| Rank | Model | Provider | Score |
|---|---|---|---|
| 1 | Qwen3.8 Max | Alibaba | 67.7% |
| 2 | Qwen3.8 Flash Next | Alibaba | 62.5% |
| 3 | Qwen3.8 27B | Alibaba | 61.7% |
| 4 | Qwen3.6 Plus | Alibaba | 56.6% |
| 5 | Qwen3.6 27B | Alibaba | 53.5% |
| 6 | Qwen3.6 35B A3B | Alibaba | 49.5% |
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.