RapidResponseBench

Evals

Benchmark / dataset

Can defenses adapt quickly after seeing a few jailbreaks?

Category
Jailbreak & misuse
Insurance exposure
Regulatory/bias
Publisher
Anthropic + academic (MATS)
Publisher type
Academic
License
unknown
Status
Stale (>12mo)
Last commit
2024-11-12
Stars
35

View source on GitHub →


Wanich Risk Lab, 2026.