Summary Background Obesity, a comorbid medical condition, is usually observed in patients with established coronary artery disease. Paradoxically, patients with a higher body mass index (BMI) usually have better clinical outcomes after coronary revascularization. Methods We searched five online databases through December 2017. We identified studies reporting the rate of all‐cause mortality or cardiovascular‐related outcomes among patients after coronary revascularization with percutaneous coronary intervention or coronary artery bypass graft based on various BMI categories. Network meta‐analysis was performed using Bayesian methods. Results Sixty‐five records involving 865,774 participants were included in our study. A U‐shaped association was observed across BMI categories for all‐cause mortality. Using normal weight as the reference, all‐cause mortality was increased for (relative risk RR: 2.4; 95% credibility interval CrI: 2.1–2.7) patients with underweight, whereas it was lowered in patients with overweight, obese, and severely obese. This association remained significant in many subgroups. We also observed that the risk of major adverse cardiovascular events (MACE) was lowest among patients with overweight. Furthermore, patients with underweight were associated with greater risks of myocardial infarction (RR: 1.9; 95% CrI: 1.4–2.5), cardiovascular‐related mortality (RR: 2.8; 95% CrI: 1.6–4.7), stroke (RR: 2.0; 95% CrI: 1.3–3.3) and heart failure (RR: 1.7; 95% CrI: 1.1–2.7) compared with normal weight patients; no significant association was observed among individuals with higher BMI. Conclusions The ‘obesity paradox’ does exist in patients after coronary revascularization, especially for patients with post‐percutaneous coronary intervention. All‐cause mortality in patients with high BMI is significantly lower compared with patients with normal weight. Furthermore, patients with underweight experience higher rates of cardiovascular outcomes compared with patients with normal weight.