| 1 | Claude Fable 5 | Anthropic | Closed | claude-fable-5 | |
| 2 | Claude Opus 4.8 | Anthropic | Closed | claude-opus-4-8 | |
| 3 | Claude Opus 4.7 (Adaptive) | Anthropic | Closed | claude-opus-4-7 | |
| 4 | Claude Opus 4.6 | Anthropic · Closed | 66.7% | | |
| 5 | GPT-5.5 | OpenAI · Closed | 65.9% | | |
| 6 | GPT-5.4 | OpenAI · Closed | 64.3% | | |
| 7 | Gemini 3.5 Flash | Google · Closed | 62.6% | | |
| 8 | Claude Opus 4.5 | Anthropic · Closed | 60.6% | | |
| 9 | Gemini 3.1 Pro | Google · Closed | 60.6% | | |
| 10 | GPT-5.2 | OpenAI · Closed | 58.8% | | |
| 11 | GPT-5.2-Codex | OpenAI · Closed | 58.3% | | |
| 12 | GLM-5.1 | Z.AI · Open weight | 58.2% | | |
| 13 | MiniMax M3 | MiniMax · Open weight | 57.2% | | |
| 14 | Kimi K2.6 | Moonshot AI · Open weight | 57.1% | | |
| 15 | Claude Sonnet 4.5 | Anthropic · Closed | 53.0% | | |
| 16 | Qwen3.6 Plus | Alibaba · Closed | 52.9% | | |
| 17 | GLM-5 | Z.AI · Open weight | 49.4% | | |
| 18 | Kimi K2.5 | Moonshot AI · Open weight | 49.2% | | |
| 19 | Gemini 3 Pro | Google · Closed | 49.0% | | |
| 20 | Gemini 3 Flash | Google · Closed | 49.0% | | |
| 21 | DeepSeek V3.2 (Thinking) | DeepSeek · Open weight | 45.7% | | |
| 22 | MiniMax M2.5 | MiniMax · Closed | 45.2% | | |
| 23 | Claude Sonnet 4.6 | Anthropic · Closed | 44.5% | | |
| 24 | Qwen3 Coder Next | Alibaba | 43.8% | | |
| 25 | MiniMax M2.7 | MiniMax · Open weight | 43.4% | | |
| 26 | GLM-4.7 | Z.AI · Open weight | 42.3% | | |
| 27 | MiniMax M2.1 | MiniMax | 41.2% | | |
| 28 | Kimi K2.5 (Reasoning) | Moonshot AI · Closed | 41.0% | | |
| 29 | DeepSeek V4 Pro | DeepSeek · Open weight | 40.7% | | |
| 30 | Qwen3.5 Flash | Alibaba · Closed | 38.1% | | |
| 31 | Nemotron 3 Super 120B A12B | NVIDIA · Open weight | 36.2% | | |
| 32 | Trinity-Large-Thinking | Arcee AI · Open weight | 32.1% | | |
| 33 | Qwen3 Coder 480B A35B | Alibaba | 30.9% | | |