Taking advantage of newly released court sentence documents, the current study aims to evaluate the effect of a judge’s gender in juridical decision-making in China. Specifically, we focus on whether the gender of a judge and the gender composition of a collegiate bench have effects on sentence outcomes, after controlling legal circumstances. All the rape sentence documents from 2012 to 2015 uploaded to China Judgments Online were retrieved. The gender of the judge was estimated using the naïve Bayesian classifier. To compensate possible misclassification of a judge’s gender and the gender composition of a collegiate bench, a measurement error model (MC-SIMEX) was implemented for both count (length of sentence in months) and binary (whether defendant receives probation) outcomes. Our results showed that there is no consistent difference between male and female judges on sentencing outcomes. However, a female dominated collegiate bench is associated with shorter length of sentence. Our study not only adds further to the knowledge of the role a judge’s gender plays in the juridical process in China, but provides analysts with an effective way to utilize text-mining techniques in social science research.