Background and Purpose: Whether specific patient groups have benefited from advances of treatment technologies including acute reperfusion therapy is uncertain. We aimed to investigate long-term trends of acute reperfusion therapy and functional outcomes according to the stroke severity using a large clinical registry. Methods: In the nationwide, hospital-based, multicenter, prospective registry cohort from the Japan Stroke Data Bank between January 2000 and December 2020, patients with ischemic stroke were studied. The baseline National Institutes of Health Stroke Scale (NIHSS) score of 10 or more was considered as possible large vessel occlusions (LVOs). Secular changes were assessed per 5-year categories (2000-2005, 2006-2010, 2011-2015, 2016-2020). Outcomes included favorable outcome (mRS score was 0 to 2 at discharge), and in-hospital mortality. Results: Of 235,695 patients, 127,741 ischemic stroke patients (76,850 men [60.2 %]; median age 75, [interquartile range, 66-82] years) with available data on NIHSS score were analyzed. NIHSS score was ≥10 in 31,747 patients (24.9%). In both patients with NIHSS ≥10 and those with NIHSS <10, the frequencies of intravenous thrombolysis (1.6% to 26.5%, and 0.3% to 6.9%, respectively) and endovascular therapy (2.0% to 29.8%, and 0.8% to 3.8%, respectively) increased from the 2000-2005 period to the 2015-2020 period. In patients with NIHSS ≥10, favorable outcome was more frequent in the 2015-2020 cohort than that in the 2000-2005 cohort (adjusted odds ratio, 1.63; [95% CI, 1.44-1.85]). In contrast, patients with NIHSS <10 had a decreased favorable outcome in the 2015-2020 cohort than that in the 2000-2005 cohort (adjusted odds ratio, 0.80; 95% CI, [0.75-0.85]). In-hospital mortality decreased in both patients with NIHSS ≥10 and NIHSS <10 per step on the 5-year categories. Conclusions: Over the 20-year period, acute reperfusion therapy has increasingly been provided to patients with NIHSS ≥10. Favorable outcomes significantly increased in patients with NIHSS ≥10 but decreased in those with NIHSS <10 over time. In-hospital mortality decreased across all NIHSS scores.