OBJECTIVE: To examine the relationship between food frequency questionnaire estimated isoflavone intakes and cognitive performance. DESIGN: The Study of Women’s Health Across the Nation (SWAN), is a multiethnic, community based, longitudinal study of women aged 42 to 52 years at entry. Dietary isoflavone intakes were estimated from an interviewer-administered food frequency questionnaire at baseline. Intakes of genistein and daidzein were highly correlated (r = 0.98); therefore, analyses were conducted using genistein only. The SWAN includes white, African American, Hispanic, Chinese, and Japanese women; this analysis was performed only in the latter two ethnic groups because the others had minimal genistein intake (median, <4 microg/day). Cognitive function tests were measured at the fourth annual follow-up visit using the East Boston Memory Test (Immediate and Delayed), Symbol Digit Modalities Test, and Digit Span Backward Test. Ethnicity-specific general linear models were used to examine the relationship between each of these cognitive tests and energy-adjusted genistein intake controlling for age, menopause stage, ever-use of any hormones, and current use of any hormones. RESULTS: Among 195 Japanese and women and 185 Chinese women, median intakes of genistein (mug/day) were 6,788 and 3,534, respectively. No associations between genistein intake and measures of cognitive performance were found in either ethnic group. CONCLUSIONS: Our results did not support the hypothesis that genistein intake, at the levels consumed by the study sample, benefits cognitive performance. It also possible that the bioavailability of genistein in food sources is insufficient to exert a neurophysiological effect or that the potential effect of genistein is only manifest in low-estrogen states; the current study is not able to address these possibilities.