Purpose The benefit of high-dose chemotherapy with autologous stem-cell transplantation (ASCT) as first-line treatment in patients with diffuse large B-cell lymphomas is still a matter of debate. To address this point, we designed a randomized phase III trial to compare rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP)-14 (eight cycles) with rituximab plus high-dose sequential chemotherapy (R-HDS) with ASCT. Patients and Methods From June 2005 to June 2011, 246 high-risk patients with a high-intermediate (56%) or high (44%) International Prognostic Index score were randomly assigned to the R-CHOP or R-HDS arm, and 235 were analyzed by intent to treat. The primary efficacy end point of the study was 3-year event-free survival, and results were analyzed on an intent-to-treat basis. Results Clinical response (complete response, 78% v 76%; partial response, 5% v 9%) and failures (no response, 15% v 11%; and early treatment-related mortality, 2% v 3%) were similar after R-CHOP versus R-HDS, respectively. After a median follow-up of 5 years, the 3-year event-free survival was 62% versus 65% ( P = .83). At 3 years, compared with the R-CHOP arm, the R-HDS arm had better disease-free survival (79% v 91%, respectively; P = .034), but this subsequently vanished because of late-occurring treatment-related deaths. No difference was detected in terms of progression-free survival (65% v 75%, respectively; P = .12), or overall survival (74% v 77%, respectively; P = .64). Significantly higher hematologic toxicity ( P < .001) and more infectious complications ( P < .001) were observed in the R-HDS arm. Conclusion In this study, front-line intensive R-HDS chemotherapy with ASCT did not improve the outcome of high-risk patients with diffuse large B-cell lymphomas.