Museum researchers have long acknowledged the importance of dialogue in informal learning, particularly for open-ended exploratory exhibits. Novel interaction techniques like full-body interaction are appealing for these exploratory exhibits, but designers have not had a metric for determining how their designs are supporting productive learning talk. Moreover, with the incorporation of digital technologies into museums, researchers and designers now have the opportunity for in situ A/B testing of multiple exhibit designs not previously possible with traditionally constructed exhibits, which once installed were difficult and expensive to iterate. Here we present a method called Scoring Qualitative Informal Learning Dialogue (SQuILD) for quantifying idiosyncratic social learning talk, in order to conduct in situ testing of group learning at interactive exhibits. We demonstrate how the method was applied to a 2 × 2 experiment varying the means of control (full-body vs. handheld tablet controller) and the distribution of control (single-user-input vs. multi-user-input) of an interactive data map exhibit. Though pilot testing in the lab predicted that full-body and multi-input designs would best support learning talk, analysis of dialogue from 119 groups' interactions revealed surprising nuances in the affordances of each. Implications for embodied interaction design are discussed.