Abstract Aging diminishes social cognition, and changes in this capacity can indicate brain diseases. However, the relative contribution of age, diagnosis and brain reserve to social cognition, especially among older adults and in global settings, remains unclear when considering other factors. Here, using a computational approach, we combined predictors of social cognition from a diverse sample of 1,063 older adults across nine countries. Emotion recognition, mentalizing and overall social cognition were predicted via support vector regressions from various factors, including diagnosis (subjective cognitive complaints, mild cognitive impairment, Alzheimer’s disease and behavioral variant frontotemporal dementia), demographics, cognition/executive function, brain reserve and motion artifacts from functional magnetic resonance imaging recordings. Higher cognitive/executive functions and education ranked among the top predictors, outweighing age, diagnosis and brain reserve. Network connectivity did not show predictive values. The results challenge traditional interpretations of age-related decline, patient–control differences and brain associations of social cognition, emphasizing the importance of heterogeneous factors.