In this paper, we construct a new split-step numerical method for stochastic delay Hopfield neural networks. The main aim of this paper is to investigate the mean-square stability of this split-step 胃-methods for stochastic delay Hopfield neural networks. It is proved that the split-step 胃-methods are mean-square stable under suitable conditions. Numerical experiments verify the numerical stability results obtained from theory. A comparison between this work and Ronghua et al. is also discussed in the example.