OpenAI's GPT-6 Astra scores 66.7% on wet-lab benchmark
The gain came with fewer reasoning tokens, so the benchmark improvement reflects better raw-data reading rather than longer thinking. Rubrics that reward partial credit and error-spotting make this a more realistic measure of lab readiness than pass/fail tests. Teams evaluating agents for scientific work can use it to compare GPT-6 Astra against GPT-5.6 Sol on messy real-world inputs.
OpenAI built BioBasicsBench with enzyme-design company Ligo, a benchmark of 100 tasks using raw wet-lab data such as gels, colony plates, microscopy, sequencing reads and bench videos. GPT-6 Astra earned 66.7% of available credit, versus 43.8% for GPT-5.6 Sol. The rubrics award partial credit, including for spotting errors or stating that evidence cannot support a conclusion. At the xhigh setting, Astra used 4,704 output tokens per task, about half of the older model's usage.
OpenAI built BioBasicsBench, a test that gives AI agents the messy raw data of real lab work, like gel photos and microscope videos, and grades whether they read it correctly.
GPT-6 Astra earned 66.7% of available credit on a new wet-lab benchmark, versus 43.8% for GPT-5.6 Sol.
BioBasicsBench, built with enzyme-design company Ligo, draws 100 tasks from scientists’ raw gels, colony plates, microscopy, sequencing reads and bench videos.
Its rubrics give partial credit, including for spotting errors or saying evidence can’t support conclusions.
At the xhigh setting, Astra used 4,704 output tokens per task, about half the older model’s, so longer reasoning didn’t drive the gain.
