Zero-shot evaluation reveals limitations of single-cell foundation models.

Foundation models such as scGPT and Geneformer have not been rigorously evaluated in a setting where they are used without any further training (i.e., zero-shot). Understanding the performance of models in zero-shot settings is critical to applications that exclude the ability to fine-tune, such as discovery settings where labels are unknown. Our evaluation of the zero-shot performance of Geneformer and scGPT suggests that, in some cases, these models may face reliability challenges and could be outperformed by simpler methods. Our findings underscore the importance of zero-shot evaluations in development and deployment of foundation models in single-cell research.