Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Output OOD Detection on Samsum
Loading...
99.99
AUROC
AP-OOD
77.0164
82.9807
88.945
94.9093
Feb 5, 2026
AUROC
FPR@95
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
FPR@95
AP-OOD
Backbone=PEGASUS_LARGE...
2026.02
99.99
0
Binary logits
Backbone=PEGASUS_LARGE...
2026.02
99.95
4
Deep SAD
Backbone=PEGASUS_LARGE...
2026.02
99.95
8
Relative Mahalanobis
Backbone=PEGASUS_LARGE...
2026.02
99.52
95
AP-OOD
Backbone=PEGASUS-LARGE...
2026.02
98.89
4.09
KNN
Backbone=PEGASUS-LARGE...
2026.02
97.28
10.99
Mahalanobis
Backbone=PEGASUS-LARGE...
2026.02
96.99
15.25
Deep SVDD
Backbone=PEGASUS-LARGE...
2026.02
95.61
21.66
Entropy
Backbone=PEGASUS-LARGE...
2026.02
87.07
50.83
Perplexity
Backbone=PEGASUS-LARGE...
2026.02
77.9
47.35
Feedback
Search any
task
Search any
task