| 1 | Claude Opus 5 | Anthropic | Proprietary | 97.0% | |
| 2 | DeepSeek V4 Pro 0813 | DeepSeek | Proprietary | max reasoning | |
| 3 | GPT-5.6 Sol | OpenAI | Proprietary | max reasoning | |
| 4 | Grok 4.6 | xAI · Closed | high reasoning | 95.6% | |
| 5 | GPT-5.6 Terra | OpenAI · Closed | max reasoning | 95.4% | |
| 6 | GLM-5.3 | Z.AI · Open weight | max reasoning | 95.4% | |
| 7 | Claude Fable 5 | Anthropic · Closed | 95.0% | | |
| 8 | Kimi K3 | Moonshot AI · Closed | 93.4% | | |
| 9 | GPT-5.6 Luna | OpenAI · Closed | max reasoning | 93.0% | |
| 10 | GLM-5.3-Flash | Z.AI · Open weight | max reasoning | 92.0% | |
| 11 | DeepSeek V4 Flash 0731 | DeepSeek · Closed | high reasoning | 88.8% | |
| 12 | Claude Opus 4.8 | Anthropic · Closed | 88.6% | | |
| 13 | Grok 4.5 | xAI · Closed | high reasoning | 86.6% | |
| 14 | Muse Spark 1.2 | Meta · Closed | xhigh reasoning | 86.6% | |
| 15 | Qwen3.8-27B | Alibaba · Open weight | xhigh reasoning | 86.0% | |
| 16 | Claude Opus 4.8 Claude Code | Anthropic | Claude Code | Claude Code | |
| 17 | Qwen3.8 Max | Alibaba · Open weight | 85.6% | | |
| 18 | GLM-5.2 | Z.AI · Open weight | max reasoning | 82.8% | |
| 19 | GPT-5.5 | OpenAI · Closed | xhigh reasoning | 82.6% | |
| 20 | Inkling-Small | Thinking Machines Lab · Open weight | 0.99 reasoning | 82.2% | |
| 21 | Muse Spark 1.1 | Meta · Closed | xhigh reasoning | 82.0% | |
| 22 | Claude Opus 4.7 | Anthropic · Closed | 82.0% | | |
| 23 | Gemini 3.7 Flash | Google · Closed | high reasoning | 80.8% | |
| 24 | Gemini 3.8 Flash | Google · Closed | high reasoning | 80.0% | |
| 25 | Composer 2.5 | Cursor · Closed | Cursor CLI | Cursor CLI | |
| 26 | Gemini 3.6 Flash | Google · Closed | high reasoning | 79.6% | |
| 27 | Claude Sonnet 5 | Anthropic · Closed | 79.6% | | |
| 28 | Gemini 3.5 Flash | Google · Closed | high reasoning | 78.8% | |
| 29 | Gemini 3.1 Pro Preview | Google | high reasoning | 78.8% | |
| 30 | GPT-5.4 | OpenAI · Closed | xhigh reasoning | 78.2% | |
| 31 | Claude Opus 4.6 (Adaptive) | Anthropic · Closed | 78.2% | | |
| 32 | Kimi K2.7 Code | Moonshot AI · Open weight | 78.2% | | |
| 33 | GPT-5.3 Codex | OpenAI · Closed | xhigh reasoning | 78.0% | |
| 34 | Inkling | Thinking Machines Lab · Open weight | 0.99 reasoning | 77.6% | |
| 35 | Claude Sonnet 4.6 | Anthropic · Closed | 77.4% | | |
| 37 | GPT-5.5 Codex | OpenAI | Codex | Codex | |
| 38 | Claude Opus 4.5 Thinking | Anthropic · Closed | 76.4% | | |
| 39 | Gemini 3 Pro Preview | Google | high reasoning | 76.4% | |
| 40 | GLM-5.1 | Z.AI · Open weight | 76.4% | | |
| 41 | GPT-5.5 Factory | OpenAI | Factory | Factory | |
| 42 | Kimi K2.6 | Moonshot AI · Open weight | 76.2% | | |
