This comparative study addresses the quantification of gait deviations from normal gait, and across different motor impairments induced by neurological diseases. We compared Gait Deviation Index and Gait Profile Score, well-known in the literature, to a novel 3D-metric based on Dynamic Time Warping (DTW). These deviation measures are analyzed following the same methodology, based on unsupervised learning, on the same database. Results show that our 3D-metric outperforms the other. This confirms that for finely quantifying deviations, it is crucial to consider different references to represent normal gait variability, as well as using an elastic distance (DTW) for matching two gait cycles.