•An updated database consisting of 532 UHPC beams that failed by shear is established.•Ten ML models with different algorithms are developed to predict the shear strength of UHPC beams.•The performance of the ML models is evaluated and compared to empirical models.•The ML models are interpreted using the SHAP methods.•The impact of critical features on the shear strength of UHPC beams is identified. To provide more accurate and reliable predictions of the shear strength of ultrahigh-performance concrete (UHPC) beams, in this study, the machine learning (ML) approaches were employed to develop the data-driven models, and the ML models were interpreted using the Shapley additive explanations (SHAP) method. It was found that the ensemble models, particularly CatBoost, outperform individual ML models and traditional empirical models. The geometric dimensions and shear span-to-depth ratio were the most influential features for predicting the shear strength of UHPC beams, followed by the parameters of reinforcement and material properties of the UHPC.