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

CWEval

Benchmarks

Task NameDataset NameSOTA ResultTrend
Secure Code GenerationCWEval
pass@148.2
29
Secure Code GenerationCWEval
Functionality92.27
22
Vulnerability injectionCWEval Python
Attack Success Rate (ASR)66.67
14
Showing 3 of 3 rows