This article provides an experimental analysis of the possibilistic handling of default rules. Three different nonmonotonic consequence relations are considered: minimum specificity inference (MSP), lexicographical closure (LC), and epsilon-belief functions (LCD). The latter was initially proposed within the belief function framework; it is rephrased here within a possibility theory framework. These three consequence relations share some properties but differ on others, which allows for an experimental test of their psychological plausibility. Actual human reasoning is shown to manifest properties which are similar to those of LC but not to those of MSP or LCD.