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

WebGenBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Vulnerability Attack AnalysisWebGenBench Dashboards target-domain and cross-domain 1.0
ASR (CodeQL)100
12
Vulnerability Attack AnalysisWebGenBench Blogging target-domain and cross-domain 1.0
ASR (CodeQL)100
12
Vulnerability Attack AnalysisWebGenBench Social Media target-domain and cross-domain 1.0
ASR (CodeQL)80.65
12
Vulnerability Attack AnalysisWebGenBench Internal Tools target-domain and cross-domain 1.0
ASR (CodeQL)90
12
Vulnerability Attack AnalysisWebGenBench E-commerce target-domain and cross-domain 1.0
Attack Success Rate (CodeQL)100
12
Showing 5 of 5 rows