LAUSR

ABSTRACT Using the historical simulations from 27 models in phase 5 of the Coupled Model Intercomparison Project (CMIP5) and 27 models in phase 6 (CMIP6), the authors evaluated the differences between CMIP5 and CMIP6 models in simulating the climate mean of extreme temperature over China through comparison with observations during 1979–2005. The CMIP6 models reproduce well the spatial distribution of annual maxima of daily maximum temperature (TXx), annual minima of daily minimum temperature (TNn), and frost days (FD). The model spread in CMIP6 is reduced relative to CMIP5 for some temperature indices, such as TXx, warm spell duration index (WSDI), and warm days (TX90p). The multimodel median ensembles also capture the observed trend of extreme temperature. However, the CMIP6 models still have low skill in capturing TX90p and cold nights (TN10p) and have obvious cold biases or warm biases over the Tibetan Plateau. The ability of individual models varies for different indices, although some models outperform the others in terms of the average of all indices considered for different models. By comparing different version models from the same organization, the updated CMIP6 models show no significant difference from their counterparts from CMIP5 for some models. Compared with individual models, the median ensembles show better agreement with the observations for temperature indices and their means. Graphical abstract