The development of an effective and efficient method for generating test data is an extremely challenging process which directly impacts the time that could be spent on activities relevant to software testing. Therefore, various researches related to this area have been carried out. Among the techniques for automatically generating test data, we highlight the use of metaheuristics, a promising area called Search-Based Software Testing (SBST). Thus, this article proposes the use of an Elitist Genetic Algorithm (GA) as a tool for generation and selection of test data applied in Mutation Testing for different benchmarks. The results indicate a good performance of the algorithm used in the benchmarks.