A The paradigm of Mobile Agents is emerging in the field of distributed computing. Mobile agents present features, such as autonomy and capability to roam to hosts, process data, and save remote communications. Many mobile agent platforms have been developed for research purposes while other platforms have been deployed as commercial products. Several Java-based platforms have been already implemented and many researchers is now starting to implement some based applications. In most of the cases, the performance of the applications is an issue of paramount importance. A common problem when one wants to benefit from mobile agent platform is the decision about which platform to use. In fact performance evaluation is exploited to address different issues according to which, different measurements are required. In practice, there is a need for tools and techniques for evaluation of the performances of the adopted mobile agent platforms. Related work proposes a set of performance metrics, slightly different one from the other, and measure different approaches. In this research, a mathematical model is presented that evaluates performance evaluation of different agent platforms and agents interested behavior. The study suggests set of agent platforms to evaluate and finally comparing performance amongst them.