<p>High-entropy alloy (HEA) bonded cemented carbides is really a rapidly evolving topic with investigation at the global level introducing new ideas and application at a high speed. However, the design of HEA bonded hardmetals based on “trial and error method” or “semi-empirical method” is low efficiency and high cost. During the past decade or so, ML Artificial intelligence (AI)-based machine learning (ML) techniques have been widely employed to investigate the properties of various types of alloys. This paper performed research on the prediction of Vickers hardness and fracture toughness of WC-HEAs exploiting ML techniques through employing three machine learning models including Support Vector Machines (SVM), Random Forest (RF) and Artificial Neural Networks (ANN). The models were evaluated on the basis of goodness-of-fit (<i>R</i>²), mean absolute error (MAE) and root mean square error (RMSE) in assessing the model performance and the best performing RF model was optimized. Finally, the hardness and toughness of 65 groups of WC-HEAs were successfully predicted by the optimized RF model. It was demonstrated that WC-HEAs such as WC-FeMoTiCu, WC-CoFeNiAlMoTiCu and WC-CoCrNiMoMnTiCu presented optimum hardness and toughness. Furthermore, it was discovered that WC-HEA containing four elements, Al, Mo, Ti and Cu, showed greater Vickers hardness, while the alloys containing four elements, W, C, Co and Ni, exhibited higher fracture toughness values. This contributes to the timely and cost-effective design of new alloys by materials engineers and researchers, and provides valuable insights for future alloy design and development.</p>