We propose a test of the Porter hypothesis for the Dutch horticulture sector, using a stochastic production frontier analysis allowing for an inclusion of policy variables to account for the effect of environmental policy of firm performance. We find considerable heterogeneity in the way firms react to environmental policy measures. Our estimation results indicate, for example, that a 1997 voluntary agreement covering energy, nutrient and pesticides use enhances technical efficiency of vegetable and plants growers, contrary to specialised flower growers. Specialised flower growers, however, did react to the 1993 multi-year agreement on energy reduction, contrary to vegetable and plant growers. Summarising, our findings are mixed but do not seem to reject the anecdotal evidence mentioned by Porter and Van der Linde (1995b) that Dutch horticulture firms' performance increased due to increased environmental stringency.