BioBasicsBench: wet-lab agent eval with Ligo

OpenAI published BioBasicsBench with Ligo (6 Nov): 100 routine wet-lab tasks on raw gels, plates, microscopy and instrument exports, scored against expert rubrics. At the 'xhigh' setting OpenAI reports GPT-6 Astra at 66.7% mean reward vs 43.8% for GPT-5.6 Sol (OpenAI's figures). The post also shows where models still fail (wrong controls, overcounting colonies, assumptions overriding evidence). Fact that the benchmark and post exist; Partly fact on the scores.

Why it mattersEven outside biotech, it is a clear reminder that agent 'done' on messy real-world inputs needs rubrics and human review — the failure cases are the useful part for any ops team.

Curated by Sara Simeone as part of our human editorial coverage. The original sources are linked below; curation is distinct from a Hype or Fact? assessment.

SHARE THISPost on X ↗Share on LinkedIn ↗Copy link

How we knowCompany figures are labelled as their own claims; anything we couldn't verify is labelled as a report or a claim.