There are increasing incidences of elderly patients with recurrent or metastatic head and neck squamous cell carcinoma (R/M HNSCC). However, the treatment is not yet established. We conducted a propensity score matching analysis to evaluate the efficacy and safety of tegafur–uracil versus 5-fluorouracil in combination with cisplatin plus cetuximab in elderly patients with R/M HNSCC. Elderly patients with R/M HNSCC treated with cetuximab-containing chemotherapy were recruited into this study. In order to reduce the selection bias, propensity score matching was performed. Kaplan–Meier curves were plotted for progression-free survival (PFS) and overall survival (OS). Toxicities were graded according to the National Cancer Institute’s Common Terminology Criteria V3.0. After propensity sore matching, 54 patients with tegafur–uracil, cisplatin plus cetuximab (UPEx), and 54 patients with 5-fluorouracil, cisplatin plus cetuximab (EXTREME) were identified. The median PFS was 5.4 months in UPEx and 5.8 months in EXTREME (p = 0.451). The median OS was 10.8 months in UPEx and 10.2 months in EXTREME (p = 0.807). The overall response rate (ORR) and disease control rate (DCR) were insignificant in both arms, accounting for 61% versus 59% (p = 0.680) and 72% versus 70% (p = 0.732) in the UPEx arm and the EXTREME arm, respectively. A multivariate analysis showed that age and ECOG PS were, independently, predictors. Grade 3/4 adverse events were much fewer in UPEx than in EXTREME (p < 0.001). Both cetuximab-containing chemotherapies are effective in elderly patients with R/M HNSCC. Safety profiles are improved when tegafur–uracil is substituted for 5-fluorouracil. Further prospective studies are warranted to validate our conclusions.