A grid devised to evaluate the methodological quality of randomized therapeutic trials is presented. Fourteen items are analysed: description of the principal criterion of assessment, criteria of inclusion, number of subjects seen and excluded, number of subjects randomized to each group, number of subjects excluded who are alive or lost to follow-up and reasons for the fall-outs, blind character of the doctors, patients and persons responsible for the assessment criteria, calculation of the number of subjects required before starting the trial, method of randomization and its blind character, analysis and discussion of covariables, statistical tests used, taking into account of the fall-outs and power of the trials with non-significant results. This grid, used for the analysis of 527 randomized trials, showed that about one-half of them were of mediocre quality, the most frequent defects encountered being the multiplicity of assessment criteria, the lack of description of the subjects excluded, the absence of calculation of the number of subjects required before starting the trial and the small number of subjects in trials with non-significant results.