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

Vulnerability Exploitation on CVEBench One-Day

26.1Pass@1

Seed Agent

15.38818.16920.9523.731May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
26.134.537.5------
2026.05
16.924.827.5------
2026.05
16.824.227.5------
2026.05
15.824.630------
2026.05
---20-7.5----
2026.05
-----32.55--
2026.05
-------12.5-
2026.05
--------20
2026.05
---35-2.5----
2026.05
-----457.5--
2026.05
-------30-
2026.05
--------37.5
2026.05
---22.5-7.5----
2026.05
-----4010--
2026.05
-------25-
2026.05
--------32.5
2026.05
---22.5-5----
2026.05
-----32.55--
2026.05
-------20-
2026.05
--------22.5