Osteoarthritis (OA) is a considerable health problem worldwide. It is known to be associated with certain occupational risk factors. We examined the prevalence rate of OA by occupational cluster. Data were collected from the Korea National Health and Nutrition Examination Surveys (2010–2013). The total number of unweighted sample size was 9,905 participants: 4,460 men and 5,445 women, and OA prevalence was 5.3% and 18.4% respectively. OA patients were defined as participants with knee/hip joint pain and radiographic change of knee/hip joint. Occupational type was classified as either white, pink, blue, or green collar based on the occupational characteristics following physical demand: white for manager and professionals; pink for clerks and service/sales workers; blue for craft/trade workers, machine operators and assemblers, and elementary manual workers; and green for agricultural/fishery workers. We calculated the odds ratios (ORs) and 95% confidence intervals (95% CI) for the odds of a participant’s having OA according to the occupational cluster, with gender stratification. The multiple logistic regression model showed that, compared to the white collar group, the ORs of the pink, blue, and green collar workers were 1.23 (95% CI 0.64–2.36), 1.85 (95% CI 1.18–2.88), and 2.91 (95% CI 1.86–4.54), respectively, in males, and 2.53 (95% CI 1.71–3.73), 2.86 (95% CI 1.94–4.21), and 3.90 (95% CI 2.60–5.83), respectively in females. The prevalence rate of OA was associated with the occupational cluster, in order from highest to lowest: green, blue, pink, and white collar.