The role of balancing selection is a long-standing evolutionary puzzle. Balancing selection is a crucial evolutionary process that maintains genetic variation (polymorphism) over extended periods, however, detecting it poses a significant challenge. Building upon the polymorphism-aware phylogenetic models (PoMos) framework, we introduce PoMoBalance designed to disentangle the interplay of mutation, genetic drift, directional and balancing selection pressures influencing population diversity. Rooted in the Moran model, PoMos have demonstrated efficiency in species tree inference, capturing mutational effects, fixation biases, and GC-bias rates. Implemented in the open-source RevBayes Bayesian framework, PoMoBalance offers a versatile tool for multi-individual data analysis. This study extends PoMos’ capabilities to explore balancing selection and disentangle it from GC-biased gene conversion. The novel aspect of our approach in studying balancing selection lies in PoMos’ ability to account for ancestral polymorphisms and incorporate parameters that measure frequency-dependent selection. We implemented validation tests and assessed the model on the data simulated with SLiM and a custom Moran model simulator. Real sequence analysis ofDrosophilapopulations reveals insights into the evolutionary dynamics of regions subject to frequency-dependent balancing selection, particularly in the context of sex-limited colour dimorphism.