Grok 4.6 leads in biosecurity refusal without compromising research utility

ns123abc · x · 2026-09-02

SpaceXAI shared an independent evaluation by LatchBio highlighting Grok 4.6's biosecurity capabilities. On the BioSecBench-Refusal benchmark, Grok 4.6 was the only model to score above 50% on both refusing disguised red-team tasks and completing routine dual-use research tasks. The report notes that this safety behavior stems from model intelligence rather than input classifiers, without degrading performance in general biological benchmarks.

Related event: Independent Evaluation Finds Grok 4.6 Blocks Dangerous Bio Queries Without Losing Capability(2 posts)→

Original post →

More from Models

Models channel →