Deregulation policy has caused some changes in the concepts of power systems reliability assessment and enhancement. In this paper, generation reliability is considered and a method for its assessment using intelligent systems is proposed. Also, because of power market and generators' forced outages stochastic behavior, Monte Carlo Simulation is used for reliability evaluation. Generation reliability, merely focuses on interaction between generation complex and load. Therefore, in this research, based on market type and its concentration, reserve margin and various future times, a Neuro-Fuzzy system is proposed for evaluation of generation reliability which is valid and usable for all kinds of power pool markets. Finally, the proposed method is assessed on IEEE-Reliability Test System with satisfactory results. It will be shown that if market becomes more concentrated or price elasticity of demand increases, reliability will improve.