We evaluated global soil organic carbon (SOC) stocks and turnover time predictions from a global land model (ELMv1‐ECA) integrated in an Earth System Model (E3SM) by comparing them with observed soil bulk and Δ14C values around the world. We analyzed observed and simulated SOC stocks and Δ14C values using machine‐learning methods at the ESM gridcell scale (~200 km). In gridcells with sufficient observations, the model provided reasonable estimates of soil carbon stocks across soil depth and Δ14C values near the surface but underestimated Δ14C at depth. Among many explanatory variables, soil albedo index, soil order, plant function type (PFT), air temperature, and SOC content were major factors affecting predicted SOC Δ14C values. The influences of soil albedo index, soil order, and air temperature were primarily important in the shallow subsurface (<=30 cm). We also performed sensitivity studies using different vertical root distributions and decomposition turnover times and compared to observed SOC stock and Δ14C profiles. The analyses support the role of vegetation in affecting soil carbon turnover, particularly in deep soil, possibly through supplying fresh carbon and degrading physical‐chemical protection of SOC via root activities. Allowing for gridcell‐specific rooting and decomposition rates substantially reduced discrepancies between observed and predicted Δ14C values and SOC content. Our results highlight the need for more explicit representation of roots, microbes, and soil physical protection in land models.