Software cost estimation approximate judgment of the cost and time required to complete the project successfully. The cost estimation is usually measured in terms of effort. The Constructive Cost Model (COCOMO) is one of the most important model for software cost estimation. In this paper, soft computing techniques: genetic algorithm has been used for tuning the parameters of COCOMO model to predicate the software cost more accurately. Moreover, the performance of proposed methods compared through COCOMO NASA Data Set were used.