A computational study of evaluation of current turbulence models is performed for a better prediction of thermal stratification in an upper plenum of a liquid metal reactor. The turbulence models tested in the present study are the two-layer model, the shear stress transport (SST) model, the v2-f model and the elliptic blending mode(EBM). The performances of the turbulence models are evaluated by applying them to the thermal stratification experiment conducted at JNC (Japan Nuclear Corporation). The algebraic flux model is used for treating the turbulent heat flux for the two-layer model and the SST model, and there exist little differences between the two turbulence models in predicting the temporal variation of temperature. The v2-f model and the elliptic blending model better predict the steep gradient of temperature at the interface of thermal stratification, and the v2-f model and elliptic blending model predict properly the oscillation of the ensemble-averaged temperature. In general the overall performance of the elliptic blending model is better than the v2-f model in the prediction of the amplitude and frequency of the temperature oscillation.