BACKGROUND: The switch/sucrose nonfermentable complex mutations (SWI/SNF-mut) are common in non-small cell lung cancer (NSCLC). However, the association of SWI/SNF-mut with the clinical outcomes of immune checkpoint inhibitors (ICIs), particularly of epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs), has not been established. METHODS: We retrospectively collected data of patients at Cancer Hospital Chinese Academy of Medical Sciences. Patients with advanced NSCLC who received programmed cell death protein-1 or programmed cell death ligand 1 (PD-[L]1) inhibitors were included in cohort 1 and those with EGFR mutations (EGFR-mutant) received EGFR-TKIs monotherapy were included in cohort 2. Two reported Memorial Sloan-Kettering Cancer Center (MSKCC) cohorts received immunotherapy alone used as the validation for cohort 1. We analyzed the relationship between SWI/SNF alterations and clinical outcomes in each cohort. RESULTS: In total, 1162 patients were included, of which 230 patients (19.8%) were identified as SWI/SNF-mut with the most common genetic alterations being ARID1A (33.4%) and SMARCA4 (28.3%). In cohort 1 (n = 146), patients with co-mutations of SWI/SNF and Kirsten rat sarcoma oncogene (KRAS) (SWI/SNFmutKRASmut, n = 18) had significantly prolonged progression-free survival (PFS) (8.6 m vs. 1.9 m; hazard ratio [HR],  0.31; 95% confidence intervals [CI], 0.11-0.83; p = 0.032) to PD-(L)1 inhibitors monotherapy, which was consistent with the MSKCC cohorts (not reach [NR] vs. 6.3 m; HR, 0.36, 95% CI, 0.15-0.82; p = 0.016). In cohort 2 (n = 205), ARID1A-mut (n = 16) was associated with improved PFS after EGFR-TKIs (20.6 m vs. 11.2 m; HR, 0.47, 95% CI, 0.27-0.94; p = 0.023). CONCLUSIONS: In advanced NSCLC, patients with SWI/SNFmutKRASmut seem to benefit more from ICIs. Furthermore, ARID1A-mut may provide a protective effect to EGFR-TKIs in EGFR-mutant patients. However, this is a retrospective single-institution analysis that requires further validation by large prospective studies.