On: Claude 3.5 Sonnet

[alach11]

Claude 3.5 Sonnet took a solid lead on our internal benchmarks over gpt-4-turbo for extraction tasks against large documents.

It may not be great for every workflow, but it certainly hits a sweet spot for intelligence x cost on most of my workflows.

[petra → alach11]

Have anybody tried it against Gemini, for extraction tasks against large documents(its similar to question answering from books, right?)?

[panarky → petra]

Claude 3.5 Sonnet supports a maximum of 200k tokens. Gemini handles 2,000k tokens.