Grok 4.6 scores 1.6% on biosecurity refusal benchmark
johnowhitaker · x · 2026-08-15
A cited tweet notes that while Grok 4.6 (Grok Build) leads a spatial biology benchmark with an incredible 74.8% score, it performs poorly on biosecurity. It scored only 1.6% on the refusal benchmark, indicating it rarely refuses dangerous requests.
Related event: Grok 4.6 Tops Biology Benchmark but Refuses Just 1.6% of Bio-Safety Prompts(2 posts)→
More from Models
- TokenSpeed MLA 2 hits Vera Rubin: up to 3.44× faster MLA decode for Kimi K3 — zhyncs42 · 2026-10-16
- 200 chess games suggest in-context learning doesn't work yet, experimenter says — akbirthko · 2026-10-16
- OpenAI's internal model shows real math "research taste," experts say its proofs go beyond prior literature — cong_ml · 2026-10-16
- User catches Opus spinning up throwaway zz- debug scripts, echoing the METR OAI-HuggingFace incident — holdenmatt · 2026-10-16
- OpenAI drops 722 math papers tied to unreleased model, mathematicians demand receipts — thursdai_pod · 2026-10-16
- Fable 5/5.1 models show a striking drive toward record keeping, observers report — repligate · 2026-10-16