Compressive strength is one of the most critical performance indicators of high-performance concrete (HPC), playing a key role in the safety, durability, and load-bearing capacity of structures. Due to the time-consuming and costly nature of conventional laboratory testing methods for determining this parameter, the application of intelligent data-driven approaches has gained increasing attention as an efficient and accurate alternative. In this study, to predict the compressive strength of high-performance concrete, two models—Gradient Boosting Regression and Ada Boost Regression—were employed as advanced machine learning algorithms. The dataset used in this research consists of 1,030 experimental HPC samples collected from the University of California, Irvine database, including various mix design parameters such as cement content, water, blast furnace slag, fly ash, superplasticizer, aggregates, and specimen age. Initially, correlation analysis was conducted to examine the relationships between input variables and compressive strength, revealing that cement content, concrete age, and superplasticizer dosage have the strongest positive correlations, while water content exhibits the most significant negative correlation with compressive strength. Subsequently, the proposed model was trained and evaluated using a ten-fold cross-validation strategy. Subsequently, the two proposed models were trained and evaluated using 10-fold cross-validation. The results demonstrated that the Gradient Boosting Regression model possesses higher accuracy and reliability in predicting the compressive strength of high-performance concrete across all evaluation metrics. The findings of this study highlight the strong potential of boosting-based machine learning algorithms as reliable and cost-effective alternatives to traditional experimental methods for the design and performance assessment of advanced concrete materials.