Whether they do some kind of reasoning or not, they have all the biases included that come from their training/programming: what material was included, how that material is handled, etc.
AFAIAA, there's certainly not even a single frontier model, trained on "the internet", that is able to process information factually and in an unbiased manner.
So, they're not really reasoning impartially, as a computer "should" be wont to do. They're regurgitating biases. In a word: parroting.
Can you coax a model into seeming fair, via context? Sure. But, the baseline would be need to be based on reasoning ab initio, to qualify as reasoning. Otherwise, they are, again, parroting.
It's important to not mis-state what is or is not "emergent reasoning", or else people will think we have something that we don't, because some expert said so.
Disagree? Do you think that there is at least one accessible frontier model trained on the internet that is not parroting the baises of its creators and users, and performs its own "emergent reasoning" (instead of just doing something that mimics doing that)? Then please link to it.
