Surveys are required to locate previously unknown occurrences of threatened species. To optimize efficiency of species-at-risk surveys, I used species distribution models for 22 rare plants throughout southern Ontario to predict the best possible survey locations among individual 1-ha pixels. For each pixel, I weighted model outputs by accuracy and species rarity to create an efficiency value. Based on efficiency values, I conducted field surveys in multi-species cells, "MSC" (areas with high predicted efficiency for multiple species) and in single species cells, "SSC" (areas with high probability for only one species) to determine the utility of multi-species survey optimization. MSC were over two times more likely to have at least one threatened plant species discovered than SSC. Efficiency ranks were also useful in directing surveyors toward incidental discoveries of other rare species that were not modeled. This technique can help direct surveys to more efficiently find threatened species occurrences.