This study analyses the relationships between cognitive performance, social participation and behavioural risks, taking into account age and educational attainment. We examine individual data for 11 European countries and Israel from the first wave of the Survey on Health, Ageing and Retirement in Europe (SHARE). The stochastic frontier approach methodology enables us to identify different sources of plasticity on cognitive functioning while taking into account age-related decline in cognitive performance. Several social participation variables were examined: employment status, attending educational courses, doing voluntary or charity work, providing help to family, friends or neighbours, participating in sports, social or other clubs, in a religious organisation and in a political or community organisation, and we controlled for age, education, income, physical activity, body-mass index, smoking and drinking. In the pooled sample, the results clearly show that all kinds of social involvement enhance cognitive functions, in particular in work. Moreover, behavioural risks such as physical inactivity, obesity, smoking or drinking were clearly detrimental to cognitive performance. Models for men and women were run separately. For both genders, all social involvement indicators associated with better cognitive performance. The results varied by countries, however, particularly the signs of the associations with a number of indicators of social involvement and behavioural risks.