Coral skeletons are valuable archives of past ocean conditions. However, interpretation of coral paleotemperature records is confounded by uncertainties associated with single-element ratio thermometers, including Sr/Ca. A new approach, Sr-U, uses U/Ca to constrain the influence of Rayleigh fractionation on Sr/Ca. Here we build on the initial Pacific Porites Sr-U calibration to include multiple Atlantic and Pacific coral genera from multiple coral reef locations spanning a temperature range of 23.15–30.12°C. Accounting for the wintertime growth cessation of one Bermuda coral, we show that Sr-U is strongly correlated with the average water temperature at each location (r2?=?0.91, P?0.001, n?=?19). We applied the multispecies spatial calibration between Sr-U and temperature to reconstruct a 96?year long temperature record at Mona Island, Puerto Rico, using a coral not included in the calibration. Average Sr-U derived temperature for the period 1900–1996 is within 0.12°C of the average instrumental temperature at this site and captures the twentieth century warming trend of 0.06°C per decade. Sr-U also captures the timing of multiyear variability but with higher amplitude than implied by the instrumental data. Mean Sr-U temperatures and patterns of multiyear variability were replicated in a second coral in the same grid box. Conversely, Sr/Ca records from the same two corals were inconsistent with each other and failed to capture absolute sea temperatures, timing of multiyear variability, or the twentieth century warming trend. Our results suggest that coral Sr-U paleothermometry is a promising new tool for reconstruction of past ocean temperatures.