| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| GUI Agent Task | AndroidWorld | Success Rate80 | 200 | |
| Mobile Task Automation | AndroidWorld (test) | Average Success Rate1 | 119 | |
| GUI Agent | AndroidWorld | Accuracy62 | 70 | |
| Mobile GUI Automation | AndroidWorld | Overall Success Rate76.9 | 68 | |
| GUI navigation | AndroidWorld latest (test) | Success Rate78.9 | 48 | |
| Mobile UI Control | AndroidWorld | Overall Task Success Rate71.6 | 45 | |
| Mobile GUI Agent Decision Making | AndroidWorld | Success Rate82.05 | 27 | |
| GUI Agent Task Success | AndroidWorld (online) | Task Success Rate48.7 | 25 | |
| End-to-end GUI Navigation | AndroidWorld | Success Rate77.6 | 25 | |
| Android GUI Automation | AndroidWorld M | L1 Score53.8 | 22 | |
| Agentic Reasoning | AndroidWorld | Success Rate82.05 | 20 | |
| Mobile GUI Agents | AndroidWorld 138 tasks (test) | Success Rate71.1 | 18 | |
| Mobile UI Task Automation | AndroidWorld (full) | Success Rate (Easy)82.79 | 16 | |
| Mobile Agent Decision-making | AndroidWorld (Evaluation set 116 templates) | Average Success Rate (SR)62.9 | 16 | |
| GUI Task Completion | AndroidWorld | Success Rate (SR)57.8 | 15 | |
| Reward Modeling | AndroidWorld | Precision92.5 | 14 | |
| End-to-End Environment Interaction | AndroidWorld (test) | Pass@180.2 | 14 | |
| Mobile agent task completion | AndroidWorld 116 tasks | Task Success Rate (TSR)75 | 10 | |
| Online Reinforcement Learning | AndroidWorld | Success Rate62.28 | 9 | |
| Agentic Phone Use | AndroidWorld | Task Success Rate83.2 | 7 | |
| GUI Agent Automation | AndroidWorld (AW) (Online) | Success Rate25.1 | 6 | |
| Safe Navigation | AndroidWorld core20 safe general tasks | Success Count (out of 20)11 | 4 | |
| Mobile Use | AndroidWorld | Score70.7 | 4 | |
| Mobile operating system task execution | AndroidWorld (AW) | AUV43.2 | 4 | |
| Action Success Prediction | AndroidWorld (smallest held-out split) | Precision87.1 | 3 |