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

Original

Benchmarks

Task NameDataset NameSOTA ResultTrend
Self-doubt detectionOriginal Source Datasets
Self-Doubt AUROC84.06
7
Multi-class ClassificationOriginal (test)
Accuracy (0-shot)73.4
6
ClusteringOriginal (test)
KM84.6
6
Stroke ClassificationOriginal (test)
AUC92.5
4
Triplet (Ori-Imp)Original (test)
Thard17.8
3
Triplet (Ori-Ori)Original (test)
Thard46.9
3
Solar Flare PredictionOriginal (test)
TSS63.3
1
Showing 7 of 7 rows