Using the latest developments from the evaluation literature, namely the technique of matching, this paper shows a positive, but lower than previously thought, effect of microfinance on expenditure per capita, supply of labour, and level of school enrolment for boys and girls. For instance, participants spend 3 per cent more on average than non-participants in control villages. This paper also takes into account repayment delays to calculate the cost of credit provision. It shows how a better investigation at the individual level of the benefits brought and the cost borne could help microfinance institutions to better select their customers.