| 43 | GPT-5.2 | OpenAI · Closed | xhigh reasoning | 75.8% | |
| 44 | Gemini 3 Flash Preview | Google | high reasoning | 75.0% | |
| 45 | Gemini 3.5 Flash-Lite | Google · Closed | high reasoning | 75.0% | |
| 46 | MiniMax M3 | MiniMax · Open weight | 75.0% | | |
| 47 | MiniMax M2.1 | MiniMax | 74.8% | | |
| 48 | Muse Spark | Meta · Closed | 74.4% | | |
| 49 | MiniMax M2.5 | MiniMax · Closed | 74.2% | | |
| 50 | MiMo-V2.5-Pro | Xiaomi · Closed | 74.0% | | |
| 51 | MiniMax M2.7 | MiniMax · Open weight | 73.8% | | |
| 52 | Qwen3.6 Plus | Alibaba · Closed | 73.4% | | |
| 53 | GPT-5.4 mini | OpenAI · Closed | xhigh reasoning | 73.0% | |
| 54 | Qwen 3.6 Max (preview) | Alibaba · Closed | 72.8% | | |
| 55 | GPT-5.2-Codex | OpenAI · Closed | high reasoning | 72.4% | |
| 56 | Grok 4.20 0309 Reasoning | xAI | 72.2% | | |
| 57 | Grok 4.3 | xAI · Closed | high reasoning | 71.4% | |
| 58 | GLM 5 Thinking | Zhipu AI | 71.4% | | |
| 59 | Qwen3.5 Plus Thinking | Alibaba | 71.2% | | |
| 60 | MiMo-V2.5 | Xiaomi · Closed | 71.0% | | |
| 61 | Kimi K2.5 Thinking | Moonshot AI | 70.0% | | |
| 62 | Claude Sonnet 4.5 Thinking | Anthropic · Closed | 70.0% | | |
| 63 | Qwen3.6-27B | Alibaba · Open weight | 70.0% | | |
| 64 | GPT-5.4 nano | OpenAI · Closed | high reasoning | 69.8% | |
| 65 | GPT-5.1 | OpenAI · Closed | high reasoning | 69.8% | |
| 66 | GLM-4.7 | Z.AI · Open weight | 69.4% | | |
| 67 | GPT-5 | OpenAI | high reasoning | 69.0% | |
| 68 | Nemotron 3 Ultra 550b A55b | Nvidia | 69.0% | | |
| 69 | Qwen3.7 Max | Alibaba · Closed | 68.8% | | |
| 70 | DeepSeek V3p2 Thinking | Fireworks AI | high reasoning | 67.6% | |
| 71 | Claude Haiku 4.5 Thinking | Anthropic · Closed | 66.6% | | |
| 72 | Mistral Medium 3.5 | Mistral AI | high reasoning | 66.4% | |
| 73 | Ling 3.0 Flash 2607 | Ant | 65.2% | | |
| 74 | Qwen3.5 Flash | Alibaba · Closed | 64.4% | | |
| 75 | Gemini 3.1 Flash Lite Preview | Google | high reasoning | 62.8% | |
| 76 | Devstral 2512 | Mistral AI | 62.8% | | |
| 77 | GPT-5 mini | OpenAI · Closed | high reasoning | 60.8% | |
| 78 | Kimi K2 Thinking | Moonshot AI | 60.2% | | |
| 79 | Grok 4 0709 | xAI | 57.8% | | |
| 80 | Laguna M.1 | Poolside · Closed | 57.6% | | |
| 81 | Laguna XS.2 | Poolside · Open weight | 55.2% | | |
| 82 | Gemini 2.5 Pro | Google · Closed | 54.4% | | |
| 83 | Nemotron Lightning 3p5 30b A3b | Fireworks AI | 52.8% | | |
| 84 | Grok 4 Fast (Reasoning) | xAI · Closed | 45.4% | | |
| 85 | Grok 4.1 Fast (Reasoning) | xAI · Closed | 41.4% | | |
| 86 | Mistral Large 2512 | Mistral AI | 41.4% | | |
| 87 | GPT-OSS 120B | OpenAI · Open weight | 33.6% | | |
| 88 | Command A 03 2025 | Cohere | 7.8% | | |