The purpose of this study was to formulate and test two case-mix models for depression treatment that permit comparisons of patient outcomes across diverse clinical settings. It assessed demographics; eight, diagnostic-specific, case-mix variables; and clinical status at baseline and follow-up for 187 patients. Regressions were performed to test two models for four dependent variables including depression severity and diagnosis. Individual treatment settings were then ranked based on a comparison of actual versus predicted outcomes using regression coefficients and predictor variables. A model inclusive of baseline physical health status and depression severity predicted depression severity, mental health, and physical health functioning at follow-up. A simpler model performed well in predicting depression remission. This study identifies variables to be included in case-mix adjustment models and demonstrates statistical methods to control for differences across settings when comparing depression outcomes.