| 1 | GPT-5.5 | OpenAI | Proprietary | high reasoning | |
| 2 | Claude Opus 4.8 | Anthropic | Proprietary | 70.04% | |
| 3 | Claude Opus 4.7 | Anthropic | Proprietary | 68.54% | |
| 4 | Gemini 3.5 Flash | Google · Closed | high reasoning | 67.42% | |
| 5 | Gemini 3.1 Pro Preview | Google | high reasoning | 67.42% | |
| 6 | GPT-5.3 Codex | OpenAI · Closed | high reasoning | 64.05% | |
| 7 | Muse Spark | Meta · Closed | 59.55% | | |
| 8 | Claude Sonnet 4.6 | Anthropic · Closed | 59.55% | | |
| 9 | Qwen3.7 Max | Alibaba · Closed | 59.18% | | |
| 10 | Claude Opus 4.5 | Anthropic · Closed | 58.43% | | |
| 11 | Claude Opus 4.6 (Adaptive) | Anthropic · Closed | 58.43% | | |
| 12 | GPT-5.4 | OpenAI · Closed | high reasoning | 58.43% | |
| 13 | Kimi K2.6 | Moonshot AI · Open weight | 57.30% | | |
| 14 | DeepSeek V4 Pro 0813 | DeepSeek · Closed | 56.18% | | |
| 15 | Gemini 3 Pro Preview | Google | high reasoning | 55.06% | |
| 16 | Claude Opus 4.5 Thinking | Anthropic · Closed | 53.93% | | |
| 17 | GLM-5.1 | Z.AI · Open weight | 53.93% | | |
| 18 | Gemini 3 Flash Preview | Google | high reasoning | 51.69% | |
| 19 | GPT-5.2 | OpenAI · Closed | high reasoning | 51.69% | |
| 20 | Qwen 3.6 Max (preview) | Alibaba · Closed | 51.69% | | |
| 21 | GLM 5 Thinking | Zhipu AI | 49.44% | | |
| 22 | MiniMax M2.7 | MiniMax · Open weight | 47.19% | | |
| 23 | MiniMax M3 | MiniMax · Open weight | 46.07% | | |
| 24 | Qwen3.6 Plus | Alibaba · Closed | 44.94% | | |
| 25 | GPT-5.1 | OpenAI · Closed | high reasoning | 44.94% | |
| 26 | Qwen3.6-27B | Alibaba · Open weight | 44.94% | | |
| 27 | GPT-5.4 mini | OpenAI · Closed | high reasoning | 44.94% | |
| 28 | Grok 4.3 | xAI · Closed | 43.45% | | |
| 29 | Claude Sonnet 4.5 Thinking | Anthropic · Closed | 41.57% | | |
| 30 | MiniMax M2.5 | MiniMax · Closed | 41.57% | | |
| 31 | Qwen3.5 Plus Thinking | Alibaba | 41.57% | | |
| 32 | Grok 4.20 0309 Reasoning | xAI | 40.45% | | |
| 33 | Kimi K2.5 Thinking | Moonshot AI | 40.45% | | |
| 34 | GPT-5.4 nano | OpenAI · Closed | high reasoning | 39.89% | |
| 35 | Gemma 4 31b It | Google | high reasoning | 39.33% | |
| 36 | Claude Haiku 4.5 Thinking | Anthropic · Closed | 38.20% | | |
| 37 | GLM-4.7 | Z.AI · Open weight | 38.20% | | |
| 38 | MiniMax M2.1 | MiniMax | 37.08% | | |
| 39 | GPT-5 | OpenAI | high reasoning | 37.08% | |
| 40 | Kimi K2 Thinking | Moonshot AI | 37.08% | | |
| 41 | DeepSeek V3p2 Thinking | Fireworks AI | high reasoning | 35.95% | |
| 42 | DeepSeek V3p2 | Fireworks AI | none reasoning | 34.83% | |
| 43 | Laguna M.1 | Poolside · Closed | 31.46% | | |
| 44 | Gemini 2.5 Pro | Google · Closed | 30.34% | | |
| 45 | Mistral Medium 3.5 | Mistral AI | high reasoning | 30.34% | |
| 46 | Grok 4 Fast (Reasoning) | xAI · Closed | 29.21% | | |
| 47 | Laguna XS.2 | Poolside · Open weight | 28.09% | | |
| 48 | GLM-4.6 | Z.AI · Open weight | 28.09% | | |
| 49 | Grok 4 0709 | xAI | 28.09% | | |
| 50 | GPT-5 mini | OpenAI · Closed | high reasoning | 26.97% | |
| 51 | Moonshotai Kimi K2 Instruct | Together AI | 25.84% | | |
| 52 | Grok 4.1 Fast (Reasoning) | xAI · Closed | 24.72% | | |
| 53 | Gemini 3.1 Flash Lite Preview | Google | high reasoning | 24.72% | |
| 54 | Qwen3.5 Flash | Alibaba · Closed | 24.72% | | |
| 55 | Qwen3 Max | Alibaba · Closed | 24.72% | | |
| 56 | DeepSeek V3p1 | Fireworks AI | 22.47% | | |
| 57 | Gemini 2.5 Flash Preview 09 2025 Thinking | Google | 21.35% | | |
| 59 | GPT-OSS 120B | OpenAI · Open weight | 19.10% | | |
| 60 | Grok 4.1 Fast Non Reasoning | xAI | 17.98% | | |
| 61 | Trinity-Large-Thinking | Arcee AI · Open weight | 17.98% | | |
| 62 | Mistral Small 2603 | Mistral AI | high reasoning | 16.85% | |
| 63 | GPT-4.1 | OpenAI · Closed | high reasoning | 14.61% | |
| 64 | Magistral Medium 2509 | Mistral AI | 13.48% | | |
| 65 | Mistral Large 2512 | Mistral AI | 8.99% | | |
| 66 | Command A 03 2025 | Cohere | 2.25% | | |
| 67 | Llama4 Maverick Instruct Basic | Fireworks AI | 2.25% | | |