← all datasets

WMDP

Emerging
2papers using it
22,924HF downloads
28HF likes
2025first seen

Dataset Card for WMDP The Weapons of Mass Destruction Proxy (WMDP) benchmark is a dataset of multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. WMDP serves two roles: first, as an evaluation for hazardous knowledge in LLMs, and second

Papers using WMDP (2)

WMDP β€” datasets β€” cybersecurity