Brain metastasis occurs in approximately 50% of patients with advanced HER2-positive breast cancer. Despite improved prognosis, survival remains limited. This study aims to investigate the clinicopathological characteristics of HER2-positive breast cancer brain metastasis (BCBM) patients and their prognostic associations, to identify personalized treatment strategies to enhance survival. This retrospective study included HER2-positive BCBM patients treated at three institutions: the Fifth Medical Center of the Chinese PLA General Hospital, Peking University First Hospital, and the First Affiliated Hospital of Xi'an Jiaotong University. Clinical, pathological, and treatment data were collected. A prognostic model was developed using recursive variable selection, starting with significant variables from univariate analysis and refining them through a recursive loop in multivariate Cox regression. The model stratified patients into three risk groups: low-risk (score 0-1), intermediate-risk (score 2-3), and high-risk (score 4-6), based on various independent prognostic factors. The median survival times for the low-, intermediate-, and high-risk groups were 30, 20, and 10 months, respectively (P < 0.0001, HR = 1.35, 95% CI: 0.94-1.94; HR = 4.02, 95% CI: 2.4-6.73). The mean ROC curve AUC values for the 1-year, 2-year, and 3-year prognostic predictions were 0.69, 0.70, and 0.61, respectively. In the independent validation cohort of 75 patients, prognostic stratification into low-, intermediate-, and high-risk groups revealed significant differences in outcomes (73 months vs. 35 months vs. 9 months, P < 0.001, HR = 2.68, 95% CI: 1.30-5.52; HR = 8.82, 95% CI: 3.89-19.97). The mean AUC value for the 1-year and 2-year prognostic predictions in the validation cohort was 0.94, whereas the mean AUC value for the 3-year prognostic prediction was 0.81. This study developed a prognostic stratification model for HER2-positive BCBM patients based on clinicopathological characteristics.