Service update · OpenAI

OpenAI introduces BioBasicsBench, a wet-lab science benchmark for AI agents

Recorded time: Nov 07, 2026 08:31 · Beijing Time (UTC+8)
Review updated: Nov 07, 2026 11:29 Sat · Beijing Time (UTC+8)

OpenAI and biotech firm Ligo launched BioBasicsBench: 100 tasks from real experiments measuring how AI agents handle routine wet-lab analyses.

Customize my briefingMarkdown

Source trace

Reviewed by Ailyre. Source evidence is presented separately from our summary.

Source excerpt

x.com

Source checked: Nov 07, 2026 08:31 Sat · Beijing Time (UTC+8)

Original ↗View archived evidence ↗