Once you got your outputs, you can use the below commands to obtain the RMSE:

Errors=Targets-Outputs;

MSE=mean(Errors.^2);

RMSE=sqrt(MSE);

Dear Mohammed Kareem,

You can use support vector regression (SVR) method in ANFIS also i suggest you to see links and attached file on topic.

https://bioresources.cnr.ncsu.edu/resources/comparison-of-artificial-neural-networks-ann-and-adaptive-neuro-fuzzy-inference-system-anfis-models-in-simulating-polygalacturonase-production/

https://www.mathworks.com/matlabcentral/answers/123846-fuzzy-logic-toolbox-anfis-calculate-rmse-mae-r-squared

https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6104032

Article Solid waste forecasting using modified ANFIS modeling

Article A Hybrid Model based on mBA-ANFIS for COVID-19 Confirmed Cas...

Best regards

Dear Mohammed Kareem,

You can find excellent explanations about MAE and RMSE in the following link

Article Root mean square error (RMSE) or mean absolute error (MAE)?–...

Can be done easily.

Extract predicted output and then compare the results with actual output