Background Laparoscopy-assisted gastrectomy (LG) is rapidly gaining popularity owing to its minimal invasiveness. Previous studies have found that compared with two-dimensional (2D)-LG, three-dimensional (3D)-LG showed better short-term outcomes. However, the long-term oncological outcomes in patients with locally resectable gastric cancer (GC) remain controversial. Methods In this noninferiority, open-label, randomized clinical trial, a total of 438 eligible GC participants were randomly assigned in a 1:1 ratio to either 3D-LG or 2D-LG from January 2015 to April 2016. The primary endpoint was operating time, while the secondary endpoints included 5-year overall survival (OS), disease-free survival (DFS), and recurrence pattern. Results Data from 401 participants were included in the per-protocol analysis, with 204 patients in the 3D group and 197 patients in the 2D group. The 5-year OS and DFS rates were comparable between the 3D and 2D groups (5-year OS: 70.6% vs. 71.1%, Log-rank P  = 0.743; 5-year DFS: 68.1% vs. 69.0%, log-rank P  = 0.712). No significant differences were observed between the 3D and 2D groups in the 5-year recurrence rate (28.9% vs. 28.9%, P  = 0.958) or recurrence time (mean time, 22.6 vs. 20.5 months, P  = 0.412). Further stratified analysis based on the type of gastrectomy, postoperative pathological staging, and preoperative BMI showed that the 5-year OS, DFS, and recurrence rates of the 3D group in each subgroup were similar to those of the 2D group (all P  > 0.05). Conclusions For patients with locally resectable GC, 3D-LG performed by experienced surgeons in high-volume professional institutions can achieve long-term oncological outcomes comparable to those of 2D-LG. Registration number NCT02327481 ( http://clinicaltrials.gov ). Graphical abstract