To analyze the effect of the weight of water resources carrying capacity evaluation index on its evaluation results, taking Xinjiang, China, as an example, this paper selects nine evaluation indicators related to the water resources system, social and economic development system, and ecosystem. The analytic hierarchy process (AHP), the coefficient of variation method, the geometric average method, and Murphy’s averaging method are used to calculate the weight of evaluation indexes. Subsequently, the fuzzy comprehensive evaluation model is used to evaluate the water resources carrying capacity of Xinjiang from 2011 to 2015. The results show that Murphy’s averaging method improves the shortcomings of single subjective or objective weight values and rankings that are inconsistent with the actual situation. The water resources carrying capacity of the study area was in a weak overload state for all years except 2014, and the water resources carrying capacity showed a downward trend year by year. According to the actual situation of precipitation change, Murphy’s averaging method is more reasonable in terms of index assignment and evaluation results. This method is more suitable for the water resources carrying capacity evaluation in Xinjiang.