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

Code Correctness Prediction on LiveCodeBench Python (AUROC)

86.7AUROC

Func. Equiv.

Updated 6d ago

Evaluation Results

Method	Links
Func. Equiv. 2026.05		86.7
Func. Equiv. 2026.05		85.9
Func. Equiv. 2026.05		85.9
Func. Entropy 2026.05		85.9
Func. Entropy 2026.05		85.7
Func. Entropy 2026.05		85.7
Func. Equiv. 2026.05		85.6
Func. Sets 2026.05		85.6
Func. Entropy 2026.05		85.5
Func. Sets 2026.05		85.5
Func. Sets 2026.05		85.5
Func. Sets 2026.05		85.2
P(True) 2026.05		83
Func. Entropy 2026.05		82.9
Func. Equiv. 2026.05		82.6
Func. Sets 2026.05		82.6
P(True) 2026.05		82.4
P(True) 2026.05		81.5
CodeBLEU 2026.05		81.3
Cos. Sim. 2026.05		80.4
Min. Tok. Neg. 2026.05		79.7
CodeBLEU 2026.05		79.5
CodeBLEU 2026.05		79.5
Verb. Conf. 2026.05		79.5
Min. Prob. 2026.05		78.3
Min. Tok. Neg. 2026.05		77.9
Avg. Tok. Neg. 2026.05		77.6
Avg. Tok. Neg. 2026.05		77.4
Min. Prob. 2026.05		77.3
P(True) 2026.05		77.1
Min. Tok. Neg. 2026.05		77
Min. Tok. Neg. 2026.05		76.8
Min. Tok. Neg. 2026.05		76.6
CodeBLEU 2026.05		76.6
Min. Prob. 2026.05		76.2
Prob. Margin 2026.05		76.2
Seq. Prob. 2026.05		76.1
Avg. Tok. Neg. 2026.05		76
Seq. Prob. 2026.05		75.7
Cos. Sim. 2026.05		75.6
Cos. Sim. 2026.05		75.3
Prob. Margin 2026.05		75.2
P(True) 2026.05		75.2
Prob. Margin 2026.05		74.9
CodeBLEU 2026.05		74.4
Min. Prob. 2026.05		73.8
Cos. Sim. 2026.05		73.8
Seq. Prob. 2026.05		72.9
Verb. Conf. 2026.05		72.5
Cos. Sim. 2026.05		72.4
Verb. Conf. 2026.05		71.6
Min. Prob. 2026.05		70.5
Avg. Tok. Neg. 2026.05		69.5
Seq. Prob. 2026.05		69.1
Verb. Conf. 2026.05		68.1
Prob. Margin 2026.05		66.8
Verb. Conf. 2026.05		59.7
Avg. Tok. Neg. 2026.05		58.2
Seq. Prob. 2026.05		58
Prob. Margin 2026.05		55.4