| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Mind2Web | AUTOMMEMO | Success Rate45.68 | 24 | 15d ago | |
| MMBench-GUI | InfiGUI-G1-7B | Windows (Basic) Score82.7 | 16 | 2mo ago | |
| GUI-Odyssey (test) | WebFactory-3B | Type Accuracy66 | 4 | 2mo ago | |
| GUI-Act-Web (test) | GUI-R1-3B | Type Accuracy89.9 | 4 | 2mo ago | |
| AITW (First 128 task samples) | General Success Rate73.2 | 2 | 3mo ago | ||
| AITW First 96 task samples | iSHIFT | General Success0.7225 | 2 | 3mo ago |
