Meteorological data is the essential data of ecological, resources, environment, global change and other research areas. However, the meteorological in Mountain are rare and complex than in plain. And acquiring precise spatial grid meteorological data has been a difficult task in this area. Anusplin and Cokriging interpolation method are one of the most common method that considering terrain'impacts during the Meteorological Spatial Interpolation. To ensure which one is more suit for complex area, we take the most complex mountain area (the Southeastern margin of the Qinghai-Xizang Plateau) as study area to compare the two methods. Based on Anusplin and Cokriging meteorological spatial interpolation method separately, combined with the terrain data and 96 meteorological stations in the southeastern margin of the Qinghai-Xizang Plateau region, 250 m resolution average temperature and total precipitation interpolated surfaces in 2010 was obtained. With the cross-validation method comparison method, the interpolation accuracy of Anusplin and Cokriging was compared, and the spatial distribution of errors was analyzed. Applying relevant information, accurate of the two methods in local area where the result of interpolation are quite different was qualitatively analyzed. Through this, the method which is more suit for this area is sought out and the applicability of Anusplin in this area was assessed. The results showed that, Anusplin interpolation outperformed Cokriging. In the comparing of mean square error(RMSE) of the interpolation of temperature and precipitation, Anusplin temperature is only 0. 82 ℃ and Cokriging is 1. 45 ℃, the RMSE of precipitation of the two methodes are consistent, but Anusplin are superior to Cokriging in the highly heterogeneous area. Therefore Anusplin can achieve better results than Cokriging, indicating that Anusplin is suit for the interpolation in Southeastern Margin of Qinghai-Xizang Plateau.