The aim of the study was to establish a reliable scoring tool to identify the probability of symptomatic intracranial hemorrhage (sICH) in anterior circulation stroke patients with contrast enhancement (CE) on brain non-contrast CT (NCCT) after endovascular thrombectomy (EVT). We retrospectively reviewed consecutive patients with acute ischemic stroke (AIS) who had CE on NCCT immediately after EVT for anterior circulation large vessel occlusion (LVO). We used the Alberta stroke program early CT score (ASPECTS) scoring system to estimate the extent and location of CE. Multivariable logistic regression was performed to derive an sICH predictive score. The discrimination and calibration of this score were assessed using the area under the receiver operator characteristic curve, calibration curve, and decision curve analysis. In this study, 194 of 322 (60.25%) anterior circulation AIS-LVO patients had CE on NCCT. After excluding 85 patients, 109 patients were enrolled in the final analysis. In multivariate regression analysis, age ≥70 years (adjusted OR (aOR) 9.23, 95% CI 2.43 to 34.97, P＜0.05), atrial fibrillation (AF) (aOR 4.17, 95% CI 1.33 to 13.12, P＜0.05), serum glucose ≥11.1 mmol/L (aOR 9.39, 95% CI 2.74 to 32.14, P＜0.05), CE-ASPECTS ＜5 (aOR 3.95, 95% CI 1.30 to 12.04 P＜0.05), and CE at the internal capsule (aOR 3.45, 95% CI 1.03 to 11.59, P＜0.05) and M1 region (aOR 3.65, 95% CI 1.13 to 11.80, P＜0.05) were associated with sICH. These variables were incorporated as the CE-age-glucose-AF (CAGA) score. The CAGA score demonstrated good discrimination and calibration in this cohort, as well as the fivefold cross validation. The CAGA score reliably predicted sICH in patients with CE on NCCT after EVT treatment.