It is frequently hypothesized that genetically modified crops can help to reduce pesticide use while maintaining or even increasing profit levels. No known studies evaluate these new technologies in the actual farm setting and no systematic empirical work has verified this hypothesis for cotton production. This study uses Data Envelopment Analysis (DEA) to assess the relative technical efficiency of pesticide use for a sample of 208 cotton producers in NC. The average technical efficiency (VRS) was only 0.36. Differences in mean efficiencies between seed type were not significant. Tobit analysis of the estimated input use efficiency showed that efficiency is significantly affected by harvest beginning and ending dates and whether stacked gene cotton is grown. Other important attributes were the use of formal plants for pest, nutrient and conservation management and whether the farmer grows herbicide tolerant cotton.