Performances of conventional and improved soil moisture balance as well as locally calibrated empirical models were evaluated in simulating potential recharge (R) and soil moisture content for a semi-arid foothill region. Models comparison with observed values using lysimeter data during [(2011–2012), (2012–2013)] reveal poor performance of conventional soil moisture balance model, underestimating annual R values. Improved soil moisture balance model provided acceptable estimation of annual R for 2011–2012 by considering the wetting of the near surface soil storage. However, it produced the worst simulation for daily soil moisture content once rainy season was over. Sensitivity analysis revealed that the precision degree of initial soil moisture deficit value would strongly influence estimation of R by improved soil moisture balance model, which can be viewed as a limiting factor. Additionally, locally calibrated model produced the best estimation of annual R and daily soil moisture content, which is suggested for the study region.