This study considers the application of a genetic algorithm (GA) to the basic vehide routing problem with tow-dimensional loading constraints (2L-CVRP). Vehicle routing problem encompasses a whole class of complex optimization problems that target the derivation of minimum total cost routes for a number of resources (vehicles, etc.) located at a central depot in order to service efficiently a number of demand customers. Several practical issues in the industry involving both production and transportation decisions are modeled as VRP instances and the hard combinatorial problems in the strong sense (NP-hard). 2L-CVRP is a generalization of the Capacitated Vehicle Routing Problem, in which customer demand is formed by a set of rectangular, weighted items. In this paper, computational results are given for the pure GA which is put forward. As compare with the mathematic method, we can find the advantage of using GA to solve the problem especially in large sizeproblems.