| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| UI Navigation | AndroidControl (offline) | Step Success Rate79.1 | 23 | |
| GUI planning | AndroidControl High | SR67.5 | 21 | |
| GUI planning | AndroidControl Low | SR (%)86.4 | 21 | |
| Short-term planning | AndroidControl Low | Type85.17 | 16 | |
| Mobile Agent Navigation | AndroidControl 1.0 (test) | Step Success Rate (SR)72.9 | 15 | |
| Mobile GUI Agent Execution | AndroidControl Curated Easy | Type Success Rate88.6 | 15 | |
| Mobile GUI Agent Execution | AndroidControl Curated-Hard | Type Rate80.8 | 15 | |
| Long-term Planning | AndroidControl High | Type Rate71.79 | 14 | |
| GUI Action Grounding | AndroidControl High (test) | Type Accuracy85.22 | 8 | |
| GUI Action Grounding | AndroidControl-Low (test) | Type Accuracy93.61 | 8 | |
| Mobile Agent Evaluation | AndroidControl High (test) | Grounding43.16 | 8 | |
| Mobile Agent Evaluation | AndroidControl Low (test) | Grounding0.8769 | 8 | |
| GUI Agent Navigation and Action | AndroidControl | Type Rate83.21 | 7 | |
| GUI Agent | AndroidControl | Type85.25 | 7 | |
| GUI Action Step Prediction | AndroidControl (test) | Step Accuracy (High)50 | 7 | |
| GUI reasoning | AndroidControl High | Type65.91 | 4 | |
| GUI reasoning | AndroidControl Low | Type82.29 | 4 | |
| GUI Navigation | AndroidControl Low | Step Accuracy87.6 | 4 | |
| GUI Navigation | AndroidControl High | Action Matching Score (AMS)68.1 | 4 | |
| UI Control | AndroidControl | Success Rate57.3 | 2 |