Abstract: Aiming at the problems of single index and lack of expert experience in the current performance evaluation of CNC systems, a comprehensive evaluation method for machining capability and efficiency of CNC systems based on typical multi-feature machining test pieces is proposed. Firstly, a test piece integrating typical features such as curved surfaces, sharp corners, grooves and inclined planes is designed. In accordance with existing specifications, scoring criteria are established from three dimensions: machining accuracy, surface quality and machining efficiency. Secondly, the opinions of multiple experts are introduced, and the weights of each scoring criterion are determined combined with the two-level fuzzy comprehensive evaluation method. Combined with the measured data of the test pieces, the particle swarm optimization algorithm is used to optimize the weights of each evaluation point. Finally, experiments are carried out, and two test pieces are machined with different parameters. The experimental results show that the proposed method effectively and reasonably quantifies the machining capability and efficiency of CNC systems for different typical features, and provides an accurate and relatively comprehensive reference for evaluating the performance of CNC systems in machining different features.