The Naples score (NS), which is a composite of cardiovascular adverse event predictors including neutrophil-to-lymphocyte ratio, lymphocyte-to-monocyte ratio, albumin, and total cholesterol, has emerged as a prognostic risk score in cancer patients. We aimed to investigate the predictive value of NS for long-term mortality in ST-segment elevation myocardial infarction patients (STEMI). A total of 1889 STEMI patients were enrolled in this study. The median duration of the study was 43 months (IQR: 32-78). Patients were divided into 2 groups according to NS as group 1 and group 2. We created 3 models as a baseline model, model 1 (baseline + NS in continuous), and model 2 (baseline + NS as categorical). Group 2 patients had higher long-term mortality rates than group 1 patients. The NS was independently associated with long-term mortality and adding NS to a baseline model improved the model performance for prediction and discrimination of long-term mortality. Decision curve analysis demonstrated that model 1 had a better net benefit probability for detecting mortality compared with the baseline model. NS had the highest contributive significant effect in the prediction model. An easily accessible and calculable NS might be used for risk stratification of long-term mortality in STEMI patients undergoing primary percutaneous coronary intervention.