Grok 1 was open sourced a while ago. Some people did the GGUF's for it so now I have been able to test it. The results are not that good. I hope Elon does a better job in Grok 3.
I updated Based LLM Leaderboard with the Grok 1 and another new model. Here is the link
The other model is Deepseek 2.5 from China. I would expect it to rank higher in health domain but it did not.
Llama 3.1 is still the king.
nostr:note1l49rchxenzek7ygyqtakf4nkzzc3jqw8wsxcljkn4jqxl2nd764q6es8qg