Aiming at the advanced technology, high development cost and difficult implementation of reliability appraisal test of LM-8 launch vehicle, a method of reliability assessment of small sample based on Bayesian theory is proposed. According to Bayes theorem, various pre-test information is fully utilized to make up for the deficiency of experimental data. Taking Weibull life model, Exponential life model and Binomial life model as three examples of life different distribution types, corresponding mathematical model and numerical calculation method combining Bayesian theory are discussed. Finally, three different types of equipment in the launch vehicle system are selected for reliability evaluation and the results show that the proposed method can make full use of existing information, of which assessment results are superior to the classical method.