This study evaluates the simulation of wintertime (15 October, 2019, to 15 March, 2020) statistics of the central Arctic near -surface atmosphere and surface energy budget observed during the MOSAiC campaign with short-term forecasts from 7 state-of-the-art operational and experimental forecast systems. Five of these systems are fully coupled ocean -sea ice -atmosphere models. Forecast systems need to simultaneously simulate the impact of radiative effects, turbulence, and precipitation processes on the surface energy budget and nearsurface atmospheric conditions in order to produce useful forecasts of the Arctic system.This study focuses on processes unique to the Arctic, such as, the representation of liquid -bearing clouds at cold temperatures and the representation of a persistent stable boundary layer. It is found that contemporary models still struggle to maintain liquid water in clouds at cold temperatures. Given the simple balance between net longwave radiation, sensible heat flux, and conductive ground flux in the wintertime Arctic surface energy balance, a bias in one of these components manifests as a compensating bias in other terms. This study highlights the different manifestations of model bias and the potential implications on other terms. Three general types of challenges are found within the models evaluated: representing the radiative impact of clouds, representing the interaction of atmospheric heat fluxes with sub -surface fluxes (i.e., snow and ice properties), and representing the relationship between stability and turbulent heat fluxes.