Take a look at https://biomodhub.github.io/biomod2/articles/examples_1_mainFunctions.html

Maybe this is what are you looking for:

# Get evaluation scores & variables importance get_evaluations(myBiomodModelOut) get_variables_importance(myBiomodModelOut, as.data.frame = TRUE)

If it's not in percentage, just normalize it.

Thanks, but maybe I could have been more clear. I already used get_variables_importance(). The return is based on the permutations and, as far as I could tell, assesses the contribution of each variables to the prediction, answering the question: "to which variable are my predictions the most sensitive ?". What I want to know is the contribution of each variable to model evaluation.

Thanks again