Eighteen animal, models of depression are reviewed in relation to three sets of validating criteria. Of the 18 models, five could only be assessed for predictive, validity, seven could be assessed for predictive and face validity, and six could potentially have predictive, face and construct validity. Some traditional models (reserpine reversal, amphetamine potentiation) are rejected as invalid; the models with the highest overall validity are the intracranial self-stimulation, chronic stress and learned helplessness models in rats, and the primate separation model.