| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AndroidLab | GUI-Owl-7B w/ Android Coach | Average SR (%)49.5 | 17 | 1mo ago | |
| MobileWorld | GUI-ONLY Score55.6 | 14 | 3mo ago | ||
| Android GUI Evaluation Benchmark 500 human-annotated trajectories (test) | Mobile-R1 | Accuracy78.55 | 11 | 1mo ago |