This paper develops a differential-evolution-based solution for the problem of proton exchange membrane fuel cell stack modeling. The problem is analytically intractable and computationally hard. The present paper produces results that outperform state-of-the-art approaches on three performance metrics: solution quality corresponding to a given cost, cost of finding a solution of a given quality, and frequency of producing an optimal or near-optimal solution. (C) 2012 Elsevier Ltd. All rights reserved.