Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
GUI Interaction on OSW-G
Loading...
0.672
Accuracy
GROUNDNEXT-7B (SFT)
0.25704
0.36477
0.4725
0.58023
Nov 10, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
GROUNDNEXT-7B (SFT)
Model Scale=7B, Traini...
2025.11
0.672
GROUNDNEXT-3B (SFT)
Model Scale=3B, Traini...
2025.11
0.622
JEDI-7B
Model Scale=7B, Traini...
2025.11
0.541
PhiGround-4B-7C
Model Scale=4B, Traini...
2025.11
0.514
JEDI-3B
Model Scale=3B, Traini...
2025.11
0.509
GUI-Actor-3B
Model Scale=3B, Traini...
2025.11
0.489
GUI-Actor-7B
Model Scale=7B, Traini...
2025.11
0.47
Qwen2.5-VL-7B (Agent mode)
Model Scale=7B, Evalua...
2025.11
0.427
Aguvis-7B
Model Scale=7B, Traini...
2025.11
0.387
Qwen2.5-VL-3B (Agent mode)
Model Scale=3B, Evalua...
2025.11
0.374
UGround-V1-7B
Model Scale=7B, Traini...
2025.11
0.364
Qwen2.5-VL-7B
Model Scale=7B, Traini...
2025.11
0.314
OS-Atlas-7B
Model Scale=7B, Traini...
2025.11
0.277
Qwen2.5-VL-3B
Model Scale=3B, Traini...
2025.11
0.273
Feedback
Search any
task
Search any
task