The aim of this study was to determine the impact of complete response (CR) to systemic therapy on survival. We reviewed the cases of 647 chemo-naive patients with metastatic melanoma who were treated with cisplatin-vinblastine-dacarbazine or cisplatin-taxol-dacarbazine alone, or cisplatin-vinblastine-dacarbazine together with interferon α or interleukin-2 plus interferon α. After excluding patients with uveal melanoma and patients who had resection of metastases, 567 patients were eligible to participate in this analysis. An event chart is presented for the 51 patients with CR and for three random samples of patients without CR. We compared overall survival of responders versus nonresponders using response as a time-dependent covariate in a Cox proportional hazards model. In addition, we used the landmark method, choosing 6 months as the landmark. Logistic regression techniques were used to determine factors associated with CR to therapy. All P values were 2-tailed and considered significant at α less than 0.05. Analyses were conducted using SAS for Windows. In this analysis, CR was associated with patients who were younger, male, and who had better performance status, lower M-stage, no liver metastases, and no visceral sites involved, normal LDH and had received biochemotherapy. While accounting for these factors, the relationship between CR and survival remained statistically significant, suggesting a causal relationship between response and survival. Using 6-month landmark analysis method, we still find a significant difference in overall survival between response groups, favoring patients who achieved CR with systemic therapy. In conclusion, CR to systemic therapy is associated with long-term survival in patients with stage IV melanoma.