New models of interventions provide evidence-based learning tailored to the needs of individual physicians. The aim of this study is to assess the cost-effectiveness of an individualized case-based learning intervention provided by primary care physicians (PCPs) to patients with diabetes based on a randomized clinical trial (RCT). The RCT was conducted from October 2006 to May 2007. Eleven clinics with 41 consenting PCP's in a large medical group in Minnesota were randomized to receive or not receive the learning intervention. Twelve simulated type 2 diabetes cases designed to remedy specific deficits found in physician electronic medical record (EMR) observed practice patterns were individually assigned to PCP's. A diabetes simulation model was used to estimate costs and quality of life years (QALYs) gained over a 40 year period from the health plan perspective. Change from pre-intervention to 12 month post-intervention levels of glycated hemoglobin (A1c), blood pressure (BP) and LDL-Cholesterol (LDL) of the patients assigned to randomized PCP's was assessed using general linear mixed models that accommodated the cluster randomized study design. Intervention clinic patients with baseline A1c >=7% had significantly better A1c reduction at 12 month post-intervention (-0.19%, p=.034) relative to patients in non-intervention clinics. The individualized case-based learning intervention had a negative net cost of -$71 (SE=$143) in the first year, and both increased QALYs and reduced costs over a 40-year period. A brief individualized case-based simulated learning intervention for primary care physicians support is a cost-effective approach to improve glucose control in adults with type 2 diabetes who were not at recommended clinical goals.