The effects of reservoir heterogeneity and anisotropy were quantified through the cyclic CO2-Assisted Gravity Drainage (GAGD) process performance in a heterogeneous multi-layering sandstone reservoir. First, an integrating workflow of multiple-point geostatistics (MPS) and Sequential Gaussian Simulation (SGSIM) was adopted for the lithological and petrophysical modeling to capture the fluvial depositional environment and preserve the reservoir heterogeneity, respectively. Next, sensitivity analysis was conducted through compositional reservoir simulation and Design of Experiments (DoE) to eliminate the non-influencing petrophysical parameters on the GAGD process performance. Then, heterogeneity and anisotropy effects were quantified with respect to reservoir permeability and anisotropy ratio, respectively. The effects was attained by generating and incorporating multiple reservoir stochastic images (realizations) that capture the entire geological uncertainty space into the reservoir flow simulation. Based on the reservoir flow responses, it was concluded that the impact of permeability anisotropy on the GAGD process is higher than that of heterogeneity, because the main concept of GAGD process considers vertical fluid movements from the top-layer injection wells to the horizontal producers.