Background: Only about half of all patients with anxiety disorders or major depression respond to cognitive behaviour therapy (CBT), even though this is an evidence-based treatment. Personalized treatment offers an approach to increase the number of patients who respond to therapy. The aim of this study was to examine predictors and moderators of (differential) treatment outcomes in transdiagnostic versus diagnosis-specific group CBT. Methods: A sample of 291 patients from three different mental health clinics in Denmark was randomized to either transdiagnostic or diagnosis-specific group CBT. The study outcome was the regression slope of the individual patient's repeated scores on the WHO-5 Well-being Index. Pre-treatment variables were identified as moderators or predictors through a two-step variable selection approach. Results: While the two-step approach failed to identify any moderators, four predictors were found: level of positive affect, duration of disorder, the detachment personality trait, and the coping strategy of cognitive reappraisal. A prognostic index was constructed, but did not seem to be robust across treatment sites. Conclusions: Our findings give insufficient evidence to support a recommendation of either transdiagnostic or diagnosis-specific CBT for a given patient or to predict the response to the applied group therapies.