The PCMDI Metrics Package (PMP) is an open-source Python-based framework that enables objective "quick-look" comparisons of Earth System Models (ESMs) with one another and available observations. It is used for routine and systematic evaluation of thousands of simulations, with for example CMIP6 at Petabyte scale. PMP results are produced in the context of all model simulations contributed to CMIP6 and earlier CMIP phases, and we are preparing to more seamlessly apply it to next generation model intercomparisons with particular attention to higher resolution simulations and CMIP7 in the future. Among other applications, the PMP enables modeling groups to evaluate changes during the development cycle in the context of the range of structural errors in the multi-model ensemble. The PMP’s comparisons emphasize statistics of large- to global-scale annual cycles, tropical and extratropical modes of variability including ENSO and MJO, and regional monsoons. Newly added metrics in version 3 include cloud feedback and high frequency characteristics of simulated precipitation. The PMP is prototyping the evaluation of higher resolution simulations such as from the HighResMIPs and cloud-resolving E3SM experiments. This presentation will introduce the new implementation and recent updates in the PMP version 3.