| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| GUI Grounding | ScreenSpot Pro | Average Score7,350 | 307 | |
| GUI Grounding | ScreenSpot v2 | Avg Accuracy96.5 | 283 | |
| GUI Grounding | ScreenSpot Pro | Accuracy72.7 | 163 | |
| GUI Grounding | ScreenSpot | Avg Acc91 | 133 | |
| GUI Grounding | ScreenSpot Web V2 | Text Accuracy97.9 | 55 | |
| GUI Grounding | ScreenSpot Desktop V2 | Text Accuracy100 | 55 | |
| GUI Grounding | ScreenSpot Mobile V2 | Text Accuracy100 | 55 | |
| GUI Grounding | ScreenSpot-Pro (test) | Element Accuracy58.66 | 43 | |
| GUI Grounding | ScreenSpot (test) | Element Accuracy90.6 | 42 | |
| GUI Grounding | Screenspot v1 | Average Accuracy91.67 | 39 | |
| Grounding | ScreenSpot Pro | Average Grounding Accuracy48.7 | 33 | |
| Grounding | ScreenSpot V2 | Accuracy96.5 | 32 | |
| Grounding | ScreenSpot v2 (test) | Overall Accuracy95.3 | 29 | |
| Visual Grounding | ScreenSpot-Pro 1.0 (test) | Development Score71.6 | 27 | |
| UI Element Grounding | ScreenSpot Overall v2 | Overall Accuracy (Avg)95.2 | 26 | |
| GUI Grounding | ScreenSpot v1 (test) | Mobile Text Acc98.6 | 25 | |
| GUI Element Injection Attack Success | ScreenSpot Pro (885-sample split) | Attack Success Rate (ASR)100 | 24 | |
| GUI Interaction | ScreenSpot V1 | Avg Acc92 | 23 | |
| GUI Visual Grounding | ScreenSpot Standard Setting 1.0 | Accuracy (Mobile, Text)94.1 | 15 | |
| UI Element Grounding | ScreenSpot Overall v2 (Aggregated) | Average Grounding Accuracy92.1 | 14 | |
| GUI Action Grounding | ScreenSpot-Pro (test) | Accuracy (Development)40.8 | 14 | |
| Web UI Localization | Screenspot V2 | Center Accuracy82.9 | 14 | |
| Screen Grounding | ScreenSpot v1 (test) | Accuracy (Desktop, Text)95.4 | 13 | |
| Grounding | ScreenSpot-Pro macOS | Grounding Accuracy41.39 | 13 | |
| Element Grounding | ScreenSpot v2 (test) | Grounding Accuracy88 | 13 |