Android In The Wild
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mobile Automation | Android In The Wild (AITW) | Average Score7.7 | 21 | |
| Multimodal GUI-agent action execution | Android in the Wild (AITW) held-out 500-example (test) | AITW Accuracy6.6 | 3 |
Showing 2 of 2 rows