This study was designed to identify clinical predictors of favorable pathology and biochemical recurrence (BCR) in patients with intermediate-risk prostate cancer (IRPCa). Between 2006 and 2012, clinicopathological and oncological data from 203 consecutive men undergoing robot-assisted radical prostatectomy (RARP) for IRPCa were reviewed in a single-institutional retrospective study. Favorable pathology was defined as Gleason score ≤6 and organ-confined cancer as detected by surgical pathology. Logistic regression analysis was used to determine predictive variables of favorable pathology, and the Kaplan-Meier and multivariate Cox regression model were used to estimate BCR-free survival after RARP. Overall, 38 patients (18.7%) had favorable pathology after RARP. Lower quartile prostate-specific antigen density (PSAD) was associated with favorable pathology compared to the highest quartile PSAD after adjusting for preoperative PSA, clinical stage and biopsy Gleason score (odds ratio, 5.42; 95% confidence interval, 1.01-28.97; P = 0.048). During a median 37.8 (interquartile range, 24.6-60.2) months of follow-up, 66 patients experienced BCR. There were significant differences with regard to BCR free survival by PSAD quartiles (log rank, P = 0.003). Using a multivariable Cox proportion hazard model, PSAD was found to be an independent predictor of BCR in patients with IRPCa after RARP (hazard ratio, 4.641; 95% confidence interval, 1.109-19.417; P = 0.036). The incorporation of the PSAD into risk assessments might provide additional prognostic information and identify some patients in whom active surveillance would be appropriate in patients with IRPCa.