Democratic theorists and social epistemologists often celebrate the epistemic benefits of diversity. One of the cornerstones is the ‘diversity trumps ability’ theorem and simulation results by Hong and Page (2004). Ironically, the interplay between diversity and ability is rarely studied in radically different frameworks. In fact, Hong and Page’s landscape models apply predominantly to decision problems where the groups must find the optimal decision among thousands of options. Their landscape models are ineffective in binary and sparse decision problems (i.e., involving a few options). To fill this gap, I will introduce a new source reliability framework for binary decision problems, where agents rely on imperfect sources to identify the best solution. I use this new source reliability framework to assess whether, when, and (if so) why diversity trumps expertise in binary decision problems