This secondary analysis from the Prevention of Recurrent Episodes of Depression with Venlafaxine Extended Release (ER) for Two Years (PREVENT) study compared the efficacy of venlafaxine ER and fluoxetine for the prevention of recurrence in patients with a history of recurrent major depressive disorder (MDD). Patients received double-blind treatment with venlafaxine ER (75–300 mg/d) or fluoxetine (20–60 mg/d) for 10 weeks (acute phase). Responders (17-item Hamilton Rating Scale for Depression [HAM-D17] score ≤12 and ≥50% reduction from baseline) continued on the same treatment during the 6-month continuation phase. At the start of the first and second 12-month maintenance phases, venlafaxine ER responders were randomly assigned to receive venlafaxine ER or placebo, whereas patients receiving fluoxetine continued to receive fluoxetine throughout both maintenance phases. The primary outcome was time to recurrence (HAM-D17 > 12, reduction in HAM-D17 score ≤ 50% from acute baseline, and meeting DSM-IV criteria for a diagnosis of MDD), which was assessed using Kaplan–Meier estimates. Using the primary definition of recurrence, the estimated probability of not experiencing a recurrence was 71.9% for venlafaxine ER (n = 160) and 55.8% for fluoxetine (n = 99) across 24 months of maintenance treatment. For this primary analysis, the overall effect of venlafaxine ER treatment was not statistically significant (p = 0.399) compared with fluoxetine; however, a significant treatment-by-time interaction was observed (p = 0.034). No significant between-group differences were observed with any of the secondary efficacy variables. Venlafaxine ER and fluoxetine were similarly well tolerated across 2 years of maintenance-phase therapy.