Maximal oxygen consumption (VO2max) assessed by cardiopulmonary exercise training (CPET), is an important parameter for risk assessment in patients with pulmonary hypertension (PH). However, CPET may not be available for all PH-patients. Thus, we aimed to test previously published predictive models of VO2max from the 6-min walk distance (6 MWD) for their accuracy and to create a new model.We tested four models (Ross (2010), Miyamoto (2000) and Zapico et al. (2019)). To derive a new model, data was split into a training and testing dataset (70:30) and step-wise linear regression was performed. To compare the different models standard error of estimate (SEE) was calculated and the models have been graphically compared by Bland-Altman plots. Sensitivity and specificity for correct prediction into low risk classification (VO2max>15 mL min kg−1) was calculated for all models.276 observations were included in the analysis (194/82 training/ testing dataset). 6 MWD and VO2max significantly correlated (r=0.65, p<0.001). Linear regression showed significant correlation of 6 MWD, weight and heart rate response (HRR) with VO2max and the best fitting prediction equation was: VO2max=1.83+0.031×6 MWD(m)–0.023×weight(kg)–0.015×HRR(bpm). SEE for the different models were 3.03, 3.22, 4.36 and 3.08 mL min kg−1 for Ross, Miyamoto, Zapico et al. and the new model respectively. Predicted mean VO2max was 16.5 mL min kg−1 (versus observed 16.1 mL min kg−1).6 MWD and VO2max reveal good correlation in all models. However, the accuracy of all models is inadequate for clinical use. Thus, CPET and 6 MWD measures both remain valuable risk assessment tools in the management of PH.