Obsessive–compulsive disorder (OCD) is a disabling and common neuropsychiatric condition of poorly known etiology. Many attempts have been made in the last few years to develop animal models of OCD with the aim of clarifying the genetic, neurochemical, and neuroanatomical basis of the disorder, as well as of developing novel pharmacological and neurosurgical treatments that may help to improve the prognosis of the illness. The latter goal is particularly important given that around 40% of patients with OCD do not respond to currently available therapies. This article summarizes strengths and limitations of the leading animal models of OCD including genetic, pharmacologically induced, behavioral manipulation-based, and neurodevelopmental models according to their face, construct, and predictive validity. On the basis of this evaluation, we discuss that currently labeled “animal models of OCD” should be regarded not as models of OCD but, rather, as animal models of different psychopathological processes, such as compulsivity, stereotypy, or perseverance, that are present not only in OCD but also in other psychiatric or neurological disorders. Animal models might constitute a challenging approach to study the neural and genetic mechanism of these phenomena from a trans-diagnostic perspective. Animal models are also of particular interest as tools for developing new therapeutic options for OCD, with the greatest convergence focusing on the glutamatergic system, the role of ovarian and related hormones, and the exploration of new potential targets for deep brain stimulation. Finally, future research on neurocognitive deficits associated with OCD through the use of analogous animal tasks could also provide a genuine opportunity to disentangle the complex etiology of the disorder.