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 jailbreaks and (2) defending against these jailbreaks. To this end, we provide the JBB-Behaviors dataset, which comprises a list of 200 distinct benign and misuse behaviors---both original and sourced from prior work (in particular, Trojan Detection Challenge/HarmBench and AdvBench)---which were curated with reference to OpenAI's usage policies.
from the project README
Formats
json
License
MIT
Added
2026-09-10
Get it
From the project’s own instructions where it documents any; otherwise a plain clone.
shell
$ pip install jailbreakbench
Then jbb.read_dataset() in Python loads the JBB-Behaviors dataset.
Contents
50 files2.8 MB repository
.py34
.yml3
.jpg2
.json2
.md2
(no ext)2
.png2
.bib1
Use it with
Commands are curated, not yet run by us.
jq — Stream the records one per line to see their shape.
sample.json
$ jq -c . sample.json
DuckDB — Query the file in place with SQL — DuckDB detects CSV, JSON and JSONL by extension.
sample.json
$ duckdb -c 'SELECT * FROM '\''sample.json'\'' LIMIT 10'