UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning
Open paper
Benchmark
Model
Rank
Results
natural-language-visual-grounding-on-screenspot
UI-R1-E-3B
#8
Accuracy (%): 89.2
computer-use-agents-on-screenspot-v2
UI-R1-E-3B
#37
Accuracy: 89.5
computer-use-agents-on-screenspot-pro
UI-R1-E-3B
#45
Accuracy: 33.5
Rank counts only results with a code link.