Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Selective Prediction on CommonsenseQA

0.9999Power

UCB-CLP

0.9989640.9992070.999450.999693Dec 1, 2025
Updated 5d ago

Evaluation Results

MethodLinks
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.9999
2025.12
0.999
Showing 100 of 207 rows