WHO recommendations for dengue diagnosis require laboratory facilities. Antibody-based rapid diagnostic tests (RDTs) have performed poorly, and clinical diagnosis remains the mainstay in dengue-endemic countries. We evaluated a combination antigen-antibody RDT for point-of-care testing in a high-prevalence setting. In this prospective cohort study, adults were enrolled from a tertiary infectious disease centre for evaluation of undifferentiated febrile illness from October 2011 to May 2012. SD Bioline Dengue Duo was evaluated at point-of-care against a WHO-based reference standard of viral isolation, RT-PCR, NS1-, IgM-, and IgG-ELISA. 246 adults were enrolled (median age 34 years, range 18–69), of which 197 could be confirmed definitively as either dengue or non-dengue. DENV-2 was the predominant serotype (79.5%) and the ratio of primary to secondary cases was 1:1.1. There were no test failures and minimal interobserver variation with a Fleiss’ kappa of 0.983 (95% CI 0.827–1.00). Overall sensitivity and specificity were 93.9% (95% CI 88.8–96.8%) and 92.0% (95% CI 81.2–96.9%) respectively. Using WHO clinical criteria alone for diagnosis had similar sensitivities (95.9%, 95% CI 91.4–98.1%) and lower specificities (20.0%, 95% CI 11.2–33.0%). No significant difference in performance was found when testing early versus late presenters, primary versus secondary cases, or DENV-1 versus DENV-2 infections. The use of a combination RDT fulfills WHO ASSURED criteria for point-of-care testing and can enhance dengue diagnosis in an endemic setting. This has the potential to markedly improve clinical management of dengue in the field.