Vision

Like open source? Probably llama3.1/2 or whatever the multimodal one is. Although it will be no where close to openai lol

Closed source, sonnet and gemini are very good

Hi!

Either as long as they can run locally.

What about qwen

Haven't heard much about qwen's multimodal capability tbh

I wouldn't trust academic benchmarks too much. I feel like most models these days are overfitting to the benchmarks out there

oh, really? That's interesting.

with OAI vision for a 8000 character document (with lot's of numbers), I am getting 1 character wrong

i'd like a similar model but running locally