Résumé : Background Pulmonary artery wedge pressure (PAWP) during exercise, as a surrogate for left ventricular (LV) end-diastolic pressure (EDP), is used to diagnose heart failure with preserved ejection fraction (HFpEF). However, LVEDP is the gold standard to assess LV filling, end-diastolic PAWP (PAWP ED ) is supposed to coincide with LVEDP and mean PAWP throughout the cardiac cycle (PAWP M ) better reflects the haemodynamic load imposed on the pulmonary circulation. The objective of the present study was to determine precision and accuracy of PAWP estimates for LVEDP during exercise, as well as the rate of agreement between these measures. Methods 46 individuals underwent simultaneous right and left heart catheterisation, at rest and during exercise, to confirm/exclude HFpEF. We evaluated: linear regression between LVEDP and PAWP, Bland–Altman graphs, and the rate of concordance of dichotomised LVEDP and PAWP ≥ or < diagnostic thresholds for HFpEF. Results At peak exercise, PAWP M and LVEDP, as well as PAWP ED and LVEDP, were fairly correlated (R 2 >0.69, p<0.01), with minimal bias (+2 and 0 mmHg respectively) but large limits of agreement (±11 mmHg). 89% of individuals had concordant PAWP and LVEDP ≥ or <25 mmHg (Cohen's κ=0.64). Individuals with either LVEDP or PAWP M ≥25 mmHg showed a PAWP M increase relative to cardiac output (CO) changes (PAWP M /CO slope) >2 mmHg·L −1 ·min −1 . Conclusions During exercise, PAWP is accurate but not precise for the estimation of LVEDP. Despite a good rate of concordance, these two measures might occasionally disagree.