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

DA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Affine-invariant depth estimationDA-2K
Accuracy97.1
16
Certainty Equivalent EstimationDA non-mixed prospects 1992
Median Certainty Equivalent (p=0.1)59
13
Entity MatchingDA (test)
F1 Score98.4
13
Dialogue AnalysisDA
R Metric92.5
10
3D Spatial understandingDA-2K
Pass@191.9
7
Showing 5 of 5 rows