OpenAI launches BioBasicsBench to test AI agents on wet-lab data
OpenAI and Ligo present BioBasicsBench, a 100-task benchmark measuring how well AI agents interpret raw laboratory data from routine experiments.
By GennnAi··1 min read
The tasks span five areas: protein methods, imaging and cytometry, quantification and assays, nucleic acid methods, and molecular cloning. Agents must spot errors and recognise when evidence cannot support a conclusion. Each task was reviewed by a Ligo scientist and an external PhD-level wet-lab scientist, plus a final internal review. OpenAI warns higher scores do not yet mean reliable lab judgement. It says the benchmark excludes physical work such as pipetting and robotic execution.
Source: OpenAI, published on November 6, 2026.