Post
171
Remember when @mistralAI said large enough and casually dropped Mistral-Large-Instruct-2407? π€―π
It's now on http://lmsys.org! π It works amazing for instruction following, hard prompts, coding, and longer queries with only 123 billion parameters. π‘π»
It outperforms GPT4-Turbo and Claude 3 Opus on Coding, Hard Prompts, Math, and Longer Query categories. ππ’
It also outperforms Llama 3.1 405B on Instruction Following while being 3x smaller. ππ
It also does exceedingly well on the Ai2 ZebraLogic logistic reasoning benchmark despite being much smaller than the other models. π¦π€
Mistral is not here to take part but to take over! ππ
Model: https://mistral.ai/news/mistral-large-2407/
171
Remember when @mistralAI said large enough and casually dropped Mistral-Large-Instruct-2407? π€―π
It's now on http://lmsys.org! π It works amazing for instruction following, hard prompts, coding, and longer queries with only 123 billion parameters. π‘π»
It outperforms GPT4-Turbo and Claude 3 Opus on Coding, Hard Prompts, Math, and Longer Query categories. ππ’
It also outperforms Llama 3.1 405B on Instruction Following while being 3x smaller. ππ
It also does exceedingly well on the Ai2 ZebraLogic logistic reasoning benchmark despite being much smaller than the other models. π¦π€
Mistral is not here to take part but to take over! ππ
Model: https://mistral.ai/news/mistral-large-2407/