The paper introduces mclust 5, an updated version of the R package mclust, which is widely used for model-based clustering, classification, and density estimation using Gaussian finite mixture models. The new version includes several enhancements such as new covariance structures, dimension reduction capabilities, model selection criteria, initialization strategies for the EM algorithm, and bootstrap-based inference. These features make mclust a comprehensive and powerful tool for data analysis via finite mixture modeling. The paper discusses the new functionalities, provides examples of their application, and compares mclust with other R packages in terms of popularity and functionality. It also covers topics such as model-based clustering, dimension reduction, model selection, bootstrap inference, and initialization of the EM algorithm. The paper includes detailed explanations, code snippets, and visualizations to illustrate the concepts and demonstrate the practical use of mclust 5.The paper introduces mclust 5, an updated version of the R package mclust, which is widely used for model-based clustering, classification, and density estimation using Gaussian finite mixture models. The new version includes several enhancements such as new covariance structures, dimension reduction capabilities, model selection criteria, initialization strategies for the EM algorithm, and bootstrap-based inference. These features make mclust a comprehensive and powerful tool for data analysis via finite mixture modeling. The paper discusses the new functionalities, provides examples of their application, and compares mclust with other R packages in terms of popularity and functionality. It also covers topics such as model-based clustering, dimension reduction, model selection, bootstrap inference, and initialization of the EM algorithm. The paper includes detailed explanations, code snippets, and visualizations to illustrate the concepts and demonstrate the practical use of mclust 5.