| 1 | Claude Opus 5 | Anthropic | Proprietary | 73.19% | |
| 2 | Claude Fable 5 | Anthropic | Proprietary | 71.83% | |
| 3 | Kimi K3 | Moonshot AI | Proprietary | 71.56% | |
| 4 | Muse Spark 1.1 | Meta · Closed | xhigh reasoning | 71.29% | |
| 5 | Muse Spark 1.2 | Meta · Closed | xhigh reasoning | 70.94% | |
| 6 | Inkling-Small | Thinking Machines Lab · Open weight | 0.99 reasoning | 69.62% | |
| 7 | Inkling | Thinking Machines Lab · Open weight | 0.99 reasoning | 68.57% | |
| 8 | Grok 4.3 | xAI · Closed | 68.53% | | |
| 9 | GPT-5.5 | OpenAI · Closed | xhigh reasoning | 68.42% | |
| 10 | Kimi K2.5 Thinking | Moonshot AI | 68.26% | | |
| 11 | MiniMax M3 | MiniMax · Open weight | 68.10% | | |
| 12 | Qwen3 Max | Alibaba · Closed | 68.03% | | |
| 13 | Grok 4.5 | xAI · Closed | high reasoning | 67.41% | |
| 14 | Claude Opus 4.6 (Adaptive) | Anthropic · Closed | 67.02% | | |
| 15 | Claude Sonnet 5 | Anthropic · Closed | 66.98% | | |
| 16 | Grok 4 Fast (Reasoning) | xAI · Closed | 66.90% | | |
| 17 | Kimi K2.6 | Moonshot AI · Open weight | 66.74% | | |
| 18 | Claude Opus 4.8 | Anthropic · Closed | 66.71% | | |
| 19 | Qwen 3.6 Max (preview) | Alibaba · Closed | 66.47% | | |
| 20 | Gemini 3 Flash Preview | Google | high reasoning | 66.43% | |
| 21 | Grok 4.6 | xAI · Closed | high reasoning | 66.16% | |
| 22 | GLM-5.2 | Z.AI · Open weight | 66.12% | | |
| 23 | Claude Opus 4.7 | Anthropic · Closed | 66.08% | | |
| 24 | Grok 4 0709 | xAI | 66.05% | | |
| 25 | Grok 4.1 Fast (Reasoning) | xAI · Closed | 65.97% | | |
| 26 | GPT-5.2 | OpenAI · Closed | xhigh reasoning | 65.89% | |
| 27 | Qwen3.8 Max | Alibaba · Open weight | 65.85% | | |
| 28 | Nemotron 3 Ultra 550b A55b | Nvidia | 65.46% | | |
| 29 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | max reasoning | 65.42% | |
| 30 | GPT-5.6 Terra | OpenAI · Closed | xhigh reasoning | 65.31% | |
| 31 | Claude Sonnet 4.6 | Anthropic · Closed | 65.31% | | |
| 32 | Qwen3.5 Plus Thinking | Alibaba | 65.31% | | |
| 33 | GPT-5.4 | OpenAI · Closed | xhigh reasoning | 65.27% | |
| 34 | Muse Spark | Meta · Closed | 65.11% | | |
| 35 | Claude Opus 4.5 Thinking | Anthropic · Closed | 65.07% | | |
| 36 | Gemini 3.5 Flash | Google · Closed | high reasoning | 64.69% | |
| 37 | Gemini 3.1 Pro Preview | Google | high reasoning | 64.49% | |
| 38 | GLM-5.1 | Z.AI · Open weight | 64.45% | | |
| 39 | GPT-5.6 Sol | OpenAI · Closed | max reasoning | 64.38% | |
| 40 | GPT-5.6 Luna | OpenAI · Closed | max reasoning | 64.22% | |
| 41 | GPT-5.1 | OpenAI · Closed | high reasoning | 63.83% | |
| 42 | Qwen3.7 Max | Alibaba · Closed | 63.71% | | |
| 43 | Grok 4.20 0309 Reasoning | xAI | 63.67% | | |
