Abstract In this study a non-parametric method of Data Envelopment Analysis (DEA) is used to estimate the energy efficiencies of soybean producers based on eight energy inputs including human labor, diesel fuel, machinery, fertilizers, chemicals, water for irrigation, electricity and seed energy and single output of grain yield. The study also helps to rank efficient and inefficient farmers and to identify optimal energy requirement and wasteful uses of energy. Data were collected using face-to-face surveys from 94 farms in Golestan province which is the most important center of soybean production in Iran. Based on the results, average yield and energy consumption for soybean production were 3233.15 kg ha −1 and 35372.23 MJ ha −1, respectively. Also, the results of DEA application showed that, the technical, pure technical and scale efficiencies of farmers were 0.853, 0.919 and 0.926, respectively. Moreover, energy saving target ratio for soybean production was calculated as 20.12%, indicating that by following the recommendations resulted from this study, about 7116.84 MJ ha −1 of total input energy could be saved while holding the constant level of soybean yield. Also, electrical energy had the highest share (78.08%) from total saving energy, followed by fertilizers (10.46%) and diesel fuel (6.18%) energy inputs.