There is no formalised theory of sustainable urban mobility systems. Observed patterns of urban mobility are often considered unsustainable; but we don’t know what a city with sustainable mobility should look like. In this paper we explore the characteristics of sustainable urban mobility systems through the technique of Bayesian networks. Using data from seventy-five world cities, we develop a probabilistic model of the city-transportation-environment interaction in the form of a Bayesian network. The Bayesian model indicates that the city with sustainable mobility is most probably a dense city with highly efficient transit and multimodal mobility. It produces high levels of accessibility without relying on a fast road network. The realization of sustainability objectives for urban mobility is probably compatible with all socioeconomic contexts. By measuring the distance of world cities from the inferred sustainability profile, we finally derive a geography of sustainability for mobility systems. The cities closest to the sustainability profile are in Central Europe as well as in affluent countries of the Far East. Car-dependent American cities are the farthest from the desired sustainability profile.