Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Classification on AGNews (Uncertainty Metrics)
Loading...
0.3786
N-ER
GPT-2
0.36256
0.47083
0.5791
0.68737
May 19, 2026
N-ER
ECE
AUC
N-CEqe
N-BSqe
N-CEq
N-BSq
AURC
N-ECUASn (n=0)
N-ECUASn (n=1)
N-ECUASn (n=128)
Updated 12d ago
Evaluation Results
Method
Method
Links
N-ER
ECE
AUC
N-CEqe
N-BSqe
N-CEq
N-BSq
AURC
N-ECUASn (n=0)
N-ECUASn (n=1)
N-ECUASn (n=128)
GPT-2
Score=cal
2026.05
0.3786
0.0362
0.7001
0.9325
1.8136
0.5353
0.5414
0.1724
0.7111
0.5802
0.3816
GPT-2
Score=raw
2026.05
0.7796
0.1844
0.6431
1.0539
2.1339
0.8138
0.8894
0.4352
1.0045
0.9803
0.7857
Feedback
Search any
task
Search any
task