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

Penetration Testing on AutoPenBench

52.5Pass@1

Seed Agent

11.83622.39332.9543.507May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
52.560.360.6------
2026.05
34.450.351.5------
2026.05
29.441.242.4------
2026.05
13.422.924.3------
2026.05
---36.4-15.1----
2026.05
-----60.69.1--
2026.05
-------36.4-
2026.05
--------33.3
2026.05
---45.5-15.1----
2026.05
-----72.712.1--
2026.05
-------42.4-
2026.05
--------39.4
2026.05
---36.4-6----
2026.05
-----66.724.3--
2026.05
-------27.3-
2026.05
--------33.3
2026.05
---36.412.1----
2026.05
-----63.639.3--
2026.05
-------27.3-
2026.05
--------12.1