OpenAI Introduces BioBasicsBench for Wet Lab Analysis

OpenAI introduces BioBasicsBench, a benchmark developed with enzyme design company Ligo and detailed in a company blog post. Its 100 tasks test whether AI agents can interpret raw experimental data, identify errors and recognize when evidence does not support a conclusion.

The tasks cover protein methods, imaging and cytometry, quantification and assays, nucleic acid methods, and molecular cloning. Inputs include gel and blot images, colony plate photographs, microscopy stacks, sequencing reads, plate reader exports and videos of laboratory work.

OpenAI evaluated seven models across 37 model and reasoning effort settings, producing 18,500 results. At the highest shared reasoning setting, GPT 6 Astra earned 66.7% of the available credit on average, compared with 43.8% for GPT 5.6 Sol. Astra performed better at detecting ambiguous evidence, checking experimental controls and applying context across images and other laboratory data.