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

XBOW

Benchmarks

Task NameDataset NameSOTA ResultTrend
Web security task completionXBOW 104 tasks
Task Completion Rate91
32
Automated Penetration TestingXBOW (Overall)
Solved Count43
4
Automated Penetration TestingXBOW Level 3 (Hard)
Solved Count3
4
Automated Penetration TestingXBOW Level 2 (Medium)
Solved Count19
4
Automated Penetration TestingXBOW Level 1 (Easy)
Solved Count21
4
Vulnerability ExploitationXBOW (full)
Total Cost7.73
2
Showing 6 of 6 rows