Original
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Original Source Datasets
84.06Self-Doubt AUROC
7
Original (test)
73.4Accuracy (0-shot)
6
Original (test)
84.6KM
6
Original (test)
92.5AUC
4
Original (test)
17.8Thard
3
Original (test)
46.9Thard
3
Original (test)
63.3TSS
1