Batesian mimicry-resemblance of a toxic model by an edible mimic-depends on deceiving predators. Mimetic advantage is considered to be dependent on frequency because an increase in mimic abundance leads to breakdown of the warning signal. Where multiple toxic species are available, batesian polymorphism is predicted-that is, mimics diversify to match sympatric models. Despite the prevalence of batesian mimicry in nature, batesian polymorphism is relatively rare. Here we explore a poison-frog mimicry complex comprising two parapatric models and a geographically dimorphic mimic that shows monomorphism where models co-occur. Contrary to classical predictions, our toxicity assays, field observations and spectral reflectances show that mimics resemble the less-toxic and less-abundant model. We examine ``stimulus generalization'' as a mechanism for this non-intuitive result with learning experiments using naive avian predators and live poison frogs. We find that predators differ in avoidance generalization depending on toxicity of the model, conferring greater protection to mimics resembling the less-toxic model owing to overlap of generalized avoidance curves. Our work supports a mechanism of toxicity-dependent stimulus generalization, revealing an additional solution for batesian mimicry where multiple models coexist.