Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Unsupervised OOD detection on The Pile ID 4Chan OOD (test)
Loading...
87.97
AUROC
AP-OOD
33.162
47.391
61.62
75.849
Feb 5, 2026
AUROC
FPR95
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
FPR95
AP-OOD
Base Model=Pythia-160M...
2026.02
87.97
88.34
Perplexity
Base Model=Pythia-160M...
2026.02
65.05
72.66
Deep SVDD
Base Model=Pythia-160M...
2026.02
55.59
88.15
KNN
Base Model=Pythia-160M...
2026.02
39.31
98.85
Mahalanobis
Base Model=Pythia-160M...
2026.02
35.27
92.93
Feedback
Search any
task
Search any
task