| Rank | Model | Provider | Score |
|---|---|---|---|
| 1 | Claude Opus 5 | Anthropic | 80.6% |
| 2 | Claude Fable 5 | Anthropic | 77.9% |
| 3 | Claude Fable 5.1 | Anthropic | 77.8% |
| 4 | MiMo V2.6 Pro | Xiaomi | 76.9% |
| 5 | Kimi K3 | Moonshot AI | 76.5% |
| 6 | GPT 5.6 Sol | OpenAI | 74.9% |
| 7 | MiMo V2.6 Flash | Xiaomi | 73.6% |
| 8 | MiMo V2.5 Pro | Xiaomi | 49.1% |
Figures are taken from public model cards, technical reports and vendor announcements, and are approximate where sources disagree. Results from different benchmark versions or tool-use settings never share a column: Terminal Bench 2.1, 3.0 and DeepSWE v1.1 are distinct benchmarks, and HLE with tools is separate from HLE without tools. Only models with a published result are listed; the score column is shaded relative to the best and worst result on this benchmark.