The purpose of the present research is to investigate whether virtual agents can help enhance participants’ performance, effort and motivation in mathematics. We hypothesize that a minimal amount behavioral realism induced by display of rapport is necessary for any social effects to occur in human-computer interaction. Further, we examine whether social facilitation effects occur depending on the gender of the participants and the interacting virtual agents. In a 2x2 between subjects design, participants interacted with a male or female virtual agent that either displayed rapport or no rapport. Our results confirm that gender plays a role when interacting with virtual agents that are capable of establishing rapport. Participants’ performance and effort were significantly enhanced when interacting with an agent of opposite gender that displayed rapport. Our results have implications on designing agents for education and training purposes.