A number of studies have explored the relationship between socio-economic status and mortality, although these have mostly been based on the working-age population, despite the fact that the burden of mortality is highest in older people. Using Poisson regression on linked New Zealand census and mortality data (2001–04, 1.3 million person years) with a comprehensive set of socio-economic indicators (education, income, car access, housing tenure, neighourhood deprivation), we examined the association of socio-economic characteristics and older adult mortality (65+ years) in New Zealand. We found that socio-economic mortality gradients persist into old age. Substantial relative risks of mortality were observed for all socio-economic factors, except housing tenure. Most relative risk associations decreased in strength with ageing [e.g. most deprived compared to least deprived rate ratio for males reducing from 1.40 (95% confidence interval (CI) 1.28–1.53) for 65–74-year-olds to 1.13 (CI 1.00–1.28) for 85 + -year-olds], except for income and education among women where the rate ratios changed little with increasing age. This suggests individual-level measures of socio-economic status are more closely related to mortality in older women than older men. Comparing across genders, the only statistically significantly different association between men and women was for a weaker association for women for car access.