VCT text-only (SecureBio)
Science
SecureBio's own runs of the 101 text-only questions of the Virology Capabilities Test, for models that can't process images. Evaluated in Inspect with zero-shot prompting, usually over 10 runs. SecureBio doesn't state how refusals enter accuracy. Claude Sonnet 4.5 prints 46.1% with 58.8% 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