This paper analyses the statistical distribution of war size. We find strong support for a Pareto-type distribution (power law) using data from different sources (COW and UCDP) and periods. A power law describes accurately the size distribution of all wars, but also the distribution of the sample of wars in any given period. The estimated Pareto exponent is always less than 1, indicating that the distribution is heavy-tailed; this means that the war average loss is controlled by the largest conflicts. Furthermore, the study of battle deaths’growth rates reveals a clear decreasing pattern; the growth of deaths declines faster the greater the number of initial deaths.