GPT-6 Astra beats chemistry foundation models on property prediction with 60 data points
Chemical foundation models such as ChemBERTa and MoLFormer are trained on molecular structures so they can be fine-tuned on small lab datasets. With only 60 experimental datapoints, general-purpose GPT-6 Astra outperformed them on five physicochemical and quantum-chemical regression tasks. The chemical models needed 10x the data: at 1,000 and 10,000 points they performed on par with Astra at 60 and 1,000 points.