Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Unsupervised OOD detection on The Pile EDGAR Reports ID OOD (test)
Loading...
68.09
AUROC
AP-OOD
47.5292
52.8671
58.205
63.5429
Feb 5, 2026
AUROC
FPR@95
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
FPR@95
AP-OOD
Base Model=Pythia-160M...
2026.02
68.09
91.47
Deep SVDD
Base Model=Pythia-160M...
2026.02
64.06
88.94
KNN
Base Model=Pythia-160M...
2026.02
59.41
93.26
Mahalanobis
Base Model=Pythia-160M...
2026.02
54.72
87.77
Perplexity
Base Model=Pythia-160M...
2026.02
48.32
86.91
Feedback
Search any
task
Search any
task