Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
Open paper
Benchmark
Model
Rank
Results
natural-language-visual-grounding-on
UGround-V1-7B
#1
Accuracy (%): 86.34
natural-language-visual-grounding-on
UGround-V1-2B
#6
Accuracy (%): 77.67
natural-language-visual-grounding-on
UGround
#9
Accuracy (%): 73.3
Rank counts only results with a code link.