[kuprel]

GPT 5.2 loses at everything but they included that

[andxor]

Who are they supposed to compare it to? I'm not sure what makes you think that Grok is even remotely comparable to the frontier models right now.

[rudhdb773b]

Grok has been and still is the best at incorporating search.

4.20 with its 4 agents puts it back at the top for reasoning as well. As soon as it's added to the API, the benchmarks should show that.

[andxor]

I agree it's good for researching current events because of the integration with X.