| 44 | Gemini 3 Pro Preview | Google | high reasoning | 63.67% | |
| 45 | Qwen3.5 Flash | Alibaba · Closed | 63.56% | | |
| 46 | Gemini 3.6 Flash | Google · Closed | high reasoning | 63.33% | |
| 47 | GPT-4.1 | OpenAI · Closed | high reasoning | 63.05% | |
| 48 | GLM 5 Thinking | Zhipu AI | 62.90% | | |
| 49 | Qwen3.6-27B | Alibaba · Open weight | 62.31% | | |
| 50 | Claude Sonnet 4.5 Thinking | Anthropic · Closed | 61.97% | | |
| 51 | Ling 3.0 Flash 2607 | Ant | 61.93% | | |
| 52 | Qwen3.6 Plus | Alibaba · Closed | 61.93% | | |
| 53 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | high reasoning | 61.85% | |
| 54 | MiMo-V2.5-Pro | Xiaomi · Closed | 61.42% | | |
| 56 | Claude Opus 4.5 | Anthropic · Closed | 61.30% | | |
| 57 | Claude Sonnet 4 20250514 Thinking | Anthropic | 61.23% | | |
| 58 | GPT-5.4 nano | OpenAI · Closed | high reasoning | 61.19% | |
| 59 | MiniMax M2.7 | MiniMax · Open weight | 61.19% | | |
| 60 | Grok 3 Mini Fast High Reasoning | xAI | high reasoning | 61.11% | |
| 61 | GPT-5 | OpenAI | high reasoning | 61.07% | |
| 62 | Mistral Large 2512 | Mistral AI | 61.03% | | |
| 63 | GLM-4.5 | Z.AI · Closed | 60.96% | | |
| 64 | GPT-5.4 mini | OpenAI · Closed | xhigh reasoning | 60.92% | |
| 65 | Claude Sonnet 4.5 | Anthropic · Closed | 60.80% | | |
| 66 | Gemini 2.5 Pro | Google · Closed | 60.80% | | |
| 67 | Gemini 3.5 Flash-Lite | Google · Closed | high reasoning | 60.68% | |
| 68 | Claude Haiku 4.5 Thinking | Anthropic · Closed | 60.61% | | |
| 69 | Kimi K2 Thinking | Moonshot AI | 60.57% | | |
| 70 | Claude 3.7 Sonnet 20250219 Thinking | Anthropic | 60.41% | | |
| 71 | Claude Haiku 4.5 | Anthropic · Closed | 60.30% | | |
| 72 | GPT-5 mini | OpenAI · Closed | high reasoning | 60.18% | |
| 73 | MiMo-V2.5 | Xiaomi · Closed | 59.91% | | |
| 74 | Gemini 2.5 Pro Exp 03 25 | Google | 59.83% | | |
| 75 | Gemini 2.5 Flash Preview 09 2025 Thinking | Google | 59.75% | | |
| 76 | o3 | OpenAI · Closed | high reasoning | 59.71% | |
| 77 | Grok 3 | xAI | 59.71% | | |
| 78 | MiniMax M2.5 | MiniMax · Closed | 59.60% | | |
| 79 | Grok 3 Mini Fast Low Reasoning | xAI | low reasoning | 59.48% | |
| 80 | Gemini 3.1 Flash Lite Preview | Google | high reasoning | 59.36% | |
| 81 | O4 Mini | OpenAI | high reasoning | 58.97% | |
| 82 | Gemini 2.5 Flash Preview 09 2025 | Google | 58.97% | | |
| 83 | MiniMax M2.1 | MiniMax | 58.90% | | |
| 84 | Mistral Medium 3.5 | Mistral AI | high reasoning | 58.78% | |
| 85 | Grok 4 Fast Non Reasoning | xAI | 58.39% | | |
| 86 | GPT-OSS 120B | OpenAI · Open weight | 58.24% | | |
| 87 | Laguna M.1 | Poolside · Closed | 58.16% | | |
| 88 | GPT-4.1 mini | OpenAI · Closed | high reasoning | 57.93% | |
