Background <p>The Naples prognostic score (NPS) has been extensively documented as a promising prognostic biomarker in various malignancies. The objective of this study is to systematically investigate the correlation between the pretreatment NPS and survival outcomes in patients with gastrointestinal (GI) cancer.</p> Methods <p>This meta-analysis was prospectively registered with PROSPERO (CRD42024567576). We conducted a systematic literature search using electronic databases, including Web of Science, PubMed, and Embase, from inception until July 1st, 2024. The primary endpoints assessed were long-term survival outcomes. Pooled hazard ratios (HR) with corresponding 95% confidence intervals (CI) were calculated using a random-effects model during the pooled analysis. Additionally, prediction intervals (PI) were generated to capture the variability of the pooled effect across different study settings.</p> Results <p>A total of 28 studies, including 10,874 patients with GI cancer, were included in this meta-analysis. The results unequivocally demonstrated a significant association between elevated NPS and worse OS, bolstered by the robust PIs. Moreover, the elevated NPS was found to be significantly related to poor DFS, while the evidence remained uncertain due to heterogeneous PIs. Additionally, findings from a single study suggested that a high NPS may be associated with poor CSS.</p> Conclusion <p>Our evidence suggests that the pretreatment NPS could be a valuable prognostic biomarker in GI cancer patients, particularly for OS. This information can be utilized by clinicians to stratify patients and develop personalized treatment plans.</p>