Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Output OOD Detection on Newsroom
Loading...
99.73
AUROC
AP-OOD
50.9852
63.6401
76.295
88.9499
Feb 5, 2026
AUROC
FPR95
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
FPR95
AP-OOD
Backbone=PEGASUS_LARGE...
2026.02
99.73
0.97
Binary logits
Backbone=PEGASUS_LARGE...
2026.02
99.45
1.87
Deep SAD
Backbone=PEGASUS_LARGE...
2026.02
99.4
1.9
Relative Mahalanobis
Backbone=PEGASUS_LARGE...
2026.02
97.38
8.68
AP-OOD
Backbone=PEGASUS-LARGE...
2026.02
94.41
28.18
Deep SVDD
Backbone=PEGASUS-LARGE...
2026.02
93.47
20.67
Mahalanobis
Backbone=PEGASUS-LARGE...
2026.02
87.38
49.06
KNN
Backbone=PEGASUS-LARGE...
2026.02
86.69
54.3
Entropy
Backbone=PEGASUS-LARGE...
2026.02
76.92
64.65
Perplexity
Backbone=PEGASUS-LARGE...
2026.02
52.86
79.4
Feedback
Search any
task
Search any
task