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

by 1wheelon 3/4/2024, 2:07 PMwith 3 comments

by alphabettingon 3/4/2024, 2:16 PM

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

https://twitter.com/AnthropicAI/status/1764653830468428150

by dangon 3/4/2024, 7:19 PM

Related ongoing thread:

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