This study was focused on the numerical prediction of the thermal fatigue life of a μBGA (Micro Ball Grid Array) solder joint. Numerical method was performed to predict three-dimensional finite element analysis with various solder alloys such as Sn–37 mass%Pb, Sn–3.5 mass%Ag, Sn–3.5 mass%Ag–0.7 mass%Cu and Sn–3.5 mass%Ag–3 mass%In–0.5 mass%Bi during a given thermal cycling. Strain values, which were obtained by the result of mechanical fatigue tests for solder alloys, were used to predict the solder joint fatigue life using the Coffin-Manson equation. The numerical results showed that Sn–3.5 mass%Ag with the 50 degree ball shape geometry had the longest thermal fatigue life in low cycle fatigue. Also a practical correlation for the prediction of the thermal fatigue life was suggested by using the dimensionless variable γ.