| 1 | Claude Fable 5.1 | Anthropic | Proprietary | 68.83% | |
| 2 | Claude Opus 5 | Anthropic | Proprietary | 67.21% | |
| 3 | GPT-6 Astra | OpenAI | Proprietary | max reasoning | |
| 4 | Claude Opus 5.5 | Anthropic · Closed | 66.16% | | |
| 5 | Claude Fable 5 | Anthropic · Closed | 66.04% | | |
| 6 | Muse Spark 1.3 Max | Meta | max reasoning | 64.53% | |
| 7 | GPT-5.6 Sol | OpenAI · Closed | max reasoning | 63.71% | |
| 8 | Gemini 3.8 Flash | Google · Closed | high reasoning | 62.25% | |
| 9 | Claude Opus 4.8 | Anthropic · Closed | 60.91% | | |
| 10 | Muse Spark 1.3 | Meta · Closed | xhigh reasoning | 60.31% | |
| 11 | Grok 4.7 | xAI · Closed | xhigh reasoning | 60.20% | |
| 12 | GPT-5.6 Luna | OpenAI · Closed | max reasoning | 59.88% | |
| 13 | Claude Sonnet 5 | Anthropic · Closed | 59.61% | | |
| 14 | GPT-5.6 Terra | OpenAI · Closed | max reasoning | 59.59% | |
| 15 | Gemini 3.7 Flash | Google · Closed | high reasoning | 59.31% | |
| 16 | Grok 4.6 | xAI · Closed | high reasoning | 59.17% | |
| 17 | DeepSeek V4.1 Flash | DeepSeek · Open weight | high reasoning | 57.86% | |
| 18 | Kimi K3 | Moonshot AI · Closed | 57.81% | | |
| 19 | GPT-5.5 | OpenAI · Closed | xhigh reasoning | 57.41% | |
| 20 | Muse Spark 1.2 | Meta · Closed | xhigh reasoning | 57.05% | |
| 21 | GLM-5.3 | Z.AI · Open weight | max reasoning | 56.97% | |
| 22 | Claude Opus 4.7 | Anthropic · Closed | 56.11% | | |
| 23 | Hy4 preview | Tencent · Open weight | 55.40% | | |
| 24 | Gemini 3.6 Flash | Google · Closed | high reasoning | 55.35% | |
| 25 | Muse Spark 1.1 | Meta · Closed | xhigh reasoning | 54.75% | |
| 26 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | high reasoning | 53.57% | |
| 27 | GLM-5.2 | Z.AI · Open weight | 53.12% | | |
| 28 | Gemini 3.5 Flash | Google · Closed | high reasoning | 53.08% | |
| 29 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | max reasoning | 52.37% | |
| 30 | Qwen3.8 Max | Alibaba · Open weight | 51.84% | | |
| 31 | Grok 4.5 | xAI · Closed | high reasoning | 51.53% | |
| 32 | Claude Sonnet 4.6 | Anthropic · Closed | 50.59% | | |
| 33 | Qwen3.8-27B | Alibaba · Open weight | xhigh reasoning | 48.48% | |
| 34 | GLM-5.3-Flash | Z.AI · Open weight | max reasoning | 47.22% | |
| 35 | Qwen3.7 Max | Alibaba · Closed | 44.77% | | |
| 36 | Kimi K2.6 | Moonshot AI · Open weight | 43.47% | | |
| 38 | MiniMax M3 | MiniMax · Open weight | 42.72% | | |
| 39 | Gemini 3.1 Pro Preview | Google | high reasoning | 41.90% | |
| 40 | MiMo-V2.5-Pro | Xiaomi · Closed | 40.97% | | |
| 41 | MiMo-V2.5 | Xiaomi · Closed | 39.91% | | |
| 42 | GPT-5.4 mini | OpenAI · Closed | xhigh reasoning | 39.63% | |
| 43 | Qwen3.7 Plus | Alibaba · Closed | 38.65% | | |
| 44 | Gemini 3.5 Flash-Lite | Google · Closed | high reasoning | 36.71% | |
| 45 | Inkling | Thinking Machines Lab · Open weight | 0.99 reasoning | 34.10% | |
| 46 | GPT-5.4 nano | OpenAI · Closed | high reasoning | 33.00% | |
| 47 | Qwen3.6 Plus | Alibaba · Closed | 31.98% | | |
| 48 | Inkling-Small | Thinking Machines Lab · Open weight | 0.99 reasoning | 31.86% | |
| 49 | Gemini 3 Flash Preview | Google | high reasoning | 29.44% | |
| 50 | Nemotron 3 Ultra 550b A55b | Nvidia | 27.39% | | |
| 51 | Kimi K2.5 Thinking | Moonshot AI | 26.30% | | |
| 52 | MiniMax M2.7 | MiniMax · Open weight | 24.56% | | |
| 53 | Grok 4.3 | xAI · Closed | high reasoning | 24.29% | |
| 54 | Claude Haiku 4.5 Thinking | Anthropic · Closed | 22.90% | | |
| 55 | Ling 3.0 Flash 2607 | Ant | 21.70% | | |
| 56 | Mistral Medium 3.5 | Mistral AI | high reasoning | 17.95% | |
| 57 | Grok 4.20 0309 Reasoning | xAI | 17.55% | | |
| 58 | Gemini 3.1 Flash Lite Preview | Google | high reasoning | 15.46% | |
| 59 | Mercury 2.5 | Inception · Closed | high reasoning | 12.95% | |
| 60 | Nemotron Lightning 3p5 30b A3b | Fireworks AI | 11.49% | | |