<p>Background: Microdose flare-up GnRH agonist and GnRH antagonist have become more popular in the management of poor ovarian responders (POR) in recent years; however, the optimal protocol for POR patients undergoing <em>in vitro</em> fertilization has still been a challenge.<br /> Methods: In this observational study design, two hundred forty four poor ovarian responders were retrospectively evaluated for their response to GnRH agonist protocol (group-1, n=135) or GnRH antagonist protocol (group-2, n=109). Clinical pregnancy rate was the primary end point and was compared between the groups. Student t-test, Mann Whitney U test and x²-test were used to compare the groups. The p&lt;0.05 was considered to show a statistically significant result.<br /> Results: The mean total gonadotropin doses were 3814&plusmn;891<em> IU</em> in group 1 and 3539&plusmn;877 <em>IU</em> in group 2 (p=0.02). The number of metaphase-II oocytes (3.6&plusmn;2.4 <em>vs</em>. 2.8&plusmn;1.9, p=0.005) and implantation rates (27.8% <em>vs</em>. 18.8%, p=0.04) in group 1 and group 2, respectively were significantly different. The fertilization rate in group 1 and group 2 was 73%<em> vs</em>. 68%, respectively (p=0.5) and clinical pregnancy rate was 19.8% <em>vs</em>. 14.4%, respectively (p=0.13).<br /> Conclusion: The GnRH agonist microdose flare-up protocol has favorable outcomes with respect to the number of oocytes retrieved and implantation rate; nevertheless, the clinical pregnancy rate was found to be similar in comparison to GnRH antagonist protocol in poor ovarian responders. GnRH antagonist protocol appears to be promising with significantly lower gonadotropin requirement and lower treatment cost in poor ovarian responders.</p>