| 1 | Claude Mythos 5 | Anthropic | Closed | claude-mythos-5 | |
| 2 | Claude Fable 5 | Anthropic | Closed | claude-fable-5 | |
| 3 | Claude Opus 5 | Anthropic | Closed | claude-opus-5 | |
| 4 | Sakana Fugu-Ultra | Sakana AI · Closed | 73.7% | | |
| 5 | Claude Opus 4.8 | Anthropic · Closed | 69.2% | | |
| 6 | Grok 4.5 | xAI · Closed | 64.7% | | |
| 7 | GPT-5.6 Sol | OpenAI · Closed | 64.6% | | |
| 8 | Claude Opus 4.7 (Adaptive) | Anthropic · Closed | 64.3% | | |
| 9 | GPT-5.6 Terra | OpenAI · Closed | 63.4% | | |
| 10 | Claude Sonnet 5 | Anthropic · Closed | 63.2% | | |
| 11 | GPT-5.6 Luna | OpenAI · Closed | 62.7% | | |
| 12 | Ornith-1.0-397B | DeepReinforce AI · Open weight | 62.2% | | |
| 13 | GLM-5.2 | Z.AI · Open weight | 62.1% | | |
| 14 | Muse Spark 1.1 | Meta · Closed | 61.5% | | |
| 15 | Qwen3.7 Max | Alibaba · Closed | 60.6% | | |
| 16 | Laguna S 2.1 | Poolside · Open weight | 59.4% | | |
| 17 | MiniMax M3 | MiniMax · Open weight | 59% | | |
| 18 | Sakana Fugu | Sakana AI · Closed | 59% | | |
| 19 | GPT-5.5 | OpenAI · Closed | 58.6% | | |
| 20 | Kimi K2.6 | Moonshot AI · Open weight | 58.6% | | |
| 21 | GLM-5.1 | Z.AI · Open weight | 58.4% | | |
| 22 | GPT-5.4 | OpenAI · Closed | 57.7% | | |
| 23 | Qwen3.7 Plus | Alibaba · Closed | 57.6% | | |
| 24 | Qwen 3.6 Max (preview) | Alibaba · Closed | 57.3% | | |
| 25 | MiMo-V2.5-Pro | Xiaomi · Closed | 57.2% | | |
| 26 | Claude Opus 4.5 | Anthropic · Closed | 57.1% | | |
| 27 | GPT-5.3 Codex | OpenAI · Closed | 56.8% | | |
| 28 | Qwen3.6 Plus | Alibaba · Closed | 56.6% | | |
| 29 | Step 3.7 Flash | StepFun · Open weight | 56.3% | | |
| 30 | MiniMax M2.7 | MiniMax · Open weight | 56.2% | | |
| 31 | MiMo-V2.5 | Xiaomi · Closed | 56.1% | | |
| 32 | GPT-5.2 | OpenAI · Closed | 55.6% | | |
| 33 | DeepSeek V4 Pro (Max) | DeepSeek · Open weight | 55.4% | | |
| 34 | Gemini 3.5 Flash | Google · Closed | 55.1% | | |
| 35 | GLM-5 | Z.AI · Open weight | 55.1% | | |
| 36 | DeepSeek V4 Pro (High) | DeepSeek · Open weight | 54.4% | | |
| 37 | Inkling | Thinking Machines Lab · Open weight | 54.3% | | |
| 38 | Gemini 3.5 Flash-Lite | Google · Closed | 54.2% | | |
| 39 | Qwen3.6-27B | Alibaba · Open weight | 53.5% | | |
| 40 | Claude Opus 4.6 | Anthropic · Closed | 53.4% | | |
| 41 | MAI-Thinking-1 | Microsoft · Closed | 52.8% | | |
| 42 | DeepSeek V4 Flash (Max) | DeepSeek · Open weight | 52.6% | | |
| 43 | Muse Spark | Meta · Closed | 52.4% | | |
| 44 | DeepSeek V4 Flash (High) | DeepSeek · Open weight | 52.3% | | |
| 45 | DeepSeek V4 Pro | DeepSeek · Open weight | 52.1% | | |
| 46 | Grok 4.20 | xAI · Closed | 51.8% | | |
| 47 | Qwen3.5 397B | Alibaba · Open weight | 50.9% | | |
| 48 | Kimi K2.5 | Moonshot AI · Open weight | 50.7% | | |
| 49 | Ornith-1.0-35B | DeepReinforce AI · Open weight | 50.4% | | |
| 50 | Qwen3.6-35B-A3B | Alibaba · Open weight | 49.5% | | |
| 51 | Laguna M.1 | Poolside · Closed | 49.2% | | |
| 52 | DeepSeek V4 Flash | DeepSeek · Open weight | 49.1% | | |
| 53 | Laguna XS.2 | Poolside · Open weight | 46.3% | | |
| 54 | Ornith-1.0-9B | DeepReinforce AI · Open weight | 42.9% | | |