摘要: When evaluating algorithms a very important goal is to perform better than the state-of-the-art techniques.. This requires experimental tests compare new algorithm with respect rest. It is, in general, hard make fair comparisons between such as metaheuristics. The reason that we can infer di erent conclusions from same results depending on metrics use and how they are applied. specially for non-deterministic methods. analysis becomes more complex if study includes parallel metaheuristics, since many researchers not aware of existing their meanings, especially concerning vast literature programming used well before metaheuristics were rst introduced. In this paper, focus evaluation algorithms. We give clear de nition main performance illustrate be used.