This diploma thesis deals with the quality of the output of publicly available machine translation engines: Amazon Translate, Bing Translator, Deep L and Google Translate. The aim of the thesis was to qualitatively compare each machine translation engine and to test their capabilities on several types of texts - expressive, informative and operative. The analysis is carried out on translations of German texts into Czech. The thesis consists of two parts, in the theoretical part we discuss the origin and development of machine translation, its types, the automatic machine translation engines which are the object of our research, and we present a two-stage model for evaluating the quality of translation. In the empirical part, the results of the analysis based on the models of K. Reiß and A. Torrens are presented. These results show that the listed machine translation engines can be ranked from the highest to the lowest level of output quality as follows: Deep L, Google Translate, Bing Translator and Amazon Translate. Furthermore, it also turns out that the error rate correlates with the creativity of the text.