This study examines the performance of AutoRegressive Integrated Moving Average (ARIMA) and the Seasonal AutoRegressive Integrated Moving Average (SARIMA) models in rainfall models and forecasts in selected locations in Western Nigeria. This is with the view of assessing these two widely used models to ascertain how well they suite the varied climatic situation across the area. The data for the study is rainfall data ranging from 1982 to 2023 sourced from the archive of the National Aeronautics and Space Administration. Row time series were plotted in R and were converted to time series object. The data was automatically fitted using auto.arima functions with the forecast plotted appropriately. Statistical analyses, including stationarity test, ACF and differencing were also done. For forecasting reliability tests, the data were split into training (1982–2014) and testing (2015–2023). Thereafter, the model performance was assessed using standard metrics such as AIC, BIC, log-likelihood, and Ljung-Box Q statistics, with diagnostic plots validating residual independence. While the result revealed a close performance between two models, SARIMA outperformed the ARIMA with seasonality. This study concludes that SARIMA is superior to ARIMA in rainfall modelling for the study area.