| 1 | Claude Opus 4.8 | Anthropic | Closed | claude-opus-4-8 | |
| 2 | GPT-5.5 | OpenAI | Closed | gpt-5-5 | |
| 3 | Claude Opus 4.7 | Anthropic | Closed | claude-opus-4-7 | |
| 4 | GPT-5.4 | OpenAI · Closed | 64.89% | | |
| 5 | Qwen3.7 Max | Alibaba · Closed | 64.27% | | |
| 6 | Claude Opus 4.5 | Anthropic · Closed | 64.23% | | |
| 7 | Gemini 3 Pro | Google · Closed | 63.23% | | |
| 8 | Claude Sonnet 4.6 | Anthropic · Closed | 62.92% | | |
| 9 | MiMo-V2.5-Pro | Xiaomi · Closed | 62.70% | | |
| 10 | Gemini 3.5 Flash | Google · Closed | 61.85% | | |
| 11 | Claude Opus 4.6 | Anthropic · Closed | 61.85% | | |
| 12 | GLM-5.1 | Z.AI · Open weight | 60.11% | | |
| 13 | GPT-5.3 Codex | OpenAI · Closed | 57.47% | | |
| 14 | Gemini 3.1 Pro | Google · Closed | 56.87% | | |
| 15 | Kimi K2.6 | Moonshot AI · Open weight | 56.82% | | |
| 16 | Gemini 3 Flash | Google · Closed | 56.63% | | |
| 17 | Qwen3.6-27B | Alibaba · Open weight | 54.84% | | |
| 18 | DeepSeek V4 Flash | DeepSeek · Open weight | 54.35% | | |
| 19 | GPT-5.2-Codex | OpenAI · Closed | 51.79% | | |
| 20 | Step 3.7 Flash | StepFun · Open weight | 51.57% | | |
| 21 | GLM-5 | Z.AI · Open weight | 50.99% | | |
| 22 | Qwen3.6 Plus | Alibaba · Closed | 50.60% | | |
| 23 | DeepSeek V4 Pro | DeepSeek · Open weight | 50.28% | | |
| 24 | GPT-5.1-Codex | OpenAI · Closed | 49.68% | | |
| 25 | Grok Build 0.1 | xAI · Closed | 49.15% | | |
| 26 | Claude Sonnet 4.5 | Anthropic · Closed | 48.51% | | |
| 27 | Grok 4.1 Fast | xAI · Closed | 47.32% | | |
| 28 | MiMo-V2.5 | Xiaomi · Closed | 46.89% | | |
| 29 | Qwen3.5 397B | Alibaba · Open weight | 46.76% | | |
| 30 | GPT-5.2 | OpenAI · Closed | 46.54% | | |
| 31 | Kimi K2.5 | Moonshot AI · Open weight | 45.88% | | |
| 32 | Grok 4.3 | xAI · Closed | 43.86% | | |
| 33 | Qwen3 Max | Alibaba · Closed | 43.74% | | |
| 34 | Qwen3.6-35B-A3B | Alibaba · Open weight | 42.65% | | |
| 35 | Grok 4 | xAI · Closed | 42.34% | | |
| 36 | Gemini 2.5 Pro | Google · Closed | 42.01% | | |
| 37 | GPT-5.1 | OpenAI · Closed | 41.24% | | |
| 38 | MiniMax M2.7 | MiniMax · Open weight | 40.40% | | |
| 39 | GLM-4.7 | Z.AI · Open weight | 39.95% | | |
| 40 | Claude 4 Sonnet | Anthropic · Closed | 39.66% | | |
| 41 | Qwen3.5-27B | Alibaba · Open weight | 39.41% | | |
| 42 | MiniMax M2.5 | MiniMax · Closed | 39.11% | | |
| 43 | Mistral Medium 3.5 128B | Mistral · Open weight | 39.10% | | |
| 44 | Gemini 3.1 Flash-Lite | Google · Closed | 38.46% | | |
| 45 | Grok 4.20 | xAI · Closed | 38.36% | | |
| 46 | Hy3 Preview | Tencent · Open weight | 36.91% | | |
| 47 | MiMo-V2-Pro | Xiaomi · Closed | 36.68% | | |
| 48 | Gemma 4 31B | Google · Open weight | 35.26% | | |
| 49 | Kimi K2.5 (Reasoning) | Moonshot AI · Closed | 32.58% | | |
| 50 | Trinity-Large-Thinking | Arcee AI · Open weight | 32.55% | | |
| 51 | GLM-5V-Turbo | Z.AI · Closed | 30.76% | | |
| 52 | GPT-OSS 120B | OpenAI · Open weight | 29.61% | | |
| 53 | DeepSeek V3.2 | DeepSeek · Open weight | 29.57% | | |
| 54 | Qwen3.5-35B-A3B | Alibaba · Open weight | 28.96% | | |
| 55 | GPT-4.1 | OpenAI · Closed | 25.65% | | |
| 56 | Nemotron 3 Super 120B A12B | NVIDIA · Open weight | 25.34% | | |