High-dose chemotherapy followed by autologous hematopoietic cell transplantation (HCT) improves outcomes in relapsed lymphoma, but the relative efficacy of different preparative regimens is not well defined. We included patients undergoing autologous HCT using BEAM (carmustine, 300 mg/m2, etoposide, cytarabine, and melphalan) or BEP (carmustine 600 mg/m2, etoposide, and cisplatin) between January 2004 and December 2013; 65 patients received BEP and 64 patients BEAM. Both cohorts were similar for advanced-stage disease, extranodal and bulky disease, and prior therapies. Median neutrophil and platelet engraftment was 10 and 20 days for both regimens, respectively. Febrile neutropenia, serum creatinine concentration increase, and electrolyte abnormalities were more frequent with BEP. Incidence of carmustine pneumonitis was not higher with BEP, likely the result of corticosteroid prophylaxis, although 2 cases of fatal pneumonitis were observed after BEP. One-year nonrelapse mortality was 6.8% after BEP and 0% after BEAM (P = .379). After a median follow-up of 39.4 months (range, 1 to 128), 4-year rates of overall survival (OS) after BEP and BEAM were 80.4% and 72.3%, respectively (P = .611). Diffuse large B cell lymphoma patients transplanted after early relapse post-rituximab-based first-line therapy presented 3-year rates of OS and progression-free survival (PFS) of 73.8% and 65%, respectively. There were no statistically significant differences in the OS and PFS of follicular lymphoma, mantle cell lymphoma, or Hodgkin lymphoma. BEP is a valid alternative to BEAM in autologous HCT. Although associated with more renal and electrolytic toxicities, BEP results in similar disease control and long-term survival as BEAM. Prospective studies are needed to confirm whether intensification of conditioning regimens for autologous HCT can improve disease control in high-risk relapsed lymphoma patients.