The purpose of this study was to define baseline variability of apparent diffusion coefficient (ADC) on diffusion-weighted MR imaging (DWI) in patients with head and neck squamous cell carcinoma (HNSCC) and to compare it with early treatment-induced ADC change. Patients with American Joint Committee on Cancer stages III and IV HNSCC were imaged with two baseline DWI examinations 1 week apart and a third DWI examination during the 2nd week of curative-intent chemoradiation therapy. Mean ADC was measured in the primary tumor and largest lymph node for each patient on the three DWI scans. Mean baseline percentage differences (%∆ADC) were compared with intratreatment change. The repeatability coefficient for baseline %∆ADC was calculated and compared with intratreatment %∆ADC. Repeatability was also assessed with Bland-Altman plots and the intraclass correlation coefficient (ICC). Sixteen patients underwent double baseline imaging, with 14 also undergoing intratreatment imaging. Baseline nodal disease ADC could be measured in 16 patients, but ADC in primary tumors could only be measured in five patients. The nodal mean (SD) baseline %∆ADC was 8% (± 7%), which was significantly different compared with intratreatment changes of 32% (± 31%) (p = 0.01). Baseline ICC was 0.86 for nodal disease and 0.99 for primary tumor (excellent correlation). The calculated repeatability coefficient for baseline nodal ADC was 15%. No patients had decreases in intratreatment ADC of more than 15%. Baseline ADC variability for HNSCC is less than intratreatment ADC change for nodal disease. Assessment of response should consider intrinsic baseline variability.