| 89 | Gemini 2.5 Flash Lite Preview 09 2025 Thinking | Google | 57.58% | | |
| 90 | GLM-4.6 | Z.AI · Open weight | 56.84% | | |
| 91 | Laguna XS.2 | Poolside · Open weight | 56.33% | | |
| 92 | Gemini 2.5 Flash Lite Preview 09 2025 | Google | 56.29% | | |
| 94 | DeepSeek V3 0324 | Fireworks AI | 54.74% | | |
| 95 | Claude Sonnet 4 | Anthropic | 54.70% | | |
| 96 | Trinity-Large-Thinking | Arcee AI · Open weight | 54.66% | | |
| 97 | Nemotron Lightning 3p5 30b A3b | Fireworks AI | 54.23% | | |
| 98 | Gemini 2.5 Flash Preview 04 17 | Google | 54.16% | | |
| 99 | DeepSeek-R1 | DeepSeek · Open weight | 54.12% | | |
| 100 | Claude 3.5 Sonnet | Anthropic · Closed | 53.61% | | |
| 101 | GPT-OSS 20B | OpenAI · Open weight | 53.15% | | |
| 102 | Qwen3 Max Preview | Alibaba | 52.95% | | |
| 103 | Grok 4.1 Fast Non Reasoning | xAI | 52.49% | | |
| 104 | DeepSeek V3 | DeepSeek · Open weight | 52.49% | | |
| 105 | DeepSeek V3p1 | Fireworks AI | 51.48% | | |
| 106 | Grok 2 1212 | xAI | 51.13% | | |
| 107 | DeepSeek V3p2 Thinking | Fireworks AI | high reasoning | 50.97% | |
| 108 | Claude 3.5 Haiku | Anthropic | 50.82% | | |
| 109 | Mistral Medium 2505 | Mistral AI | 50.74% | | |
| 110 | Moonshotai Kimi K2 Instruct | Together AI | 50.39% | | |
| 111 | Llama4 Maverick Instruct Basic | Fireworks AI | 49.73% | | |
| 112 | DeepSeek V3p2 | Fireworks AI | none reasoning | 47.94% | |
| 113 | Magistral Medium 2509 | Mistral AI | 47.40% | | |
| 114 | Meta Llama Llama 4 Scout 17B 16E Instruct | Together AI | 46.78% | | |
| 115 | GLM-4.7 | Z.AI · Open weight | 46.39% | | |
| 116 | Command A 03 2025 | Cohere | 45.96% | | |
| 117 | GPT-4o | OpenAI · Closed | high reasoning | 45.92% | |
| 118 | GPT-4o mini | OpenAI · Closed | high reasoning | 45.45% | |
| 119 | o3-mini | OpenAI · Closed | high reasoning | 45.30% | |
| 120 | Mistral Small 2503 | Mistral AI | 44.17% | | |
| 121 | Magistral Small 2509 | Mistral AI | 44.02% | | |
| 122 | Gemini 2.0 Pro Exp 02 05 | Google | 43.44% | | |
| 123 | GPT-4.1 nano | OpenAI · Closed | high reasoning | 42.08% | |
| 124 | Jamba Large 1.6 | AI21 Labs | 41.53% | | |
| 125 | Gemini 1.5 Pro 002 | Google | 40.52% | | |
| 127 | Jamba 1.5 Large | AI21 Labs | 39.43% | | |
| 128 | Meta Llama Meta Llama 3.1 70B Instruct Turbo | Together AI | 38.85% | | |
| 129 | Gemini 1.5 Flash 002 | Google | 38.19% | | |
| 130 | Jamba Mini 1.6 | AI21 Labs | 38.03% | | |
| 131 | Meta Llama Meta Llama 3.1 8B Instruct Turbo | Together AI | 37.80% | | |
| 132 | Jamba 1.5 Mini | AI21 Labs | 33.88% | | |
| 133 | Gemini 2.0 Flash 001 | Google | 33.72% | | |
| 134 | Gemini 1.5 Flash 001 | Google | 28.63% | | |