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

ContinualBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
window-closeContinualBench window-close
Success Rate72.6
9
door-openContinualBench door-open
Success Rate73.5
9
button-pressContinualBench button-press
Success Rate98.8
9
Showing 3 of 3 rows