Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Unsupervised OOD detection on The Pile ID MIMIC-III Clinical OOD (test)
Loading...
86.44
AUROC
AP-OOD
72.92
76.43
79.94
83.45
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
86.44
57.38
Perplexity
Base Model=Pythia-160M...
2026.02
85.86
65.22
Mahalanobis
Base Model=Pythia-160M...
2026.02
75.67
90.79
KNN
Base Model=Pythia-160M...
2026.02
75.56
95.85
Deep SVDD
Base Model=Pythia-160M...
2026.02
73.44
96.35
Feedback
Search any
task
Search any
task