Decades of research have examined the consequences of disagreement, both negative (harm to relationships) and positive (fostering learning opportunities). Yet the psychological mechanisms underlying disagreement judgments themselves are poorly understood. Much research assumes that disagreement tracks divergence: the difference between two individuals’ beliefs with respect to a proposition. We test divergence as a theory of interpersonal disagreement through two experiments (N = 60, N = 60) and predictive models. Our data and modeling show that judgments of disagreement track divergence, but also the direction and extremity of beliefs. Critically, disagreement judgments track key social judgments (e.g., inferences of warmth, competence, and bias) above and beyond divergence, with notable variation across domains.