Abstract: Software reliability is one of the most basic and essential problems in software development. In order to detect the software failure phenomenon, the intensity function which is the instantaneous failure rate in the non-homogeneous Poisson process can have the property that it is constant, non-increasing or non-decreasing independently at the failure time. In this study, was compared the reliability performance of the software reliability model using the Type-2 Gumble life distribution with the intensity function from increasing to decreasing pattern in the software product testing process. In order to identify the software failure phenomenon, the parametric estimation was applied to the maximum likelihood estimation method. Therefore, in this study, was compared and evaluated software reliability using software failure time data. As a result because of the smaller the shape parameter of the Type-2 Gumbel distribution is the lower the mean square error, the model of the smaller the shape parameter relatively efficient properties appears. However, from the reliability point of view, the reliability of is higher than that of and about shape parameter of the Type-2 Gumble life distribution. Through this study, the software design department will be able to help the software design by applying various life distribution and shape parameters and providing basic knowledge using software failure analysis.