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

OpenHands

Benchmarks

Task NameDataset NameSOTA ResultTrend
Failure predictionOpenHands Transfer (held-out)
ROC-AUC69.5
4
Failure predictionOpenHands (Within corpus)
ROC-AUC69.7
4
Leave-one-corpus-out transferOpenHands
AUC0.699
3
Showing 3 of 3 rows