Launching today
BioBasicsBench by OpenAI
A benchmark for how AI agents read raw lab data
1 follower
A benchmark for how AI agents read raw lab data
1 follower
BioBasicsBench is OpenAI’s benchmark, developed with enzyme-design company Ligo, for how AI agents handle everyday wet-lab science. It has 100 tasks that scientists built from real experiments, covering gels, colony plates, microscopy, sequencing reads and more, graded against expert rubrics. Per OpenAI, GPT-6 Astra scored 66.7% at its highest effort setting, and higher scores do not yet amount to reliable laboratory judgment.
No makers yet
It looks like there are no makers for this product.