There are 10 major dialects in China. Most people in dialectal regions are bilingual speakers, i.e. native dialect and Mandarin. Although lots of people can speak Mandarin, they speak it with different accents (called regional accented Chinese in this paper) depending on how well they grasp the language. In this study, we categorize the regional accented Chinese into 3 levels of accents according to phonetic annotation and subjective evaluation on a regional accented speech corpus of three regions: Shanghai, Wuhan and Xiamen. Three accent evaluation methods, namely segmental annotation, clustering on phonetic annotation and subjective evaluation, are compared based on phonetic error rates. The results show that objective evaluation score based on segmental pronunciation is higher than subjective evaluation for the same speaker. This implies that supra-segmental features play an important role in rating accent degree and segmental features alone are not enough for objective evaluation. In accent level criterion, the errors from prosodic and segmental aspects are not equal and the percentage of these two parts are various for different regional speakers. The result is helpful for machine evaluation, L2 teaching and acquisition.