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

Complex

Benchmarks

Task NameDataset NameSOTA ResultTrend
Image StylingComplex
Overall Score85.41
16
NavigationComplex
Success Rate4,010
16
Active perception handoffComplex
Search Success Rate78.2
12
Decomposed CASHComplex Budget 2/3
Loss0.2792
10
Decomposed CASHComplex Budget 3/3
Loss0.2975
5
Decomposed CASHComplex Budget 1 3
Loss0.3643
5
Showing 6 of 6 rows