Llama 3.1: Our most capable models to date

[dupe]<p>More discussion: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=41046540">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=41046540</a><p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=41046773">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=41046773</a>

405B is already being served on WhatsApp!<p><a href="https:&#x2F;&#x2F;ibb.co&#x2F;kQ2tKX5" rel="nofollow">https:&#x2F;&#x2F;ibb.co&#x2F;kQ2tKX5</a>

MMLU PRO is the benchmark I trust the most. I noticed they are using 5 shots and CoT. Is that true for GPT4 and Sonnet as well?