The 2010 World Health Organization (WHO) classification recommends that pancreatic neuroendocrine tumors (PanNETs) be graded on the basis of the mitotic rate and Ki67 index, with grade 2 (G2) PanNETs defined as having a mitotic rate of 2 to 20 mitotic figures/10 high-power fields or a Ki67 index of 3% to 20%. Grade 3 (G3) pancreatic neuroendocrine carcinoma (NEC) is defined as having >20 mitotic figures/10 high-power fields or a Ki67 index of >20%. However, some PanNETs show discordance between the mitotic rate and Ki67 index, usually having a Ki67 index in the G3 range but a mitotic rate suggesting G2, prompting us to examine the clinical significance of the Ki67 index in a large series of clinically well-characterized mitotic G2 PanNETs. Mitotic G2 well differentiated PanNETs, surgically resected at our institutions were reviewed. Of those, 19 cases had a Ki67>20% and were selected as the study group of grade-discordant (mitotic count G2/Ki67 index G3) PanNETs. For comparison, 53 grade-concordant (both mitotic count and Ki67 index G2) PanNETs matched for presenting stage with the discordant group as well as 43 morphologically poorly differentiated (either small cell or large cell type) pancreatic NECs were also included. The percentage of Ki67-positive neoplastic cells was quantified by manual counting of at least 500 cells on printed photographic images of "hot spots." The mean Ki67 index for grade-concordant and grade-discordant PanNETs and poorly differentiated NECs were 8.1% (range, 3% to 20%), 40% (range, 24% to 80%), and 70% (range, 40% to 98%), respectively. Overall, patients with grade-discordant PanNETs had significantly longer survival time compared with the patients with poorly differentiated NEC (median survival of 54.1 vs. 11 mo and 5 y survival of 29.1% vs. 16.1%; P=0.002). In addition, the survival time of the patients with grade-discordant PanNETs was shorter than that of the patients with grade-concordant PanNETs (median survival of 67.8 mo and 5 y survival of 62.4%); however, the difference was not statistically significant (P=0.2). Our data support the notion that the mitotic rate and Ki67 index-based grades of PanNETs can be discordant, and when the Ki67 index indicates G3, the clinical outcome is slightly worse. More importantly, we demonstrate that well differentiated PanNETs that are G3 by Ki67 are significantly less aggressive than bona fide poorly differentiated NECs, suggesting that the current WHO G3 category is heterogenous, contains 2 distinct neoplasms, and can be further separated into well differentiated PanNET with an elevated proliferation rate and poorly differentiated NEC.