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

Code Correctness Prediction on MultiPL-E Java (AUROC)

0.705AUROC

Min. Prob.

Updated 6d ago

Evaluation Results

Method	Links
Min. Prob. 2026.05		0.705
Func. Entropy 2026.05		0.701
Func. Sets 2026.05		0.697
Func. Entropy 2026.05		0.695
Func. Sets 2026.05		0.693
Func. Sets 2026.05		0.691
Func. Equiv. 2026.05		0.69
CodeBLEU 2026.05		0.69
Func. Equiv. 2026.05		0.687
P(True) 2026.05		0.687
Func. Entropy 2026.05		0.686
Func. Equiv. 2026.05		0.681
CodeBLEU 2026.05		0.676
Min. Tok. Neg. 2026.05		0.674
CodeBLEU 2026.05		0.672
Func. Equiv. 2026.05		0.665
Func. Sets 2026.05		0.663
Func. Entropy 2026.05		0.662
CodeBLEU 2026.05		0.662
CodeBLEU 2026.05		0.658
Min. Tok. Neg. 2026.05		0.653
Min. Tok. Neg. 2026.05		0.652
Min. Prob. 2026.05		0.647
Cos. Sim. 2026.05		0.645
Avg. Tok. Neg. 2026.05		0.644
Min. Tok. Neg. 2026.05		0.644
Prob. Margin 2026.05		0.64
P(True) 2026.05		0.64
Seq. Prob. 2026.05		0.638
Seq. Prob. 2026.05		0.637
Min. Prob. 2026.05		0.635
Min. Tok. Neg. 2026.05		0.632
Func. Entropy 2026.05		0.628
Cos. Sim. 2026.05		0.627
Cos. Sim. 2026.05		0.626
Func. Sets 2026.05		0.623
Verb. Conf. 2026.05		0.623
Min. Prob. 2026.05		0.618
Func. Equiv. 2026.05		0.616
P(True) 2026.05		0.616
Cos. Sim. 2026.05		0.615
Verb. Conf. 2026.05		0.615
Cos. Sim. 2026.05		0.61
Prob. Margin 2026.05		0.601
Min. Prob. 2026.05		0.599
Avg. Tok. Neg. 2026.05		0.598
Prob. Margin 2026.05		0.596
Verb. Conf. 2026.05		0.595
Verb. Conf. 2026.05		0.592
Avg. Tok. Neg. 2026.05		0.589
Seq. Prob. 2026.05		0.588
Seq. Prob. 2026.05		0.572
Prob. Margin 2026.05		0.553
Seq. Prob. 2026.05		0.551
Avg. Tok. Neg. 2026.05		0.551
Verb. Conf. 2026.05		0.548
P(True) 2026.05		0.548
Avg. Tok. Neg. 2026.05		0.536
P(True) 2026.05		0.529
Prob. Margin 2026.05		0.525