OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution
Open paper
Benchmark
Model
Rank
Results
computer-use-agents-on-androidworld
OmegaUse
–
Success Rate: 55.7
computer-use-agents-on-screenspot-pro
OmegaUse-G
–
Accuracy: 55.47
computer-use-agents-on-screenspot-v2
OmegaUse-G
–
Accuracy: 96.3
Rank counts only results with a code link.