GUI Interaction on OSW-G
0.672AccuracyGROUNDNEXT-7B (SFT)
Evaluation Results
| Method | Links | |
|---|---|---|
| GROUNDNEXT-7B (SFT)Model Scale=7B, Training Paradigm=SFT2025.11 | 0.672 | |
| GROUNDNEXT-3B (SFT)Model Scale=3B, Training Paradigm=SFT2025.11 | 0.622 | |
| JEDI-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 0.541 | |
| PhiGround-4B-7CModel Scale=4B, Training Paradigm=SFT2025.11 | 0.514 | |
| JEDI-3BModel Scale=3B, Training Paradigm=SFT2025.11 | 0.509 | |
| GUI-Actor-3BModel Scale=3B, Training Paradigm=SFT2025.11 | 0.489 | |
| GUI-Actor-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 0.47 | |
| Qwen2.5-VL-7B (Agent mode)Model Scale=7B, Evaluation Mode=Agent mode, Training Paradigm=SFT2025.11 | 0.427 | |
| Aguvis-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 0.387 | |
| Qwen2.5-VL-3B (Agent mode)Model Scale=3B, Evaluation Mode=Agent mode, Training Paradigm=SFT2025.11 | 0.374 | |
| UGround-V1-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 0.364 | |
| Qwen2.5-VL-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 0.314 | |
| OS-Atlas-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 0.277 | |
| Qwen2.5-VL-3BModel Scale=3B, Training Paradigm=SFT2025.11 | 0.273 |