This paper presents the first Antarctic meteor radar temperature estimates. These temperatures have been derived from meteor diffusion coefficients using two techniques: pressure model and temperature gradient model. The temperatures are compared with a temperature model derived using colocated OH spectrometer measurements and Northern Hemisphere rocket observations. Pressure model temperatures derived using rocket-derived pressures show good agreement with the temperature model, while those derived using Mass Spectrometer and Incoherent Scatter (MSIS) and CIRA model pressures show good agreement in winter but poor agreement in summer. This confirms previous studies suggesting the unreliability of high-latitude CIRA pressures. The temperature gradient model temperatures show good agreement with the temperature model but show larger fluctuations than the pressure model temperatures. Meteor temperature estimates made during the Southern delta-Aquarids meteor shower are shown to be biased, suggesting that care should be taken in applying meteor temperature estimation during meteor showers. On the basis of our results we recommend the use of the pressure model technique at all sites, subject to determination of an appropriate pressure model.