This article examines option pricing performance using realized volatilities with or without handling microstructure noise, non-trading hours and large jumps. The dynamics of realized volatility is specified by ARFIMA(X) and HAR(X) models. Main results using put options on the Nikkei 225 index are: (1) ARFIMAX model performs best, (2) the Hansen and Lunde (2005a) adjustment for non-trading hours improves the performance, (3) methods for reducing microstructure noise-induced bias yield better performance, while if the Hansen-Lunde adjustment is used, the other methods are not necessarily needed and (4) the performance is unaffected by removing large jumps from realized volatility.