Introduction: Although cognitive behavioral therapy (CBT) effectively treats obsessive-compulsive disorder (OCD), many patients refuse CBT or drop out prematurely, partly because of anxiety regarding exposure and response prevention (ERP) exercises. Inference-based cognitive behavioral therapy (I-CBT) focuses on correcting distorted inferential thinking patterns, enhancing reality-based reasoning, and addressing obsessional doubt by targeting underlying dysfunctional reasoning, without incorporating an ERP component. We hypothesized that I-CBT would be non-inferior to CBT. Additionally, we hypothesized that I-CBT would be more tolerable than CBT. Methods: 197 participants were randomly assigned to 20 sessions CBT or I-CBT and assessed at baseline, posttreatment, and 6 and 12 months’ follow-up. The primary outcome was OCD symptom severity measured using the Yale-Brown Obsessive-Compulsive Scale (Y-BOCS; non-inferiority margin: 2 points). The secondary outcome, treatment tolerability, was assessed using the Treatment Acceptability/Adherence Scale (TAAS). A linear mixed-effects model was used to assess the non-inferiority of the primary outcome and superiority of secondary outcomes. Results: Statistically significant within-group improvements in the primary and secondary outcomes were observed in both treatments. No statistically significant between-group differences in Y-BOCS were found at any assessment point, but the confidence intervals exceeded the non-inferiority threshold, making the results inconclusive. The estimated mean posttreatment TAAS score was significantly higher in the I-CBT group than in the CBT group. Conclusion: While both CBT and I-CBT are effective for OCD, whether I-CBT is non-inferior to CBT in terms of OCD symptom severity remains inconclusive. Nevertheless, I-CBT offers better tolerability and warrants consideration as an alternative treatment for OCD.