Addressing the issues of non-stationarity and transposing models parameters over time period under changing climate conditions is one of the research topics of the HYDRO team at Irstea (Antony). For example, Coron et al. (2012) generalized the split-sample test on 10-year sliding windows, using several hydrological models. The GR4J model will be applied to all the study cases prepared for this workshop, and the evaluation protocol described on the non-stationarities.irstea.fr website will be followed (levels 1 and 2). Other hydrological models will be tested (inspired from MORDOR, HBV and TOPMODEL models). We will try to understand the behaviours of the models based on the evaluation protocol. Trying to obtain a constant bias over time instead of a bias changing according to the period can for example be considered as an indicator of reliability of the model for future conditions. Our main results will be presented. Ref.: Coron, L., V. Andréassian, C. Perrin, J. Lerat, J. Vaze, M. Bourqui, and F. Hendrickx (2012), Crash testing hydrological models in contrasted climate conditions: An experiment on 216 Australian catchments, Water Resour. Res., 48, W05552, doi:10.1029/2011WR011721.