This study conducts a comparative analysis of three initial field-driven forecast products (denoted as EC_PG, CMA_PG, and NCEP_PG, collectively known as the three Pangu models) of the Pangu-Weather model, which are based on the European Centre for Medium-Range Weather Forecasts (ECMWF), the China Meteorological Administration's Global Forecast System (CMA-GFS), and the National Centers for Environmental Prediction's Global Forecast System (NCEP-GFS). The forecast performance of the Pangu-Weather model is evaluated preliminarily against the ECMWF forecast products (denoted as EC) for surface and upper-air meteorological elements in Shandong from August to December 2024. The main results are as follows: (1) 2m temperature: the EC_PG model has the best RMSE and ACC indexes within the 168-hour forecast horizon; compared with EC, the three Pangu models can effectively reduce the nighttime high errors and improve the underestimation for the Shandong plains at 14:00 p.m. (2) 10m wind: EC_PG leads the wind speed and direction scores within the 168-hour forecast horizon; compared with EC, the three Pangu models can effectively reduce the night-time high wind speed error; the three Pangu models and EC show an overall trend of overestimation of wind speed at night and underestimation during the day. (3) Upper-air (500hPa, 700hPa, and 850hPa) elements: Within the 72-hour forecast period, the three Pangu models outperform the EC at all levels of specific humidity, with CMA_PG performing the best. Among the three Pangaea models, EC_PG has the best performance in forecasting temperature and wind speed in all layers; compared with EC, EC_PG has significantly improved the forecast of temperature in all layers at Zhangqiu station, and the forecast of wind speed at 850hPa at Qingdao station is not as good as EC. Overall, among the three Pangu models evaluated, EC_PG has the optimal integrated forecasting performance; its forecasting ability is significantly better than that of the EC model for key meteorological elements such as 2m temperature, 10m wind speed and specific humidity in each layer (500hPa, 700hPa and 850hPa). This study provides initial ideas for doing systematic and comprehensive tests of meteorological macromodels in the future.