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

Software Engineering

Benchmarks

Task NameDataset NameSOTA ResultTrend
Vulnerability PredictionSoftware Engineering (SE)
Spearman rho0.65
10
Backdoor attack evaluationSoftware Engineering
ASR95
8
Task Performance EvaluationSoftware Engineering
Average Score87.5
5
Software EngineeringSoftware Engineering
Functional Correctness0.335
2
Showing 4 of 4 rows