Objective Our study aimed to verify the validity of the Chinese version of Alzheimer's Disease Assessment Scale‐Cognitive Subscale (ADAS‐Cog) for the community‐dwelling older people in China. Methods A total of 1276 individuals composed by 628 normal controls (NCs), 572 people living with mild cognitive impairment (MCI), and 76 people living with Alzheimer's disease (AD) were recruited for the current study. All of the participants underwent ADAS‐Cog, clinical interview and examination, Quick Cognitive Screening Scale for the Elderly, and Activities of Daily Living Scale. The sensitivity and specificity of ADAS‐Cog were calculated, and a receiver operating characteristic curve (ROC curve) was drawn to decide the optimal cutoff points of ADAS‐Cog for screening MCI and AD. Results Statistically significant differences were observed among the three groups (P <. 001, NC < MCI