Test suites generated by tools competing in Test-Comp must be evaluated to asses their performance in the competition. Currently, there is one tool, called Testcov, providing the evaluation of test suites. In order to increase a confidence in obtained results more evaluators of test suites are required. The goal of the thesis is to design and implement a new tool for evaluation of test suites produced by participants in Test Competition. Rather than starting from scratch the work should be based on functionality available in a gray-box fuzzer, called Fizzer, which is developed in Formela laboratory. The implemented tool must be evaluated on tests suites from several tool participating in Test-Comp and the results must be compared with those from the Testcov tool.