Networks are important tools used to model problems in realistic worlds, such as social network, protein protein interaction network, brain networks and so on. Uncertainty is an intrinsic property in networks, which comes from various reasons. For example, the randomness of systems, the noisy of measurements, and inaccuracy of information source. To address it, uncertainty can be modeled as probabilities associating edges. And this type of networks are called probabilistic networks. Clustering is one of the critical issues in probabilistic networks. It aims to find hidden community structure where edges are dense within clusters and sparse between clusters. However, there are not many open resources of probabilistic datasets and codes, and there is no general framework to compare new clustering algorithms in probabilistic networks. To fill this gap, we implement algorithms that are not available and collect existing public codes and run it, and evaluate them using different metrics.