Abstract: Evaluation is an important component in the development and application of numerical models. In recent years, as the models have grown increasingly complex, the demand for fine forecasting has also grown, leading to rapid advancements in model verification and evaluation methods. This paper begins by surveying both domestic and international research progresses in numerical model evaluation and verification, and then delves into significant contributions made by Chinese scholars in recent years to the evaluation of dynamic frameworks of new generation numerical models, the multi-temporal and spatial variability of East Asian monsoon, and the assessment of weather and climate around the Qingzang Plateau. Since precipitation is identified as a key process, the present paper presents an in-depth review of the evaluation efforts concerning precipitation diurnal variation and process evolution. Finally, future potential research directions are proposed, including the integration of multi-source observation data, the development of evaluation techniques tailored to various models and application contexts, and the synergy between model evaluation and machine learning technologies.