OpenAI and Ligo launch BioBasicsBench for wet-lab AI
According to OpenAI, BioBasicsBench tests AI agents on 100 real wet-lab tasks to interpret raw data, flag errors, and assess unsupported conclusions.
SourceAnalysis
OpenAI introduced BioBasicsBench on November 6, 2026, a benchmark developed with the biotech company Ligo to evaluate how AI agents perform routine analyses in wet-lab science.
The benchmark uses 100 tasks from real experiments to test whether agents can interpret raw lab data, identify errors, and recognize when the evidence does not support a conclusion, according to OpenAI. Accelerating biological research requires strong performance on everyday tasks, and BioBasicsBench helps identify areas for model improvement related to scientific progress, biosafety, and biosecurity.
OpenAI
@OpenAILeading AI research organization developing transformative technologies like ChatGPT while pursuing beneficial artificial general intelligence.