alt Hacker NewsMistral OCR 4.1
Comments
At this point I lost all hope for Europe playing any significant role in the AI race. If that’s a good or a bad thing I don’t know, but it seems to me like that’s the reality.
1000 Pages / 3.5€ this is expensive as hell. If this is not fastly superior than something like tesseract it is not worth it.
For anyone interested, I have an ocr pipeline running on rented GPUs, doing around 1000pages for 0.05-01 usd with around 0.8 seconds per page with full bounding boxes support for grounding.
If you’re interested you can find contact to me via this profile.
3.5 usd/1000 pages is just too expensive…
I won't comment on accuracy, but in internal benchmarks, Mistral OCR is significantly faster than comparable APIs.
I've been experimenting with using NuExtract this week on locally OCRing bank statements that don't have a predefined document structure. It's way better than Tesseract or a generic vision-enabled model. It runs great on a single RTX 4090 at the modest throughput I need.
Their hosted, API-based service is something like a third of the cost of this model.
How does this compare to Baidu Unlimited OCR. I've been very impressed with Baidu and it's essentially free to run on a decent computer, other than electricity costs.
Mistral is bumping the price of this thing every release. I think we're at 2x now?
The chinese did it better, mistral is alive thanks to regulations.
How does this compare to 4?
I've got a scan from a book that I OCR with new releases. Ligatures, critical sigla, Fraktur letterforms, subscripts, superscripts, etc.
Nothing special about this model for overly-detailed work like mine.
It's been a while since I last tested (and discontinued my subscription), but the "pro" models from OpenAI dominate. Not surprising, given the price difference, but it would be nice if an OCR-specific model could perform better. It's worth mentioning that even the highest-end models do a pretty poor job with intricate text like mine.