This study is a meta-analysis to examine the relationship between self-efficacy and mathematical creativity. This meta-analysis included 21 studies with a total sample size of 11,621 participants and 33 effect sizes across the studies. Data analysis using a random effects model using the “meta” package (version 7.0-0) in R software version 4.3.0. The results showed a positive and significant relationship between self-efficacy and mathematical creativity (z=3.51;95% CI [0.09, 0.32], p<0.001). The influence of self-efficacy on mathematical creativity is included in the low category (re=0.21). These findings had no publication bias issues with Egger’s test (t=−0.03; p=0.978) and were stable against the impact of unpublished studies (Fail−safe N=5101; p<0.001). Meta-regression revealed two variables that showed significant results: measurement method (Q=11.17;df=2; p=0.0038) and study location (Q=372.41, df=9; p<0.0001). This study provides valuable information about the relationship between self-efficacy and mathematical creativity, but more research is needed to develop effective and efficient learning strategies.