Tobacco quality has an important role in determining the quality of cigarette production. One of the stages in postharvest tobacco that needs attention is sorting, where this process is carried out by graders. Sometimes a grader is less accurate in determining the quality of tobacco, the human error factor is usually the main cause. In this research, a classification model using the Naïve Bayes method will be made to help determine the quality of tobacco. From the results of research that has been carried out the level of accuracy between the information requested by the user and the answer given by the system (Precision) is 86%, the success rate of the system in retrieving an information (recall) is 68% and the level of closeness between the predicted value and the actual value. reach (accuracy) 67%.