Abstract Purpose: Plasma circulating tumor DNA (ctDNA) analysis is used for genotyping advanced non–small cell lung cancer (NSCLC); monitoring dynamic ctDNA changes may be used to predict outcomes. Patients and Methods: This was a retrospective, exploratory analysis of two phase III trials [AURA3 (NCT02151981), FLAURA (NCT02296125)]. All patients had EGFR mutation-positive (EGFRm; ex19del or L858R) advanced NSCLC; AURA3 also included T790M-positive NSCLC. Osimertinib (FLAURA, AURA3), or comparator EGFR–tyrosine kinase inhibitor (EGFR-TKI; gefitinib/erlotinib; FLAURA), or platinum-based doublet chemotherapy (AURA3) was given. Plasma EGFRm was analyzed at baseline and Weeks 3/6 by droplet digital PCR. Outcomes were assessed by detectable/non-detectable baseline plasma EGFRm and plasma EGFRm clearance (non-detection) at Weeks 3/6. Results: In AURA3 (n = 291), non-detectable versus detectable baseline plasma EGFRm had longer median progression-free survival [mPFS; HR, 0.48; 95% confidence interval (CI), 0.33–0.68; P < 0.0001]. In patients with Week 3 clearance versus non-clearance (n = 184), respectively, mPFS (months; 95% CI) was 10.9 (8.3–12.6) versus 5.7 (4.1–9.7) with osimertinib and 6.2 (4.0–9.7) versus 4.2 (4.0–5.1) with platinum-pemetrexed. In FLAURA (n = 499), mPFS was longer with non-detectable versus detectable baseline plasma EGFRm (HR, 0.54; 95% CI, 0.41–0.70; P < 0.0001). For Week 3 clearance versus non-clearance (n = 334), respectively, mPFS was 19.8 (15.1 to not calculable) versus 11.3 (9.5–16.5) with osimertinib and 10.8 (9.7–11.1) versus 7.0 (5.6–8.3) with comparator EGFR-TKI. Similar outcomes were observed by Week 6 clearance/non-clearance. Conclusions: Plasma EGFRm analysis as early as 3 weeks on-treatment has the potential to predict outcomes in EGFRm advanced NSCLC.