| 1 | Google | high reasoning | Gemini 3.1 Pro Preview | 95.5% | |
| 2 | GPT-5.6 Sol | OpenAI | Proprietary | max reasoning | |
| 3 | Grok 4.6 | xAI | Proprietary | high reasoning | |
| 4 | Gemini 3.8 Flash | Google · Closed | high reasoning | 94.4% | |
| 5 | Gemini 3.7 Flash | Google · Closed | high reasoning | 93.9% | |
| 6 | Qwen3.8 Max | Alibaba · Open weight | 93.7% | | |
| 7 | Gemini 3.6 Flash | Google · Closed | high reasoning | 93.4% | |
| 8 | Claude Opus 5 | Anthropic · Closed | 93.4% | | |
| 9 | Claude Fable 5.1 | Anthropic · Closed | 93.4% | | |
| 10 | Claude Fable 5 | Anthropic · Closed | 93.2% | | |
| 11 | GPT-5.5 | OpenAI · Closed | xhigh reasoning | 93.2% | |
| 12 | Kimi K3 | Moonshot AI · Closed | 92.9% | | |
| 13 | Grok 4.5 | xAI · Closed | high reasoning | 92.9% | |
| 14 | Gemini 3.5 Flash | Google · Closed | high reasoning | 92.7% | |
| 15 | MiniMax M3 | MiniMax · Open weight | 92.7% | | |
| 16 | Claude Opus 4.8 | Anthropic · Closed | 92.4% | | |
| 17 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | max reasoning | 92.4% | |
| 18 | GPT-5.6 Luna | OpenAI · Closed | max reasoning | 91.7% | |
| 19 | Gemini 3 Pro Preview | Google | high reasoning | 91.7% | |
| 20 | GPT-5.2 | OpenAI · Closed | xhigh reasoning | 91.7% | |
| 21 | GPT-5.4 | OpenAI · Closed | xhigh reasoning | 91.7% | |
| 22 | Grok 4.3 | xAI · Closed | 91.4% | | |
| 23 | Muse Spark 1.1 | Meta · Closed | xhigh reasoning | 91.2% | |
| 24 | GPT-5.6 Terra | OpenAI · Closed | xhigh reasoning | 90.9% | |
| 25 | Qwen3.7 Max | Alibaba · Closed | 90.2% | | |
| 26 | Claude Opus 4.7 | Anthropic · Closed | 90.2% | | |
| 27 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | high reasoning | 89.9% | |
| 28 | Muse Spark | Meta · Closed | 89.6% | | |
| 29 | Claude Opus 4.6 (Adaptive) | Anthropic · Closed | 89.6% | | |
| 31 | Kimi K2.6 | Moonshot AI · Open weight | 89.1% | | |
| 32 | Claude Sonnet 5 | Anthropic · Closed | 88.9% | | |
| 33 | Qwen3.8-27B | Alibaba · Open weight | xhigh reasoning | 88.9% | |
| 34 | Grok 4.20 0309 Reasoning | xAI | 88.6% | | |
| 35 | Grok 4 0709 | xAI | 88.1% | | |
| 36 | GLM-5.3 | Z.AI · Open weight | max reasoning | 88.1% | |
| 37 | Gemini 3 Flash Preview | Google | high reasoning | 87.9% | |
| 38 | Qwen3.5 Plus Thinking | Alibaba | 87.4% | | |
| 39 | Qwen3.6 Plus | Alibaba · Closed | 87.4% | | |
| 40 | Inkling | Thinking Machines Lab · Open weight | 0.99 reasoning | 87.1% | |
| 41 | GPT-5.1 | OpenAI · Closed | high reasoning | 86.6% | |
| 42 | MiniMax M2.7 | MiniMax · Open weight | 86.6% | | |
| 43 | GLM-5.3-Flash | Z.AI · Open weight | max reasoning | 86.4% | |
| 44 | Nemotron 3 Ultra 550b A55b | Nvidia | 86.1% | | |
| 45 | Claude Opus 4.5 Thinking | Anthropic · Closed | 85.9% | | |
