The global prevalence of diabetes is rapidly increasing. Studies support screening and interventions for pre-diabetes, which results in serious complications and diabetes. This study aimed at developing an intelligence-based screening model for pre-diabetes that could assist with decreasing the prevalence of diabetes through early identification and subsequent interventions. Data from the Korean National Health and Nutrition Examination Survey (KNHANES) were used, excluding subjects with diabetes. The KNHANES 2010 data (n = 4,685) were used for training and internal validation, while data from KNHANES 2011 (n = 4,566) were used for external validation. We developed a model to screen for pre-diabetes using support vector machine (SVM), and performed a systematic evaluation of the SVM model using internal and external validation. We compared the performance of the SVM model with that of a screening score model based on logistic regression analysis for pre-diabetes that had been developed previously. Backward elimination logistic regression resulted in associations between pre-diabetes and age, sex, waist circumference, body mass index, alcohol intake, family history of diabetes, and hypertension. The areas under the curves (AUCs) for the SVM model in the internal and external datasets were 0.761 and 0.731, respectively, while the AUCs for the screening score model were 0.734 and 0.712, respectively. The SVM model developed in this study performed better than the screening score model that had been developed previously and may be more effective for pre-diabetes screening.