Local compression capacity of stirrups-confined concrete is considered as a local zone in load transfer in many structural applications such as the post-tensioned prestressed concrete bearing area or at end bearings of bridges. This article offers an applicable computational equation to evaluate the local compression capacity of stirrups confined concrete. A machine learning model based on multi-gene genetic programming is utilized to formulate the proposed formula. A database consisting of data collected from previous literature is used in discovering the correlation between the input parameters with compression capacity of stirrups-confined concrete. The numerical study covers the use of both ordinary and high-performance concrete, since the peak strength of concrete prisms varied from 16 MPa to 112 MPa. It takes into account the bearing area aspect ratio and stirrups confined core area aspect ratio. The ratio of duct diameter to section width is varied from zero which means no duct to 0.29. The effect of stirrups is undertaken with both the yield strength of stirrups, and the volumetric ratios.