The performance of an anaerobic hybrid reactor (AHR) for treating penicillin-G wastewater was investigated at the ambient temperatures of 30-35 degrees C for 245 days in three phases. The experimental data were analysed by adopting an adaptive network-based fuzzy inference system (ANFIS) model, which combines the merits of both fuzzy systems and neural network technology. The statistical quality of the ANFIS model was significant due to its high correlation coefficient R(2) between experimental and simulated COD values. The R(2) was found to be 0.9718, 0.9268 and 0.9796 for the I, II and III phases, respectively. Furthermore, one to one correlation among the simulated and observed values was also observed. The results showed the proposed ANFIS model was well performed in predicting the performance of AHR. (C) 2011 Elsevier Ltd. All rights reserved.