<p>Understanding and applying the performance of the global climate models is crucial to studies in future climate, water resources, and environmental assessment. In this paper, we evaluate a new phase of the Coupled Model Intercomparison Project as CMIP6 for the end of the century (2071–2100) under the pathways SSP1-2.6, SSP2-4.5 and SSP5-8.5 and correct them using a weighing technique. Daily and monthly air temperature and precipitation datasets from sixteen CMIP6 models were evaluated with observed values using Pearson’s correlation (<i>r</i>), Root mean square error (<i>RMSE</i>), L-Infinity norm error (<i>LINE</i>), and exponentially weighted error (<i>EWE</i>). The monthly data sets of the projected SSP1-2.6, SSP2-4.5 and SSP5-8.5 climate scenarios for the end of the century were in good agreement with the observed data. However, daily precipitation performs poorly except for daily air temperature. The weighted sum approach was used to ensemble the five best of sixteen CMIP6 models for daily precipitation data based on the baseline period 1995–2014 from the evaluations. To evaluate the performance of the best weights for the models, we have chosen the least squares objective function, which minimizes the sum of squared differences between the observed values and the predicted values. The optimization problem involves finding the best weights that minimize the least square’s objective function. The weighting approach significantly enhances model performance by effectively combining the strengths of individual models. The hybrid model benefits from a balanced integration of its components by assigning higher weights to more accurate models and lower weights to less accurate ones. The results show that the weighting of the ensemble of five models improved the <i>RMSE</i> by 25.8–35.3% over the single models. The outcome of the study will contribute to future assessment of climate change in hydrology, water resources, and related modelling purposes.</p>