Live data from Hacker News

Mistral AI Launches New 8x22B MOE Model

twitter.com

1–10 of 161 posts

Re: Mistral AI Launches New 8x22B MOE Model

#9
post #7
post #5

8x22b. If this is as good as Mixtral 8x7b we are in for a wonderful time.

I've heard command-r is first opensource to beat gpt4 in benchmarks

It beats the old GPT4 version in lmsys benchmark you can check it out here https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboar... but Command R is commercially licensed We can assume that mistral will do a better job.
Post reply on HN