Background: The GeparNuevo trial investigated the addition of durvalumab, an anti-PD-L1 checkpoint inhibitor (CPI), to standard neoadjuvant chemotherapy (NACT) in patients with early TNBC. Durvalumab increased the pathological complete response (pCR) rate particularly in patients treated with durvalumab alone before start of chemotherapy (Loibl et al. Ann Oncol 2019). Methods: GeparNuevo randomized patients with cT1b-cT4a-d tumors and centrally confirmed TNBC to durvalumab (D) 1.5 g i.v. or placebo every 4 weeks. D/placebo monotherapy (0.75 g i.v.) was given for the first 2 weeks (window phase), followed by D/placebo plus nab-paclitaxel 125 mg/m² weekly for 12 weeks, followed by D/placebo plus epirubicin/cyclophosphamide (EC) q2 weeks for 4 cycles. Randomization was stratified by stromal tumor infiltrating lymphocytes (sTILs) (low (≤10%), intermediate (11-59%), high (≥60%)). The primary objective was pCR (ypT0 ypN0). Secondary time-to-event endpoints included invasive disease-free survival (iDFS), distant disease-free survival (DDFS) and overall survival (OS). Results: A total of 174 patients were enrolled between June 2016 and September 2017. The pCR rate with durvalumab was 53.4% versus placebo 44.2% (OR 1.45, 95% CI 0.80–2.63, unadjusted Wald p = 0.224). Durvalumab effect was seen only in the window cohort (pCR 61.0% versus 41.4%, OR 2.22, 95% CI 1.06–4.64, p = 0.035; interaction p = 0.048). After a median follow-up of 42.2 months, 34 events occurred in 174 patients. 3-year iDFS in pCR vs non pCR was 92.0% vs 71.9% (log-rank p = 0.002). 3-year iDFS was 84.9% with durvalumab vs 76.9% with placebo (HR 0.54, 95%CI 0.27-1.09, stratified log-rank p = 0.0559); 3-year DDFS 91.4% vs 79.5% (HR 0.37, 95%CI 0.15-0.87, p = 0.0148); 3-year OS 95.1% vs 83.1% (HR 0.26, 95%CI 0.09-0.79, p = 0.0076). No difference was seen in iDFS, DDFS and OS between the window and no window cohort. Conclusions: Durvalumab added to neoadjuvant chemotherapy in TNBC significantly improved long-term outcome despite a small pCR increase and no continuation after surgery. It needs to be questioned whether adjuvant therapy with CPI is needed at all. Clinical trial information: NCT02685059