there are many approaches for solving variety combinatorial optimization problems (np-compelete) that devided to exact solutions and approximate solutions. exact methods can only be used for very small size instances due to their expontional search space. for real-world problems, we have to employ approximate methods such as evolutionary algorithms (eas) that find a near-optimal solution in a reasonable time, rather than an exact method which gurantees to find the optimal solution in an exponential time. eas are most popular random search techniques. in this thesis, we proposed eas consist on genetic algorithm (ga), ant colony optimization (aco), particle swarm optimization (pso), and artificial bee colony (abc) to solve np-compelete problems such as traveling salesman problem (tsp), knapsack problem (kp), and the optimization of artificial neural network parameters (ann). each problem carried out with each ea, and then the obtained results will compared together. consequently, for each problem, one of the eas will be selected as the best algorithm.