Objective: The purpose of this study was to examine the prevalence and correlates of alcohol-related problems across four Hispanic national groups: Mexican Americans, Puerto Ricans, Cuban Americans, and South/Central Americans. Method: Using a multistage cluster sample design, 5,224 individuals ages 18 years and older were selected from the household population of five U.S. metropolitan areas: Miami, New York, Philadelphia, Houston, and Los Angeles. Results: Cuban Americans had the lowest prevalence of alcohol-related problems. Significant differences across national group for zero versus two or more problems and for one versus two or more problems existed among men. Puerto Rican women were most likely to report two or more problems. The presence of zero versus two or more problems varied significantly across groups. There was variation in problem type across national groups among both men and women. Regression analyses showed that all groups were more likely than Cuban Americans to report two or more problems (vs zero) (Puerto Ricans: odds ratio [OR] = 2.02, p < .05; Mexican Americans: OR = 2.92, p <= .01; South/Central Americans: OR = 2.12, p <= .01). Being U.S. born (vs foreign born) increased the likelihood of experiencing one (OR = 1.57, p < .05) and two or more problems (OR = 1.95, p <= .01). The volume of consumption was associated with problems (one problem: OR = 1.16, p <= .01; two or more problems: OR = 1.31, p <= .01). Heavy episodic drinking less than once a month was associated with two or more problems (OR = 6.15, p <= .01). Heavy episodic drinking one or more times a month was associated with one problem (OR = 1.74, p <= .01) and two or more problems (OR = 3.18, p <= .01). Conclusions: It is important to recognize that Hispanics are not a homogenous group. (J. Stud. Alcohol Drugs 70: 991-999, 2009)