This study explored whether group size and group member characteristics (age, sex, and compensation status) were associated with patient outcomes (changes in pain and disability). Retrospective analyses of outcome data obtained from 2 independently run group cognitive behavioural therapy (CBT) programs for chronic pain (Program A: N = 317 and Program B: N = 693) were conducted. Intracluster correlations were significant in both studies, indicating group-level effects on patient outcomes in both group CBT programs for chronic pain. Mixed modelling revealed that group size and group member characteristics (age, sex, and compensation status) were related to patient outcomes, but not consistently across programs. The results of our analyses confirm the contribution of group composition to individual treatment outcomes in group CBT for chronic pain, and highlight factors that have the potential to contribute to group-level variability in patient outcomes. Further research is needed to identify the mechanisms that account for the impact of group characteristics on the efficacy of CBT for chronic pain.