Eighteen global climate models (GCMs) are compared to reference data for the present, the mid-Holocene (MH) and the last glacial maximum (LGM) for the Antarctic region. For the present, the reference data come from a regional climate model. GCM results for the past are compared to ice core data. The goal of this study is to find the best GCM to model the evolution of the Antarctic Ice Sheet. Because temperature and precipitation are the most important climate variables when modelling the evolution of an ice sheet, these two variables are considered in this paper. In general, present-day temperature is simulated well, but precipitation is overestimated compared to the reference state. Some other findings are that the air above ice shelves is too warm and precipitation in the coastal region of the western peninsula is underestimated by the models, as compared to the present-day reference state. Furthermore, model biases play an important role in simulating the past, as they are often larger than the change in temperature or precipitation between the past and the present. Considering the results for the present-day as well as for the MH and the LGM, the best performing models are HadCM3 and MIROC 3.2.2.