To survive in its environment, an animat must have a be-havior that is not too disturbed by noise or any other distractor. Itsbehavior is supposed to be relatively unchanged when testedon similarsituations. Evolving controllers that are robust and generalize well oversimilar contexts remains a challenge for several reasons. One of themcomes from the evaluation: how to check a controller for suchproper-ties? The fitness may evaluate a distance towards a behavior known tobe robust, but such an example is not always available. An alternative isto test the behavior in multiple conditions, actually as many as possible,to avoid overfitting, but this significantly slows down the search process. This issue is expected to become even more critical when evolvingbehaviors of increasing complexity. To tackle this issue, we propose toformulate it as a problem of behavioral consistency in different contexts.We then propose a fitness objective aimed at explicitly rewarding behav-ioral consistency. Its principle is to define different sets of contexts andcompare the evolved system behavior on each of them. The fitness func-tion thus defined aims at rewarding individuals that exhibitthe expected consistency. We apply it to the evolution of two simple computational neuroscience model