Does anyone have an actual answer to the question? I have someone I’m trying to convert to Grapheneos but who is also trying to run a business, making a simple “block unknown callers” not very tenable.

Sure they did. They even had a notation on the results table that grok passed expect when reasoning mode was off.

ETA: they even posted all the reasoning texts for the models they tested

I’m not really ever in the market for drives with forty thousand power on hours, are you?