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

Controlled

Benchmarks

Task NameDataset NameSOTA ResultTrend
Drift detectionControlled (post-cutoff)
AUROC0.95
91
Classificationcontrolled 784-feature benchmark (test)
Test Accuracy (%)92.6
40
Showing 2 of 2 rows