Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Selective Answering on HotpotQA RAG v3
Loading...
0.1642
Risk@30
SURE-RAG
0.158036
0.199643
0.24125
0.282857
May 5, 2026
Risk@30
Risk@50
Risk@70
Updated 2mo ago
Evaluation Results
Method
Method
Links
Risk@30
Risk@50
Risk@70
SURE-RAG
Calibration=Standard
2026.05
0.1642
0.36
0.5457
SURE-RAG
Calibration=Calibrated
2026.05
0.167
0.351
0.5493
DeBERTa
Pooling=mean-pool
2026.05
0.2588
0.3783
0.535
DeBERTa
Pooling=max-pool
2026.05
0.3183
0.4054
0.5344
Feedback
Search any
task
Search any
task
