BioSecBench Released: Opus and Grok Lead New Biological Security Benchmark
himanshustwts · x · 2026-08-28
BioSecBench-Function is a new verifiable benchmark designed to test whether AI agents can infer the functional properties of viruses, bacteria, and toxins from data. It contains 111 deterministic evaluations. Results show that Opus 5 with Claude Code leads in endpoint pass rate (50.4%), while Grok 4.6 with Grok Build leads in overall pass rate (44%) when refusals are counted as failures.
Related event: BioSecBench: AI Agents Fall Short on Pathogen Function Inference(3 posts)→
More from Safety
- Animated teardown of XBOW's Chrome full-chain exploit that won Google's first $250K VRP bounty — moyix · 2026-10-15
- Ex-White House cyber deputy launches SAIF nonprofit with $25M from a16z founders for AI cyber defense — vishalmisra · 2026-10-15
- GLM-5.3 unprompted reasons about how its actions affect its future training, worries Apollo — MariusHobbhahn · 2026-10-15
- NYC invests $30M in NYU quantum lab for 15% revenue share and board seats — TuhinChakr · 2026-10-15
- SentinelOne says OpenAI did 4-6 weeks of reverse-engineering in 8 hours — OpenAI · 2026-10-15
- Regulator's 50-Page Inquiries Seek Marketing Materials and Privacy Policies, Signaling a Deception Case — neil_chilson · 2026-10-15