As one promising technology to mitigate CO2 emission, CO2 capture utilization and storage (CCUS) plays a crucial role in achieving carbon neutrality. The deep saline aquifer is a prime candidate for CO2 geological storage. The subsurface flow and effectiveness of CO2 storage in deep saline aquifer are highly related to the permeability heterogeneity of formations, which needs in-depth study. To bridge the gap, this study focused on quantifying the impact of permeability heterogeneity on the CO2 flow patterns, the well injectivity and the storage efficiency, which aims to enhance the understanding of CO2 storage characteristics in deep saline aquifers. The heterogeneous saline aquifer model was built by using the Sequential Gaussian Simulation (SGSIM) method. A novel classification template was proposed with the CO2 flow patterns classified as “Dispersive”, “Sweeping”, “Fingering”, and “Channeling” for CO2 storage in deep saline aquifers according to the geostatistical parameters (including dimensionless correlation lengths, first and second spatial moment, and Dykstra-Parsons coefficient). For the well injectivity, the results showed that high injectivity occurred when both horizontal and vertical correlation lengths were high or at a favourable connectivity of permeability in the horizontal and vertical directions. In addition, CO2 storage efficiency is higher when both dimensionless horizontal and vertical correlation lengths are in the range of 0.1–0.2. This is because frequent changes between high and low permeability regions led to frequent mutual displacement of water and CO2, resulting in higher residual trapping and slow CO2 front. Therefore, the dimensionless correlation lengths and breakthrough time should be considered simultaneously to achieve safer trapping and maximize the CO2 storage capacity. The findings of this work provide insights into the subsurface flow of CO2 storage in deep saline aquifers with permeability heterogeneity.