Self-efficacy is a belief that one can competently cope with a challenging situation. If self-efficacy is a strong predictor of health status in multiple sclerosis (MS), it may be an important area to target in clinical practice, as such beliefs may be modifiable. The aim of this study was to examine the predictive value of self-efficacy on self-reported health status in MS. Eighty-nine people with MS completed the Multiple Sclerosis Self-efficacy Scale (MSSE function and control scales), the Multiple Sclerosis Impact Scale (MSIS-29), and the Multiple Sclerosis Walking Scale (MSWS-12) at two time points: 1) admission to an inpatient rehabilitation unit (n = 43) or for steroid treatment for relapses (n = 46); and 2) discharge (rehabilitation group) or six weeks later (steroid group). Multiple regression analyses examined whether baseline and changes in self-efficacy predict changes in self-reported health status. Both baseline and changes in self-efficacy were strong and independent predictors of changes in health status (P-values ranged from 0.025 to < 0.001). That is, pretreatment self-efficacy scores and increases in self-efficacy scores from baseline to follow-up (improvement), were significantly associated with decreases (improvement) in perceived walking ability and physical and psychological impact of MS. The findings suggest that self-efficacy predicts improvement in health status and that self-efficacy would be an important domain to measure and manage actively in education and rehabilitation programs.