 | Poolside · Open weight | 21.25% | | |