Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Near-OOD Detection on CLINC150
Loading...
86.61
AUROC
Gemma2-2b LR baseline
73.3604
76.8002
80.24
83.6798
May 12, 2026
AUROC
AUPR (OOD)
FPR95
Updated 21d ago
Evaluation Results
Method
Method
Links
AUROC
AUPR (OOD)
FPR95
Gemma2-2b LR baseline
Backbone=Gemma2-2b, De...
2026.05
86.61
64.49
56.07
Gemma2-9b LR baseline
Backbone=Gemma2-9b, De...
2026.05
84.94
62.96
64.4
Gemma2-9b + 16k SAE + Markov
Backbone=Gemma2-9b, SA...
2026.05
83.64
72.78
48.25
Gemma2-2b + 16k SAE + Markov
Backbone=Gemma2-2b, SA...
2026.05
73.87
1.27
83.33
Feedback
Search any
task
Search any
task