Much existing empirical research on polycentric climate governance (PCG) systems examines small-N examples. In response, we aim to advance studies of PCG by exploring, and reflecting on, the use of large-N data sets for analyzing PCG. We use Python (a programming language) to create a novel data set from the United Nations’ Global Climate Action Portal. This method allows us to quantify key variables for 12,568 businesses located in Organization for Economic Co-operation and Development countries: the number of businesses’ climate commitments, their progress toward meeting those commitments, and businesses’ memberships in “more polycentric” networks via transnational climate initiatives (TCIs). Our analysis of these data reveals that greater interconnectedness may strengthen climate policy performance, since businesses with memberships in TCIs more commonly achieved their commitments. Additional research using these data, and/or similar methods, could be conducted on climate governance and on other areas of international environmental governance, such as mining and oil production.