The application of a new quantitative method of studying the author's style of literary texts is examined. The method is based on computer analysis of the statistics of numerals occurring in texts. It is shown that quantitative and ordinal numerals used by the author in the (fiction) text are individual for each author; their aggregate is a characteristic trait that distinguishes the texts of different authors. A comparative analysis of literary texts by I.A. Bunin and A.I. Kuprin is carried out; to verify the methodology, the works of F.K. Sologub and M.P. Artsybashev are additionally studied. The results of the analysis were subjected to hierarchical clustering, which correctly divided the texts according to authorship and genre.