| 46 | GPT-5 | OpenAI | high reasoning | 85.6% | |
| 47 | GLM-5.2 | Z.AI · Open weight | 85.6% | | |
| 48 | Claude Sonnet 4.6 | Anthropic · Closed | 85.6% | | |
| 49 | Grok 4 Fast (Reasoning) | xAI · Closed | 85.4% | | |
| 50 | Ling 3.0 Flash 2607 | Ant | 84.8% | | |
| 51 | Qwen3 Max | Alibaba · Closed | 84.8% | | |
| 52 | GLM-5.1 | Z.AI · Open weight | 84.5% | | |
| 53 | Grok 4.1 Fast (Reasoning) | xAI · Closed | 84.3% | | |
| 54 | o3 | OpenAI · Closed | high reasoning | 84.1% | |
| 55 | Kimi K2.5 Thinking | Moonshot AI | 84.1% | | |
| 56 | Gemini 3.5 Flash-Lite | Google · Closed | high reasoning | 83.8% | |
| 57 | Inkling-Small | Thinking Machines Lab · Open weight | 0.99 reasoning | 83.6% | |
| 58 | GLM 5 Thinking | Zhipu AI | 83.3% | | |
| 59 | GPT-5.4 mini | OpenAI · Closed | xhigh reasoning | 83.1% | |
| 60 | Qwen3.5 Flash | Alibaba · Closed | 82.8% | | |
| 61 | MiMo-V2.5-Pro | Xiaomi · Closed | 82.6% | | |
| 62 | MiniMax M2.5 | MiniMax · Closed | 82.1% | | |
| 63 | Claude Sonnet 4.5 Thinking | Anthropic · Closed | 81.6% | | |
| 64 | Gemini 2.5 Flash Preview 09 2025 | Google | 81.6% | | |
| 65 | MiMo-V2.5 | Xiaomi · Closed | 81.6% | | |
| 66 | Gemini 3.1 Flash Lite Preview | Google | high reasoning | 81.1% | |
| 67 | Gemini 2.5 Pro Exp 03 25 | Google | 80.8% | | |
| 68 | GPT-5 mini | OpenAI · Closed | high reasoning | 80.3% | |
| 69 | DeepSeek V3p2 Thinking | Fireworks AI | high reasoning | 80.3% | |
| 70 | GLM-4.7 | Z.AI · Open weight | 80.0% | | |
| 71 | Claude Opus 4.5 | Anthropic · Closed | 79.5% | | |
| 73 | Grok 3 Mini Fast High Reasoning | xAI | high reasoning | 79.3% | |
| 74 | GPT-OSS 120B | OpenAI · Open weight | 78.5% | | |
| 75 | MiniMax M2.1 | MiniMax | 78.5% | | |
| 76 | Kimi K2 Thinking | Moonshot AI | 78.5% | | |
| 77 | Qwen3 Max Preview | Alibaba | 77.8% | | |
| 78 | GPT-5.4 nano | OpenAI · Closed | high reasoning | 77.5% | |
| 79 | Gemini 2.5 Flash Preview 09 2025 Thinking | Google | 76.5% | | |
| 80 | Claude Opus 4.1 20250805 Thinking | Anthropic | 76.3% | | |
| 81 | DeepSeek V3p2 | Fireworks AI | none reasoning | 76.3% | |
| 82 | o3-mini | OpenAI · Closed | high reasoning | 75.5% | |
| 83 | Claude 3.7 Sonnet 20250219 Thinking | Anthropic | 75.3% | | |
| 84 | Claude Sonnet 4 20250514 Thinking | Anthropic | 75.0% | | |
| 85 | O4 Mini | OpenAI | high reasoning | 74.5% | |
| 86 | GLM-4.6 | Z.AI · Open weight | 74.5% | | |
| 87 | Grok 3 | xAI | 74.2% | | |
| 88 | o1 | OpenAI · Closed | high reasoning | 73.2% | |
| 89 | Grok 3 Mini Fast Low Reasoning | xAI | low reasoning | 73.0% | |
| 90 | Claude Haiku 4.5 Thinking | Anthropic · Closed | 72.2% | | |
| 91 | GLM-4.5 | Z.AI · Closed | 72.2% | | |
| 92 | Claude Opus 4 | Anthropic | 71.7% | | |
