| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AndroidWorld | M2CL | Accuracy62 | 70 | 4d ago | |
| AITZ | M2-Miner-7B | SR69.4 | 20 | 4d ago | |
| AC High | M2-Miner-7B | SR72.9 | 16 | 4d ago | |
| AC Low | M2-Miner-7B | Success Rate93.5 | 16 | 4d ago | |
| CAGUI | M2-Miner-7B | TP88.8 | 11 | 4d ago | |
| AITZ, AndroidControl, and GUI-Odyssey | Avg Z-Score-0.38 | 7 | 4d ago | ||
| GUI-Odyssey | Type Accuracy90.74 | 7 | 4d ago | ||
| AndroidControl | Type85.25 | 7 | 4d ago |