This paper analyzes the design of innovation contests when the quality of an innovation depends on the research approach, but the best approach is unknown. Inducing a variety of research approaches is desirable because it generates an option value. We show that suitable contests can induce such variety. The optimal contest is a bonus tournament, where suppliers can choose only between a low bid and a high bid. We then compare the optimal contest to other commonly studied institutions, such as scoring auctions and fixed-prize tournaments.