Accurate pretreatment grading of pancreatic neuroendocrine tumors (PanNETs) is important to guide patient management. We aimed to evaluate endoscopic ultrasound-guided fine needle biopsy sampling (EUS-FNB) for the preoperative diagnosis and grading of PanNETs. In a tertiary-center setting, patients with suspected PanNETs were prospectively subjected to 22-gauge, reverse-bevel EUS-FNB. The EUS-FNB samples (Ki-67EUS) and corresponding surgical specimens (Ki-67SURG) were analyzed with Ki-67 indexing and thereafter tumor grading, (GRADEEUS) and (GRADESURG) respectively. In total 52 PanNET-patients [median age: 66 years; females: 25/52; surgical resection 22/52 (42%)] were included. EUS-FNB was diagnostic in 44/52 (85%). In 42 available FNB-slides, the median neoplastic cell count was 1034 (IQR: 504–3667) with 32/42 (76%), 22/42 (52%), and 14/42 (33%) cases exceeding 500, 1000, and 2000 neoplastic cells respectively. Ki-67SURG was significantly higher compared to Ki-67EUS with a moderate correlation comparing Ki-67EUS and Ki-67SURG (Pearson r = 0.60, r2 = 0.36, p = 0.011). The GRADEEUS had a weak level of agreement (κ = 0.08) compared with GRADESURG. Only 2/12 (17%) G2-tumors were correctly graded in EUS-FNB-samples. EUS-guided fine needle biopsy sampling is sensitive for preoperative diagnosis of PanNET but biopsy quality is relatively poor. Therefore, the approach seems suboptimal for pretreatment grading of PanNET.