JailbreakBench — leaderboard

Open robustness benchmark for LLM jailbreaking with a curated behavior dataset, standardized threat model, scoring functions, attack artifacts, and a public attack/defense leaderboard.

Source: github.com.

Interactive version: theaggregate.ai/benchmark?slug=jailbreakbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.