Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Uncertainty Estimation on Across-dataset Off-diagonal
Loading...
2.86
AUPRC Difference (pp)
Signatures
0.8736
1.3893
1.905
2.4207
Mar 17, 2026
AUPRC Difference (pp)
Brier Score Difference (pp)
Updated 24d ago
Evaluation Results
Method
Method
Links
AUPRC Difference (pp)
Brier Score Difference (pp)
Signatures
Model=Llama-3.1-8B
2026.03
2.86
21.02
Signatures
Model=Mistral-7B-v0.3
2026.03
1.35
4.28
Signatures
Model=Qwen3-14B
2026.03
0.95
4.35
Feedback
Search any
task
Search any
task