This retrospective analysis compared the efficiency of the gonadotropin- releasing hormone (GnRH) antagonist (GnRH-ant) protocol and the GnRH agonist long (GnRH-a) protocol for patients with diminished ovarian reserve (DOR). A total of 1,233 patients with DOR (anti-Mullerian hormone <1.1 ng/mL) were recruited for this retrospective case-control study. They were divided into two groups according to female age. Younger patients were assigned to POSEIDON group3 (PG3: age ≤35 years); older patients were assigned to POSEIDON group 4 (PG4: age >35 years). All patients with DOR underwent controlled ovarian stimulation and fresh embryo transfer (ET) on day 3. We recruited 283 GnRH-a and 54 GnRH-ant cycles for PG3, and 663 GnRH-a and 233 GnRH-ant cycles for PG4. In PG3, the GnRH-a protocol was associated with a lower ET cancellation rate (30/283 = 10.2% vs. 12/54 = 22.2%, p = 0.018) and a higher live birth rate (7/54 = 13.0% vs. 78/283 = 27.6%, p = 0.024) than the GnRH-ant protocol for the initiated cycles. Furthermore, the GnRH-a protocol was correlated with a higher implantation rate than the GnRH-ant protocol for ET cycles (146/577 = 25.3% vs. 11/103 = 10.7%, P = 0.027). No differences in the ET cancellation rate, live birth rate and implantation rate between GnRH-a and GnRH-ant groups were observed among PG4 patients. In conclusion, the GnRH-a protocol was more effective than the GnRH-ant protocol for young patients with DOR. The low ET cancellation rate and high implantation rate may be related to embryo quality or endometrial receptivity, which warrant further investigation.