Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Selective Classification on Amazon Reviews (In-Distribution)
Loading...
20.6
AURC
MDS
11.552
13.901
16.25
18.599
May 21, 2025
AURC
NAURC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AURC
NAURC
MDS
Backbone=DistilBERT, T...
2025.05
20.6
73.9
KNN
Backbone=DistilBERT, T...
2025.05
19.4
68.6
Energy
Backbone=DistilBERT, T...
2025.05
12.89
39.7
Δ-MDS
Backbone=DistilBERT, T...
2025.05
12.7
38.9
MaxLogit
Backbone=DistilBERT, T...
2025.05
12.6
38.4
RLog
Backbone=DistilBERT, T...
2025.05
12.4
37.6
Δ-KNN
Backbone=DistilBERT, T...
2025.05
12.4
37.4
SIRC
Backbone=DistilBERT, T...
2025.05
12.3
37
MSP
Backbone=DistilBERT, T...
2025.05
12.2
36.8
Δ-MDS-RLog
Backbone=DistilBERT, T...
2025.05
12.2
36.8
Δ-KNN-RLog
Backbone=DistilBERT, T...
2025.05
12
35.8
Δ-KNN-MSP
Backbone=DistilBERT, T...
2025.05
12
35.9
Δ-MDS-MSP
Backbone=DistilBERT, T...
2025.05
11.9
35.4
Feedback
Search any
task
Search any
task
