Vitek GNI system is one of the most widely used automated method for the identification of aerobic gram-negative bacilli. The aim of this study was to evaluate the performance of the system with recently upgraded software. Most of the clinical isolates used in this study were those not identifiable by the conventional minimal test. The rate of identification to species was 93.1%, i.e., 81.6% with high probability, 4.7% with low probability and 6.8% with BioGNI. Citrobacter freundii and Enterobacter sp. were relatively more often unidentified or misidentified. Among the correctly identified strains, 50% of Escherichia coli and 19% of Klebsiella pneumoniae were identified at the end of 2 hour incubation. It is concluded that Vitek GNI system with newer software shortened the identification time of some species without compromising the accuracy of the identification.