Introduction: A challenge in the diagnosis of renal cell carcinoma (RCC) is to distinguish chromophobe renal cell carcinoma (chRCC) from benign renal oncocytoma, as these tumor types are histologically and morphologically similar, yet they require different clinical management. Molecular biomarkers could provide a way of distinguishing oncocytoma from chRCC, which could prevent unnecessary treatment of oncocytoma. Such biomarkers could also be applied to preoperative biopsies such as needle core biopsies, to avoid unnecessary surgery of oncocytoma. Methods: We profiled DNA methylation in fresh-frozen oncocytoma and chRCC tumors and adjacent normal tissue and used machine learning to identify a signature of differentially methylated CpG sites (CpGs) that robustly distinguish oncocytoma from chRCC. Results: Unsupervised clustering of Stanford and pre-existing TCGA RCC data revealed that of all RCC subtypes, oncocytoma is most similar to chRCC. Unexpectedly, however, oncocytoma features more extensive overall abnormal methylation than chRCC. We identified 79 CpGs with large methylation differences between oncocytoma and chRCC. A diagnostic model trained on thirty CpGs could distinguish oncocytoma from chRCC in ten-fold cross validation (area underthe ROC curve (AUC): 0.96 (95% CI: 0.88-1)) and could distinguish TCGA chRCCs from an independent set of oncocytomas from a previous study (AUC=0.87). This signature also separated oncocytoma from other RCC subtypes and normal tissue, revealing it as a standalone diagnostic biomarker for oncocytoma. Conclusions: This CpG signature could be developed as a clinical biomarker to support differential diagnosis of oncocytoma and chRCC in surgical samples. With improved biopsy techniques, this signature could be applied to preoperative biopsies.