Scalable video coding is emerging as an efficient alternative to simulcast encoding to distribute the same video content simultaneously to many users having different terminals and network conditions. In order to select the best combination of video scalability options for a given network condition and content, the availability of objective metrics that can reliably predict the video quality of scalable video sequence is crucial. In this paper, we propose a performance evaluation study of a set of state of the art Full-Reference and No-Reference metrics, considering a public database of test video sequences and related subjective quality annotations. The results demonstrate that most of the considered metrics show lack of robustness as predictors of subjective quality when both spatial and temporal quality distortions occur.