WMDP-Bio (SecureBio)
Science
SecureBio's own runs of WMDP-Bio. These are the same 1,273 four-option questions as wmdp-bio under a different protocol. Evaluated in Inspect with zero-shot prompting, usually over 10 runs. SecureBio doesn't state how refusals enter accuracy. Claude Opus 4.7 prints 92.5% with 75.4% refused, more than it could score if refusals counted as wrong, so accuracy appears to cover answered questions only and each model's denominator differs. These scores aren't comparable with other runs of the test, which is why this is a diagnostic.
Benchmark source: Securebio