GUI Grounding on SSPro
50.2AccuracyGROUNDNEXT-7B (SFT)
Evaluation results
| Method | Links | |
|---|---|---|
| GROUNDNEXT-7B (SFT)Model Scale=7B, Training Paradigm=SFT2025.11 | 50.2 | |
| GROUNDNEXT-3B (SFT)Model Scale=3B, Training Paradigm=SFT2025.11 | 48.6 | |
| GUI-Actor-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 44.6 | |
| GUI-Actor-3BModel Scale=3B, Training Paradigm=SFT2025.11 | 42.2 | |
| Aguvis-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 39.5 | |
| JEDI-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 39.5 | |
| JEDI-3BModel Scale=3B, Training Paradigm=SFT2025.11 | 36.1 | |
| Qwen2.5-VL-7B (Agent mode)Model Scale=7B, Evaluation Mode=Agent mode, Training Paradigm=SFT2025.11 | 29.7 | |
| Qwen2.5-VL-3B (Agent mode)Model Scale=3B, Evaluation Mode=Agent mode, Training Paradigm=SFT2025.11 | 29 | |
| Qwen2.5-VL-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 26.8 | |
| PhiGround-4B-7CModel Scale=4B, Training Paradigm=SFT2025.11 | 22.8 | |
| OS-Atlas-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 18.9 | |
| UGround-V1-7BModel Scale=7B, Training Paradigm=SFT2025.11 | 16.5 | |
| Qwen2.5-VL-3BModel Scale=3B, Training Paradigm=SFT2025.11 | 16.1 |