Memantine, an N-methyl-D-aspartate receptor antagonist, is approved in the United States and Europe for the treatment of moderate to severe Alzheimer disease (AD) and has also been investigated in patients with mild to moderate AD. To characterize the specific cognitive benefits of memantine in patients with mild to moderate AD, a post hoc analysis was conducted of a 24-week randomized, double-blind, placebo-controlled, clinical trial comparing memantine (10 mg twice daily) to placebo. Cognition was assessed using the Alzheimer's Disease Assessment Scale-cognitive subscale (ADAS-cog) total score, individual items, and aggregated subscales, using a mixed model repeated measures analysis. As assessed by the ADAS-cog total score, participants in the placebo group demonstrated significantly more cognitive decline from baseline than participants treated with memantine at all visits beginning at week 8. Subjects treated with placebo also declined significantly more than individuals in the memantine group on 5 of 11 ADAS-cog individual items: orientation, language, comprehension, word finding, and recall of test instructions. Out of 3 ADAS-cog aggregated item subscales (language, memory, and praxis), outcomes in 2 (language and memory) favored memantine. Consistent with findings from trials conducted in moderate to severe AD patients, this post hoc analysis of a randomized clinical trial suggests that memantine benefits core aspects of language and some aspects of memory in patients with mild to moderate AD.