Safety & factuality

HarmBench

by Center for AI Safety & collaborators

Editor note

A standard framework for red-teaming: it tests how easily attacks can make a model produce harmful content and how well defences hold.

What it tests
Robustness to jailbreaks and harmful requests.
Original source
www.harmbench.org/
Last updated
Not checked yet
License
Not checked yet — see source

Facts come only from the linked source (checked 15 Oct 2026). Credit belongs to the creators.

Reviews

No reviews yet.

Reviews from practitioners who sign in with GitHub open soon.