Abstract Background Gastric cancer surgery is increasingly being centralized in the Netherlands, whereas the diagnosis is often made in hospitals where gastric cancer surgery is not performed. The aim of this study was to assess whether hospital of diagnosis affects the probability of undergoing surgery and its impact on overall survival. Methods All patients with potentially curable gastric cancer according to stage (cT1/1b–4a, cN0–2, cM0) diagnosed between 2005 and 2013 were selected from the Netherlands Cancer Registry. Multilevel logistic regression was used to examine the probability of undergoing surgery according to hospital of diagnosis. The effect of variation in probability of undergoing surgery among hospitals of diagnosis on overall survival during the intervals 2005–2009 and 2010–2013 was examined by using Cox regression analysis. Results A total of 5620 patients with potentially curable gastric cancer, diagnosed in 91 hospitals, were included. The proportion of patients who underwent surgery ranged from 53·1 to 83·9 per cent according to hospital of diagnosis (P < 0·001); after multivariable adjustment for patient and tumour characteristics it ranged from 57·0 to 78·2 per cent (P < 0·001). Multivariable Cox regression showed that patients diagnosed between 2010 and 2013 in hospitals with a low probability of patients undergoing curative treatment had worse overall survival (hazard ratio 1·21; P < 0·001). Conclusion The large variation in probability of receiving surgery for gastric cancer between hospitals of diagnosis and its impact on overall survival indicates that gastric cancer decision-making is suboptimal.