Making sense of modeled atmospheric composition requires not only comparison to in situ measurements but also knowing and quantifying the sensitivity of the model to its input factors. Using a global sensitivity method involving the simultaneous perturbation of many chemical transport model input factors, we find the model uncertainty for ozone (O₃), hydroxyl radical (OH), and hydroperoxyl radical (HO₂) mixing ratios, and apportion this uncertainty to specific model inputs for the DC-8 flight tracks corresponding to the NASA Intercontinental Chemical Transport Experiment (INTEX) campaigns of 2004 and 2006. In general, when uncertainties in modeled and measured quantities are accounted for, we find agreement between modeled and measured oxidant mixing ratios with the exception of ozone during the Houston flights of the INTEX-B campaign and HO₂ for the flights over the northernmost Pacific Ocean during INTEX-B. For ozone and OH, modeled mixing ratios were most sensitive to a bevy of emissions, notably lightning NO_x, various surface NO_x sources, and isoprene. HO₂ mixing ratios were most sensitive to CO and isoprene emissions as well as the aerosol uptake of HO₂. With ozone and OH being generally overpredicted by the model, we find better agreement between modeled and measured vertical profiles when reducing NO_x emissions from surface as well as lightning sources.