Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Confidence Estimation on DDXPlus
Loading...
0.795
AUROC
MedConf
0.58492
0.63946
0.694
0.74854
Jan 22, 2026
AUROC
Pearson Correlation
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
Pearson Correlation
MedConf
Backbone=GPT-4.1, Type...
2026.01
0.795
0.936
MedConf
Model=Llama-3.1, Type=...
2026.01
0.722
0.968
CE
Backbone=GPT-4.1, Type...
2026.01
0.682
0.989
CE
Model=Llama-3.1, Type=...
2026.01
0.67
0.87
SemSim (BERT)
Model=Llama-3.1, Type=...
2026.01
0.652
0.733
SemSim (BERT)
Backbone=GPT-4.1, Type...
2026.01
0.622
0.785
PMI
Model=Llama-3.1, Type=...
2026.01
0.593
0.829
Feedback
Search any
task
Search any
task