Objectives The aim of the study was to compare the predictions of five popular cardiovascular disease ( CVD ) risk prediction models, namely the Data Collection on Adverse Events of Anti‐ HIV Drugs ( D : A : D ) model, the Framingham Heart Study ( FHS ) coronary heart disease ( FHS‐CHD ) and general CVD ( FHS‐CVD ) models, the A merican Heart Association ( AHA ) atherosclerotic cardiovascular disease risk score ( ASCVD ) model and the Systematic Coronary Risk Evaluation for the Netherlands ( SCORE‐NL ) model. Methods A cross‐sectional design was used to compare the cumulative CVD risk predictions of the models. Furthermore, the predictions of the general CVD models were compared with those of the HIV ‐specific D : A : D model using three categories (< 10%, 10–20% and > 20%) to categorize the risk and to determine the degree to which patients were categorized similarly or in a higher/lower category. Results A total of 997 HIV ‐infected patients were included in the study: 81% were male and they had a median age of 46 [interquartile range ( IQR ) 40–52] years, a known duration of HIV infection of 6.8 ( IQR 3.7–10.9) years, and a median time on ART of 6.4 ( IQR 3.0–11.5) years. The D : A : D , ASCVD and SCORE‐NL models gave a lower cumulative CVD risk, compared with that of the FHS‐CVD and FHS‐CHD models. Comparing the general CVD models with the D : A : D model, the FHS‐CVD and FHS‐CHD models only classified 65% and 79% of patients, respectively, in the same category as did the D : A : D model. However, for the ASCVD and SCORE‐NL models, this percentage was 89% and 87%, respectively. Furthermore, FHS‐CVD and FHS‐CHD attributed a higher CVD risk to 33% and 16% of patients, respectively, while this percentage was < 6% for ASCVD and SCORE‐NL . Conclusions When using FHS‐CVD and FHS‐CHD , a higher overall CVD risk was attributed to the HIV ‐infected patients than when using the D : A : D , ASCVD and SCORE‐NL models. This could have consequences regarding overtreatment, drug‐related adverse events and ...