Dev Radar
Support
LiveUpdated 2026-09-20 19:24 UTC

exploitgym

exploitgym — ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities…

exploitgym is ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits. - sunblaze-ucb/exploitgym. It is ranked #1129 on the Dev Radar, in Security, first seen 5 h ago and shared in 1 post (47 views).

Visit github.com

GitHub - sunblaze-ucb/exploitgym: ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} sunblaze-ucb / exploitgym Public Notifications You must be signed in to change notification…

What people said about exploitgym on X

They will lie to the world until they get the resources to ensure their prophecies of doom are self-fulfilled. "Under those actual prompts, none of the OpenAI agents’ behaviors as described by @METR_Evals is (a) cheating, or (b) disqualifying."

@retserofer, 5 h ago · 1 likes · see the post

Alternatives to exploitgym

exploitgym in numbers

FAQ

What is exploitgym?

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits. - sunblaze-ucb/exploitgym It was first shared on X 5 h ago and is ranked #1129 on the Dev Radar.

Is exploitgym free?

It is open source.

Who shared exploitgym?

1 account on X, including @retserofer, in 1 post totalling 47 views.

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 16.1k posts from 4.9k X accounts over the last 21 days, 1.8k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 19:24 UTC. Full method.