OpenAI publishes the MedChemBench chemistry benchmark

On Nov. 20, 2026 OpenAI introduced MedChemBench, 99 problems drawn from 117 papers and patents and 761 molecular structures, covering structure reconstruction, reasoning, compound selection, and property prediction. At the xhigh setting, OpenAI says GPT-6.2 Astra scored 84.5 percent of available credit, against 83.3 percent for GPT-6 Astra, 82.0 percent for GPT-6.1 Sol, and 58.2 percent for GPT-5.6 Sol. OpenAI says the scores do not show the models can discover drugs, and that prior exposure to the published sources cannot be ruled out.

/ Sources

/ About this story

Compiled by Venture Atlas from the sources above, using automated AI-assisted research. This is a summary of reporting published elsewhere, not original reporting - follow the source links for the full account. See our editorial standards.

Something wrong here? Email apostructura@gmail.com and we will fix it.

/ Related