Accurately anticipating future changes in temperature and precipitation, for example, is crucial for climate impact assessments. Climatologists typically rely on large ensembles of global climate models by combining their outputs into multi-model ensembles. However, this approach struggles to balance global accuracy with local precision, often leading to suboptimal strategies. Although climate simulations provide valuable insights, the representation of extreme events lacks reliability. Distribution-based aggregation methods, such as the recently proposed $\alpha$-pooling approach, address potential biases by statistically weighting and combining the different outputs. The $\alpha$-polling approach is applied to the whole distribution. In this work, we focus on the tail of the distribution and use models from Extreme Value Theory to explore the extent to which methods aggregating climate model output are able to reproduce the tail distribution of observations. We illustrate our methodological proposal by examining the case of two variables: temperature and precipitation intensity.