OpenAI launches BioBasicsBench to measure AI agents on everyday wet-lab analysis
OpenAI and enzyme-design biotech company Ligo released BioBasicsBench, a 100-task benchmark from real experiments that tests whether AI agents can interpret raw lab data, spot errors, and recognize when evidence does not support a conclusion.
OpenAI announced on November 7, 2026 (Singapore time) BioBasicsBench, a new way to measure how AI agents handle the routine analyses of wet-lab science (hands-on laboratory experiments).
Developed with Ligo, a biotech company focused on enzyme design, the benchmark draws on 100 tasks from real experiments. It tests whether agents can interpret raw lab data, identify errors, and recognize when the evidence does not support a conclusion.
OpenAI says accelerating biological research starts with getting everyday lab work right. BioBasicsBench is meant to show where models need to improve and to help track what those gains mean for scientific progress, biosafety, and biosecurity.
Official post: Measuring how AI agents handle everyday wet-lab science