Rates of benthic denitrification were measured using two techniques, membrane inlet mass spectrometry (MIMS) and isotope ratio mass spectrometry (IRMS), applied to sediment cores from two NO₃⁻‐rich streams draining agricultural land in the upper Mississippi River Basin. Denitrification was estimated simultaneously from measurements of N₂:Ar (MIMS) and ¹⁵N[N₂] (IRMS) after the addition of low‐level ¹⁵NO₃⁻ tracer (¹⁵N:N = 0.03–0.08) in stream water overlying intact sediment cores. Denitrification rates ranged from about 0 to 4400 μmol N·m⁻²·h⁻¹ in Sugar Creek and from 0 to 1300 μmol N·m⁻²·h⁻¹ in Iroquois River, the latter of which possesses greater streamflow discharge and a more homogeneous streambed and water column. Within the uncertainties of the two techniques, there is good agreement between the MIMS and IRMS results, which indicates that the production of N₂ by the coupled process of nitrification/denitrification was relatively unimportant and surface‐water NO₃⁻ was the dominant source of NO₃⁻ for benthic denitrification in these streams. Variation in stream NO₃⁻ concentration (from about 20 μmol/L during low discharge to 1000 μmol/L during high discharge) was a significant control of benthic denitrification rates, judging from the more abundant MIMS data. The interpretation that NO₃⁻ concentration directly affects denitrification rate was corroborated by increased rates of denitrification in cores amended with NO₃⁻. Denitrification in Sugar Creek removed ≤11% per day of the in‐stream NO₃⁻ in late spring and removed roughly 15–20% in late summer. The fraction of NO₃⁻ removed in Iroquois River was less than that of Sugar Creek. Although benthic denitrification rates were relatively high during periods of high stream flow, when NO₃concentrations were also high, the increase in benthic denitrification could not compensate for the much larger increase in stream NO₃⁻ fluxes during high flow. Consequently, fractional NO₃⁻ losses were relatively low during high flow.