| 93 | Moonshotai Kimi K2 Instruct | Together AI | 71.5% | | |
| 94 | Gemini 2.5 Flash Lite Preview 09 2025 Thinking | Google | 70.2% | | |
| 95 | Qwen3 235b A22b | Fireworks AI | 70.2% | | |
| 96 | Claude Opus 4.1 | Anthropic | 70.0% | | |
| 97 | Llama4 Maverick Instruct Basic | Fireworks AI | 69.4% | | |
| 98 | Claude Sonnet 4 | Anthropic | 69.4% | | |
| 99 | GPT-OSS 20B | OpenAI · Open weight | 68.9% | | |
| 100 | Mistral Large 2512 | Mistral AI | 68.4% | | |
| 101 | GPT-4.1 mini | OpenAI · Closed | high reasoning | 67.9% | |
| 102 | Claude 3.7 Sonnet | Anthropic | 67.4% | | |
| 103 | GPT-4.1 | OpenAI · Closed | high reasoning | 65.4% | |
| 104 | Gemini 2.0 Flash 001 | Google | 65.2% | | |
| 105 | Grok 4.1 Fast Non Reasoning | xAI | 65.2% | | |
| 106 | Gemini 2.5 Flash Lite Preview 09 2025 | Google | 64.1% | | |
| 107 | GPT-5 nano | OpenAI · Closed | high reasoning | 63.4% | |
| 108 | Langston Nim Nvidia Llama 3.3 Nemotron Super 49b V1 42e84561 Thinking | Together AI | 62.4% | | |
| 109 | Magistral Medium 2509 | Mistral AI | 62.4% | | |
| 110 | Grok 4 Fast Non Reasoning | xAI | 62.1% | | |
| 111 | DeepSeek V3 0324 | Fireworks AI | 61.6% | | |
| 112 | Claude 3.5 Sonnet | Anthropic · Closed | 59.3% | | |
| 113 | MiMo-V2-Flash | Xiaomi · Open weight | 59.3% | | |
| 114 | Gemini 1.5 Pro 002 | Google | 58.3% | | |
| 115 | Magistral Small 2509 | Mistral AI | 58.3% | | |
| 116 | Gemini 2.5 Flash Preview 04 17 | Google | 57.6% | | |
| 117 | Laguna XS.2 | Poolside · Open weight | 55.0% | | |
| 118 | DeepSeek V3 | DeepSeek · Open weight | 54.5% | | |
| 119 | GPT-4o | OpenAI · Closed | high reasoning | 53.8% | |
| 120 | GPT-4.1 nano | OpenAI · Closed | high reasoning | 50.8% | |
| 121 | Mistral Small 2402 | Mistral AI | 50.8% | | |
| 122 | Grok 2 1212 | xAI | 50.8% | | |
| 124 | Meta Llama Llama 3.3 70B Instruct Turbo | Together AI | 50.0% | | |
| 125 | Command A 03 2025 | Cohere | 48.5% | | |
| 126 | Mistral Large 2411 | Mistral AI | 47.7% | | |
| 127 | Langston Nim Nvidia Llama 3.3 Nemotron Super 49b V1 42e84561 | Together AI | 47.7% | | |
| 128 | Meta Llama Llama 4 Scout 17B 16E Instruct | Together AI | 47.0% | | |
| 129 | Gemini 1.5 Flash 002 | Google | 46.0% | | |
| 130 | Mistral Small 2503 | Mistral AI | 44.2% | | |
| 131 | GPT-4o mini | OpenAI · Closed | high reasoning | 44.2% | |
| 132 | Claude 3.5 Haiku | Anthropic | 37.9% | | |
| 133 | Jamba Large 1.6 | AI21 Labs | 36.1% | | |
| 134 | Mistral Medium 3.5 | Mistral AI | high reasoning | 34.8% | |
| 135 | Jamba Mini 1.6 | AI21 Labs | 32.1% | | |
| 136 | Command R Plus | Cohere | 31.1% | | |
| 137 | GPT-3.5 Turbo | OpenAI | high reasoning | 30.6% | |
| 138 | Laguna M.1 | Poolside · Closed | 27.0% | | |