Jailbreakbench is an open-source robustness benchmark for jailbreaking large language models (LLMs). The goal of this benchmark is to comprehensively track progress toward (1) generating successful ...
Version 1.1.0 introduces a revolutionary plugin-based architecture with component registration and rigid compile-time type safety: ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results