Continual GUI Agents
Open paper
Benchmark
Model
Rank
Results
natural-language-visual-grounding-on-screenspot
GUI-AiF (Qwen2.5VL-3B)
#20
Accuracy (%): 78.9
computer-use-agents-on-screenspot-v2
GUI-AiF (Qwen2.5VL-3B)
#46
Accuracy: 81.2
Rank counts only results with a code link.