| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Android Control high | Qwen-32B | Success Rate50.8 | 5 | 24d ago | |
| Android Control low | ReCAP-32B | Success Rate67.4 | 5 | 24d ago | |
| GUI Odyssey | iSHIFT | Success Rate73.97 | 5 | 1mo ago | |
| Android Control Low complexity | iSHIFT | Success Rate87.7 | 5 | 1mo ago | |
| Android Control High complexity | iSHIFT | Success Rate65.6 | 5 | 1mo ago |