Evapotranspiration (ET) provides a robust connection between hydrological cycles and surface energy balance. Accurate and near-daily ET estimation has utility in water resources, agricultural management applications, crop yields and drought monitoring. This study describes the implementation of an ET modeling system based on a Priestley-Taylor version of the Two-Source (soil and vegetation) Energy Balance Model (TSEB-PT) within Google Earth Engine environment. TSEB-PT performance was compared with the simpler single-source HSEB (Hybrid Surface Energy Balance) ET model to assess relative advantages and disadvantages for operational application. Results were evaluated across multiple biomes and climatic zones across the US, Europe, and Australia in comparison with eddy covariance data from 30 flux tower sites. Both models produced similar results when considering all biomes at daily, weekly, and monthly timescales. Daily ET metrics for all sites combined yielded comparable results for both models, with a slightly lower root-mean-square error for TSEB-PT (HSEB) of 1.2 (1.3) mm/d and a higher correlation (r) of 0.83 (0.80), but a larger mean percent bias error (MPBE = -9%) than HSEB (MPBE = 1%). TSEB-PT performance was lowest for sites in warm summer humid continental and hot semi-arid climates and in evergreen broadleaf forest cover, while HSEB showed lowest performance in tropical savanna hot semi-arid climates and in savanna covers. Model performance was improved for both cropland and non-cropland sites when TSEB-PT and HSEB ET estimates were combined through simple averaging due to cancellation of opposing errors, showing a promise as potential tools for water resource management on a global scale.