In structural engineering, concrete compressive strength is a fundamental property that is crucial for designing and directly impacts the load-bearing capabilities of concrete elements. The strength of concrete is determined by a variety of factors, such as the water-cement ratio and material properties, that determine its quality. Recently, Artificial Intelligence (AI) techniques have gained significant interest due to their ability to solve a variety of complex problems. To estimate the compressive strength of concrete, this work involves using different machine learning algorithms and evaluating the performance of various models, including Decision Trees (DT), Support Vector Machines (SVM), Artificial Neural Networks (ANN), k-Nearest Neighbors (KNN), and Random Forests (RF), focusing on discovering highly accurate methods. In order to achieve this, a dataset of 1030 experimental results was collected from the existing literature. Concrete compressive strength was calculated using the input parameters of cement, blast-furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and age. To measure their predictive accuracy and reliability, the models were analyzed using key performance metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination R2. The results show that the RF regressor is the most reliable model, achieving the highest R2 value of 0.90, with the lowest MAE of 3.36 MPa and RMSE of 5.06 MPa. In contrast, the KNN regressor showed the lowest accuracy with an R2 of 0.71. These results emphasize the effectiveness of RF in predicting concrete compressive strength, while also highlighting the importance of careful hyperparameter selection to improve the accuracy of models such as KNN, SVR and ANN.