The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Centre for AI Safety – Blog(Global) 9 May 2026 58

A credible technical benchmark for measuring WMD-relevant AI knowledge gaps gives Australian AI safety and biosecurity policy teams a concrete evaluation reference.

  • CAIS releases WMDP, a 4,157-question benchmark measuring hazardous AI knowledge in biosecurity, cybersecurity, and chemical security.
  • Accompanying 'CUT' unlearning method removes hazardous knowledge from LLMs while preserving general capabilities, resisting jailbreaking.
  • Benchmark and method are research outputs; no direct Australian regulatory mandate is attached to their adoption.
  • Monitor Australia's AISI and DISR may want to monitor WMDP's uptake as an industry evaluation standard for frontier model pre-deployment safety assessments.
  • Consider Agencies involved in AI procurement or frontier model governance could consider whether WMDP-style hazardous knowledge benchmarks could inform vendor assurance requirements or risk assessment criteria.

Implications are AI-generated. Starting points, not advice — see methodology for how they're framed.

View original source