Male breast cancer is uncommon, but its clinical management remains challenging because evidence is still far less abundant than that for female breast cancer. This study used data from the SEER Program to evaluate prognostic factors in male breast cancer and to compare the performance of Cox proportional hazards and accelerated failure time (AFT) models. After data cleaning and variable construction, 1,743 male patients diagnosed between 2000 and 2019 were included in the final analytic cohort. The dataset contained demographic information, tumor stage, receptor status, treatment variables, survival time, and outcome status. According to the above results, the 1-year, 3-year and 5-year survival rates are 93.7%, 82.7% and 71.5%, respectively. The test for proportional hazards showed that some variables did not meet the requirements of the Cox model, so an AFT model was selected. We can find that survival analysis of SEER data can provide statistical support for the prognosis prediction of patients.