3D graphics technologies have known a developed progress in the last years, and several processing operations can be applied on 3D meshes such as watermarking, compression, simplification and so forth. Mesh visual quality assessment becomes an important issue to evaluate the visual appearance of the 3D shape after specific modifications. Several metrics have been proposed in this context, from the classical distance-based metrics to the perceptual-based metrics which include perceptual information about the human visual system. In this paper, we propose to study the performance of several mesh visual quality metrics. First, the comparison is conducted regardless the distortion types neither the areas where these distortions are applied. Then, the degradation applied on the whole objects are considered. Finally, the comparison is conducted considering specific areas (smooth and rough). This study allows us to determine which metric is appropriate for such attribute. Experiments are conducted on the General-Purpose database and show that correlation score may vary by changing the attributes.