Influenza A/H5Nx viruses continue to diversify and undergo gene reassortment as they infect avian and mammalian hosts worldwide. The severity of human infections varies substantially between different H5 clades and neuraminidase (NA) reassortants, creating unpredictable pandemic risk. Existing H5 vaccines, typically based on a single hemagglutinin (HA) strain, cannot keep pace with this natural variation. To address this problem, we computationally engineer HA, NA, and M2 antigens representing the global antigenic space of circulating H5Nx viruses, prioritizing N1 and N6 subtypes associated with the highest threat in humans. The resulting digitally immune-optimized mRNA vaccine, DVX-panH5Nx, elicits broad HA neutralization and NA inhibition across divergent clades in mice and ferrets. Compared to WHO candidate vaccine viruses (CVVs), DVX-panH5Nx confers superior protection against antigenically distinct H5N1 challenges spanning two decades of viral evolution, demonstrating that computationally designed multivalent antigen vaccines can overcome natural influenza diversification and provide a scalable strategy for pre-pandemic preparedness.