OpenAI launches MedChemBench for medicinal-chemistry reasoning
OpenAI introduced MedChemBench, a 99-problem benchmark drawn from 117 papers and patents and covering 761 distinct molecular structures. It evaluates molecular reconstruction, evidence-based scientific reasoning, compound ranking and selection, and property prediction; OpenAI reported that models performed best on reconstruction and explanation, while selection and numerical prediction remained difficult. At the xhigh reasoning setting, OpenAI reported scores of 84.5% for GPT-6.2 Astra, 83.3% for GPT-6 Astra, 82.0% for GPT-6.1 Sol, and 58.2% for GPT-5.6 Sol.
MedChemBench provides a more structured way to compare models across four medicinal-chemistry reasoning tasks, highlighting where they can connect molecular structures with historical experimental evidence and where substantial gaps remain.
November 20, 2026
Can AI help scientists identify promising drug candidates?
Introducing MedChemBench, a benchmark that tests how well AI models read molecular structures, interpret experimental results, and choose which compounds to test next.
Read the paper(opens in a new window)

#OpenAI#MedChemBench#GPT-6.2 Astra#GPT-6 Astra#GPT-6.1 Sol#GPT-5.6 Sol#GPT-5.6 Luna