This document compares the performance of different data mining tools for anomaly detection in wireless network data. It analyzes four tools: Weka, SPSS, Tanagra, and Microsoft SQL Server's Business Intelligence Development Studio. The same wireless network log data with 1000 instances and 13 attributes is clustered into 3 groups (normal activities, suspicious activities, anomalous activities) using different unsupervised learning algorithms in each tool. The results from each tool are different due to using different distance measures and clustering algorithms. The paper aims to interpret the results from each tool and determine which provides the most accurate performance mapping for the wireless network data.