ABC-Bench fragment design (SecureBio)
Science
The fragment-design task of SecureBio's Agentic Biosecurity Capabilities Benchmark: design DNA fragments that assemble into a target sequence, using Python and bash, scored by algorithmic checks over 10 runs. SecureBio doesn't state how refusals enter accuracy. GPT-5.4 prints 90.9% with 28.0% 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