Flowering time is a main determinant of wheat adaptation to diverse environments and is influenced by three groups of genes, earliness per se (EPS), VRN and PPD. The gene-based models, used known genes to predict wheat phenotype, would be robust for wheat breeding and research. Parameters of wheat phenology models based on that in the APSIM cropping system model were replaced with functions of the number of winter and photoperiod-sensitive alleles at the three VRN1 loci and the Ppd-D1 locus, respectively. Two years of pre-vernalization and extended-photoperiod trials of 210 lines (mainly spring wheats) were used to estimate the effects of VRN1 and Ppd-D1 alleles, and calibrate the new gene-based model. Then the model validated against about 4500 observed heading times across the Australian wheatbelt. Virtual genotypes were created to cover the full range of Australian wheat germplasm, including all combinations of VRN1 and Ppd-D1 alleles. These virtual genotypes were used to investigate the adaptable genotype to minimize frost and heat stresses across Australian wheatbelt. This gene-based model allows the breeders to consider how to best target gene combinations to current and future production environments.