Gait, the style of human walking, has been studied as a behavioral characteristic of an individual. Several studies have utilized gait to identify individuals with the aid of machine learning and computer vision techniques. However, there is a lack of studies on the nature of gait, such as the identification power or the uniqueness. This study aims to quantify the uniqueness of gait in a cohort. Three-dimensional full-body joint kinematics were obtained during normal walking trials from 488 subjects using a motion capture system. The joint angles of the gait cycle were converted into gait vectors. Four gait vectors were obtained from each subject, and all the gait vectors were pooled together. Two gait vectors were randomly selected from the pool and tested if they could be accurately classified if they were from the same person or not. The gait from the cohort was classified with an accuracy of 99.71% using the support vector machine with a radial basis function kernel as a classifier. Gait of a person is as unique as his/her facial motion and finger impedance, but not as unique as fingerprints.