The authors present the results of parallel telephone and Internet surveys to investigate their comparability. The telephone survey was administered to a national probability sample based on random digit dialing. The contemporaneous Internet survey was administered to a random sample of the data base of willing respondents assembled by Harris Interactive. The survey was replicated by Harris Interactive six months later, and by Knowledge Networks, which employs a randomly recruited panel, nine months later. The data facilitate comparisons in terms of demographic characteristics, environmental knowledge, and political opinions across survey modes. Knowledge and opinion questions generally show statistically significant but substantively modest difference across modes. With inclusion of standard demographic controls, typical relational models of interest to political scientists produce similar estimates of parameters across modes. The use of commercial Internet samples may thus already be reasonable for many types of social science research.