This contribution aims to quantify the performance of the Czech regional labour markets and to reveal the most influencing economic factors standing behind. Investigated labour markets are described by the corresponding matching functions. From this point of view the successful matches are treated as an output of production process where unemployed are paired with vacancies. Resulting unemployment outflows are determined by the efficiency of this matching process. Using stochastic frontier model approach, we estimate the efficiency of regional matching functions, evaluate the differences among the regions and reveal the key determinants of this kind of effectiveness. The stochastic frontier is estimated using regional panel data for the period 1997-2013.