A set of diagnostics that utilize long-term high frequency measurements from the DOE Atmospheric Radiation Measurement (ARM) program is developed for evaluating the regional simulation of clouds, radiation and precipitation in climate models. Basic performance metrics are computed to measure the accuracy of mean state and variability of climate models. The evaluated physical quantities include vertical profiles of clouds, temperature, relative humidity, cloud liquid water path, total column water vapor, precipitation, sensible and latent heat fluxes and radiative fluxes. Process-oriented diagnostics focusing on individual cloud and precipitation-related phenomena (i.e., precipitation diurnal cycle, convection onset) are developed for the evaluation and development of specific model physical parameterizations. Initial application of  the ARM diagnostics to the DOE Accelerated Climate Modeling for Energy (ACME) and the Cloupled Model Intercomparison Project (CMIP) models and the Cloud Feedback Model Intercomparison Project (CFMIP) models will be discussed.