Mechanical ventilation for respiratory failure due to COVID-19 is associated with significant morbidity and mortality. Veno-venous extracorporeal membrane oxygenation (ECMO) is an attractive management option. This study sought to determine the effect of ECMO on hospital mortality and discharge condition in this population. We conducted a retrospective multicenter study to emulate a pragmatic targeted trial comparing ECMO to mechanical ventilation without ECMO for severe COVID-19. Data were gathered from a large hospital network database in the US. Adults admitted with COVID-19 were included if they were managed with ECMO or mechanical ventilation for severe hypoxemia and excluded if they had significant comorbidities or lacked functional independence on admission. The groups underwent coarsened exact matching on multiple clinical variables. The primary outcome was adjusted in-hospital mortality; secondary outcomes included ventilator days, intensive care days, and discharge destination. A total of 278 ECMO patients were matched to 2,054 comparison patients. Adjusted in-hospital mortality was significantly less in the ECMO group (38.8% vs. 60.1%, p < 0.001). Extracorporeal membrane oxygenation was associated with higher rates of liberation from mechanical ventilation, intensive care discharge, and favorable discharge destination. These findings support the use of ECMO for well-selected patients with severe acute respiratory failure due to COVID-19.