The aim of this paper was, on the one hand, to determine the efficacy of stimulus control and exposure with response prevention in stopping pathological gambling and, on the other hand, to test the comparative effectiveness of two therapeutic modalities (individual and group) for relapse prevention, relative to a control group, in order to maintain abstinence. The sample consisted of 69 patients selected according to DSM-IV criteria. At the first part of the study, a one-group design with repeated measures of assessment (pre- and posttreatment) was used. At the second part, a multi-group experimental design with repeated measures (pretreatment, posttreatment, and 1-, 3-, 6-, and 12-month follow-up) was used. All treated patients gave up gambling at the end of the first part of the study. In the second part, results related to relapse showed a success rate higher in both individual and group relapse prevention than in the control group. These results raise the necessity of using relapse prevention programs in the treatment of pathological gambling. Implications of this study for clinical practice and future research in this field are discussed.