GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction

Open paper
Benchmark Model Rank Results
natural-language-visual-grounding-on-screenspotGoClick-L (0.8B)#21Accuracy (%): 78.5
computer-use-agents-on-screenspot-v2GoClick-L (0.8B)#47Accuracy: 81.1

Rank counts only results with a code link.