AGO‐OVAR 12 investigated the effect of adding the oral triple angiokinase inhibitor nintedanib to standard front‐line chemotherapy for advanced ovarian cancer. At the primary analysis, nintedanib demonstrated significantly improved progression‐free survival (PFS; primary endpoint) compared with placebo. We report final results, including overall survival (OS). Patients with primary debulked International Federation of Gynaecology and Obstetrics (FIGO) stage IIB–IV newly diagnosed ovarian cancer were randomised 2:1 to receive carboplatin (area under the curve 5 or 6) plus paclitaxel (175 mg/m2) on day 1 every 3 weeks for six cycles combined with either nintedanib 200 mg or placebo twice daily on days 2–21 every 3 weeks for up to 120 weeks. Between December 2009 and July 2011, 1,366 patients were randomised (911 to nintedanib, 455 to placebo). Disease was considered as high risk (FIGO stage III with >1 cm residuum, or any stage IV) in 39%. At the final analysis, 605 patients (44%) had died. There was no difference in OS (hazard ratio 0.99, 95% confidence interval [CI] 0.83–1.17, p = 0.86; median 62.0 months with nintedanib vs. 62.8 months with placebo). Subgroup analyses according to stratification factors, clinical characteristics and risk status showed no OS difference between treatments. The previously reported PFS improvement seen with nintedanib did not translate into an OS benefit in the nonhigh‐risk subgroup. Updated PFS results were consistent with the primary analysis (hazard ratio 0.86, 95% CI 0.75–0.98; p = 0.029) favouring nintedanib. The safety profile was consistent with previous reports.