In this study, a benchmarking framework for machine learning (ML)-based solar photovoltaic power generation forecasting has been developed using an open-source Python library called Streamlit. This versatile Streamlit-based tool is designed to facilitate forecasting tasks in various domains. It provides functionalities for data loading, feature selection, relationship analysis, data preprocessing, machine learning model selection, metric selection, training, and monitoring. Users can upload data in different formats, analyze relationships between variables, preprocess data using various techniques, and evaluate the performance of selected ML models based on chosen metrics. The monitoring feature provides insight into the model’s performance. This tool offers a user-friendly interface, making it suitable for a wide range of forecasting applications in smart grids.