Rural Malians depend on sorghum as a staple food. Despite long-term investment in sorghum improvement, achieving major gains in sorghum yields has posed challenges. We assessed the potential economic impact of the first Guinea-race sorghum hybrids developed and diffused using participatory plant breeding with decentralised, farmer-based seed systems. We compared this approach to formal plant breeding with a centralised, state-managed seed system – the sole approach pursued in Mali prior to 2000. To incorporate risk, we augmented the economic surplus model by applying Monte Carlo sampling to simulate distributions of model parameters. A census of sorghum varieties in 58 villages of the Sudanese Savanna served as the adoption baseline. Our findings indicate that research on sorghum hybrids with the new approach is a sound investment. Public and private actors need to continue investing in innovative ways to expand the sorghum seed system. The sensitivity of results to the price elasticity of supply suggests commercialisation opportunities.