Best Smoothing Function to use in nltk corpus_bleu method

Question

I'm trying to implement an Image Captioning model (CNN + LSTM) and as a validation metric I'm using the BLEU score. To be more precise, the corpus_bleu implementation of nltk.

I tried using different SmoothingFunctions and I'm getting different values for the same candidate and reference.

SmoothingFunction().method1 -> 0025682587115391834

SmoothingFunction().method2 -> 0.01435390900932359

SmoothingFunction().method3 -> 0.005106152442970232

Is there a "default" method that I should use or it depends on the task itself?

Thanks in advance