The goal of the present study was to evaluate the diagnostic discriminability of three different global scores for the German version of the Consortium to Establish a Registry on Alzheimer's Disease-Neuropsychological Assessment Battery (CERAD-NAB). The CERAD-NAB was administered to 1100 healthy control participants [NC; Mini-Mental State Examination (MMSE) mean = 28.9] and 352 patients with very mild Alzheimer's disease (AD; MMSE mean = 26.1) at baseline and subsets of participants at follow-up an average of 2.4 (NC) and 1.2 (AD) years later. We calculated the following global scores: Chandler et al.'s (2005) score (summed raw scores), logistic regression on principal components analysis scores (PCA-LR), and logistic regression on demographically corrected CERAD-NAB variables (LR). Correct classification rates (CCR) were compared with areas under the receiver operating characteristics curves (AUC). The CCR of the LR score (AUC = .976) exceeded that of the PCA-LR, while the PCA-LR (AUC = .968) and Chandler (AUC = .968) scores performed comparably. Retest data improved the CCR of the PCA-LR and Chandler (trend) scores. Thus, for the German CERAD-NAB, Chandler et al.'s total score provided an effective global measure of cognitive functioning, whereby the inclusion of retest data tended to improve correct classification of individual cases.