Abstract This article aims to analyze the impact of bonding capital and bridging capital on the scientific results of research groups. The paper contributes to the literature on social capital by going beyond the idea of a linear relationship and reviews the balance between the advantages and disadvantages of bonding capital and its interaction with bridging capital. An empirical study was carried out with 1127 Colombian university research groups from the field of engineering and technology. Hierarchical regression analysis was used to test the proposed hypotheses. The results show that the benefits of bonding social capital are maintained up to a level of centrality, above which the returns of the groups are reduced, adopting an inverted U shape. Moreover, when the members of the research groups diversify their research activities and fulfil relationships that go beyond the limits of their group, this curvilinear relationship is moderated, improving the opportunity to successfully exploit the social capital derived from dense and cohesive ties. The novel contribution of this study lies in linking different types of social capital —bonding and bridging capital—to test their impact on the results of the research groups and in the proposal and testing of a moderate curvilinear relationship, which allows us to advance in this line of research.