Applications architecture is the baseline of any organizational activity, which main goal is to provide the executional environment for businessprocesses in order to deliver products or services to satisfy customer needs and generate revenue. Nowadays, large software engineering projectsalways begin with the architecture design phase, despite the waterfall or agile methodology is used by a software development team. Applicationsarchitecture design is the most important and, at the same time, error-prone stage of the whole software engineering project. It is well-known thatdesign shortcomings made on the design phase may increase drastically to testing and maintenance phases. Further costs to defects fixing may behundred times higher in the later project stages in compare to the design stage on which applications architecture is defined. Common system designsolutions, which were proven on practice and used in many projects, are known as architectural patterns. Software architecture patterns are consideredas building block for system implementation. The most popular and efficient way to share architectural patterns are graphical models that used as anyother blueprints of engineering solutions. Applications architecture models are built to represent system design, whereas, such models are alreadybased on certain patterns as the industry best practices. Hence, in this paper we consider a relevant problem of applications architecture modelsanalysis, which relevance is defined by those fact that designed blueprints of information systems and other software solutions should be carefullychecked for all presumable inefficiencies in order to avoid extra efforts and related costs for defects fixing in the later project stages. It is proposed touse ArchiMate enterprise architecture modeling language, since it can be used not only to represent applications architecture, but is connection tobusiness and technology layers. In order to evaluate applications architecture models, respective ArchiMate metamodel is considered and representedas labeled directed graph, and coupling software metric is selected for analysis. Sample calculations are demonstrated, obtained results are discussed,conclusion and future work directions are formulated.