Background Several breast cancer risk assessment models exist. Few studies have evaluated predictive accuracy of multiple models in large screening populations. Methods We evaluated the performance of the BRCAPRO, Gail, Claus, Breast Cancer Surveillance Consortium (BCSC) and Tyrer-Cuzick models in predicting risk of breast cancer over six years among 35,921 women aged 40-84 who underwent mammography screening at Newton-Wellesley Hospital from 2007-2009. We assessed model discrimination using the area under the receiver operating characteristic curve (AUC) and assessed calibration by comparing the ratio of observed-to-expected (O/E) cases. We calculated the square root of the Brier Score and positive and negative predictive values of each model. Results Our results confirmed good calibration and comparable moderate discrimination of the BRCAPRO, Gail, Tyrer-Cuzick, and BCSC models. The Gail model had slightly better O/E ratio and AUC (O/E=0.98, 95% CI:0.91-1.06, AUC=0.64, 95% CI:0.61-0.65) than BRCAPRO (O/E=0.94, 95% CI:0.88-1.02, AUC=0.61, 95% CI:0.59-0.63) and Tyrer-Cuzick (version 8, O/E=0.84, 95% CI:0.79-0.91, AUC=0.62, 95% CI:0.60-0.64) in the full study population, and the BCSC model had the highest AUC among women with available breast density information (O/E=0.97, 95% CI:0.89-1.05, AUC=0.64, 95% CI:0.62-0.66). All models had poorer predictive accuracy for HER2+ and triple negative breast cancers than hormone receptor positive HER2- breast cancers. Conclusions In a large cohort of patients undergoing mammography screening, existing risk prediction models had similar, moderate predictive accuracy and good calibration overall. Models that incorporate additional genetic and non-genetic risk factors and estimate risk of tumor subtypes may further improve breast cancer risk prediction.