Show HN: Beating OpenAI's structured outputs on cost, accuracy and speed
1–3 of 3 posts
Re: Show HN: Beating OpenAI's structured outputs on cost, accuracy and speed
#2Interesting performance with GPT 3.5, what does performance on Llama look like? What about smaller models like Llama 3.1?
Re: Show HN: Beating OpenAI's structured outputs on cost, accuracy and speed
#3Interesting performance with GPT 3.5, what does performance on Llama look like? What about smaller models like Llama 3.1?
We have some preliminary data with llama3.1 and we find that the smaller model gets to around 70% with BAML (+20% from base), but we'll update this dashboard with llama3.1 by end of week!