Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

GUI-360

Benchmarks

Task NameDataset NameSOTA ResultTrend
Tool SelectionGUI-360° (test)
Top-1 Accuracy61.9
2
Agent-team recommendationGUI-360 (test)
Retrieval Success (Top-10)83.5
2
Showing 2 of 2 rows