cudnn.benchmark is a global option, so if you first disable and later enable it, it will be used again if you pass some input to your model, which might yield non-deterministic results.
If you would like to use the benchmark mode, then yes.
If activated, cudnn will perform some benchmarking internally using the current input shape and your model to determine the best performing algorithms to use for the operations.
This will most likely slow down the first iteration, but should generally yield better performance for the following iterations.
However, if you are dealing with varying input shapes, cudnn will benchmark each of them, thus slowing down your code.