The Claude 3 Model Family: Opus, Sonnet, Haiku [pdf]

33 points by 1wheel 2 years ago | 3 comments

alphabetting 2 years ago |

Impressive benchmarks here. The 90% eval for one of the math categories on 0-shot vs 74.5% GPT-4 8-shot is nice.

monkeydust 2 years ago | |

Nice. GPT-4 beater finally perhaps (until 5 is launched which I guess must be pretty soon now)

dang 2 years ago |

Related ongoing thread:

Claude 3 model family - https://news.ycombinator.com/item?id=39590666 - March 2024 (347 comments)