Neoadjuvant immunotherapy plus chemotherapy has ushered in a new era for surgical treatment for patients with NSCLC. This study aimed to examine the efficacy and safety of neoadjuvant immunotherapy plus chemotherapy in NSCLC. Eligible studies were identified from PubMed, Embase, Web of Science, Cochrane Library, ClinicalTrials.gov, and conference meeting abstracts. The endpoints included major pathological response (MPR), complete pathological response (pCR), surgical resection rate, R0 resection, treatment-related adverse events (TRAEs), severe adverse events (SAEs), surgical complications, treatment discontinuation, surgical delay, and treatment-related death. Stata 18 software was used for statistical analysis, and p < 0.05 was considered statistically significant. Twenty-two studies including a total of 1108 patients were eligible for this study. Among the patients who received neoadjuvant immunotherapy plus chemotherapy, the pooled MPR rate was 51% (95% CI [0.44-0.58]), and pCR rate was 34% (95% CI [0.28-0.40]). The pooled surgical resection rate was 85% (95% CI [0.81-0.89]), and the pooled R0 rate was 94% (95% CI [0.91-0.96]). The pooled rate of pathological tumor downstaging was 84% (95% CI [0.79-0.88]), and the pooled rate of pathological nodal downstaging was 38% (95% CI [0.23-0.57]). During the treatment of neoadjuvant immunotherapy plus chemotherapy with or without surgery, the pooled rate of TRAEs (any grade) was 84% (95% CI [0.73-0.91]), and the pooled rate of SAEs was 29% (95% CI [0.21-0.38]). Surgical complications pooled rate was 25% (95% CI [0.14-0.41]). The pooled rate of treatment discontinuation (11%, 95% CI [0.09-0.13]), surgical delay (3%, 95% CI [0.02-0.05]), and treatment-related death (2%, 95% CI [0.02-0.03]) were conducted. Neoadjuvant immunotherapy plus chemotherapy provides a high pathological response, surgical resection rate, R0 resection rate, and pathological downstage rate and has a low risk of increasing the incidence of SAEs, surgical complications, treatment discontinuation, surgical delay, and treatment-related death. The validation of prospective and large sample studies is needed to confirm this conclusion.