Introduction: the initial assessment of the severity of the patient with Community-Acquired Pneumonia (CAP) is a key point in deciding the site of care and for making management decisions, as well as for establishing complications and prognosis. Currently, comparative studies using the Pneumonia Shock Score vs CURB-65 are still scarce. Objective: evaluate the performance and performance of the Pneumonia Shock Score in comparison to the CURB-65 in subjects with and without severe CAP as a predictor of the need for mechanical ventilation, in-hospital mortality, and 30-day mortality. Methodology: a retrospective cohort study in subjects with a diagnosis of CAP and with all the information necessary for the complete calculation of the Pneumonia Shock Score and CURB-65. CAP was defined according to the guidelines of the American Thoracic Society / British Thoracic Society. The following outcomes were considered: in-hospital mortality and 30-day mortality, as independent variables the clinical findings, history, measurement of vital signs, laboratory findings, arterial blood gas values, and diagnostic images. Results: 1907 subjects entered the definitive analysis for the Pneumonia Shock and CURB-65 scores, 301 patients died during hospitalization and 30-day follow-up. In the present cohort, the average age was 70.5 years (SD 19.44) and 61% of the population were men. The sensitivity turned out to be higher for the CURB-65 score in in-hospital mortality (83.39%) and 30-day follow-up mortality (82.87%). The Pneumonia Shock Score has a curve of receiver operating characteristics for in-hospital and 30-day mortality of 0.748 (95% CI: 0.718-0.778, p <0.001) and 0.739 (95% CI: 0.709-0.769, p <0.001), respectively. Conclusion: The Pneumonia Shock Score has a similar performance to the CURB-65 for the prediction of mortality in patients with CAP admitted to the intensive care unit.