Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Mistral OCR

mistral.ai

Post reply on HN
Print view View original

31–40 of 450 posts

Re: Mistral OCR

#31

Post by groby_b »

notepad0x90 wrote: post #16

I was just watching a science-related video containing math equations. I wondered how soon will I be able to ask the video player "What am I looking at here, describe the equations" and it will OCR the frames, analyze them and explain them to me. It's only a matter of time before "browsing" means navigating HTTP sites via LLM prompts. although, I think it is critical that LLM input should NOT be restricted to verbal…

Now? OK, you need to screencap and upload to LLM, but that's well established tech by now. (Where by "well established", I mean at least 9 months old ;)

Same goes for "navigating HTTP sites via LLM prompts". Most LLMs have web search integration, and the "Deep Research" variants do more complex navigation.

Video chat is there partially, as well. It doesn't really pay much attention to gestures & expressions, but I'd put the "earliest possible" threshold for that a good chunk closer than 5 years.

Re: Mistral OCR

#32

Post by dgfl »

newfocogi wrote: post #5

They say: "releasing the API mistral-ocr-latest at 1000 pages / $" I had to reread that a few times. I assume this means 1000pg/$1 but I'm still not sure about it.

Great example of how information is sometimes compartmentalized arbitrarily in the brain: I imagine you have never been confused by sentences such as “I’m running at 10 km/h”.

Re: Mistral OCR

#35

Post by z2 »

Is there a reliable handwriting OCR benchmark out there (updated, not a blog post)? Despite the gains claimed for printed text, I found (anecdotally) that trying to use Mistral OCR on my messy cursive handwriting to be much less accurate than GPT-4o, in the ballpark of 30% wrong vs closer to 5% wrong for GPT-4o.

Edit: answered in another post: https://huggingface.co/spaces/echo840/ocrbench-leaderboard

Re: Mistral OCR

#36

Post by zellyn »

busymom0 wrote: post #22
andoando wrote: post #18

Bit unrelated but is there anything that can help with really low resolution text? My neighbor got hit and run the other day for example, and I've been trying every tool I can to make out some of the letters/numbers on the plate https://ibb.co/mr8QSYnj

There are photo enhancers online. But your picture is way too pixelated to get any useful info from it.

Maybe if you had multiple frames, and used something very clever?

Re: Mistral OCR

#39

Post by groby_b »

bredren wrote: post #14
newfocogi wrote: post #5

They say: "releasing the API mistral-ocr-latest at 1000 pages / $" I had to reread that a few times. I assume this means 1000pg/$1 but I'm still not sure about it.

Ya, presumably it is missing the number `1.00`.

Not really. When you go 60 mph (or km/h) you don't specify the 1.00 for the hours either. pages/$ is the unit, 1000 is the value.

Re: Mistral OCR

#40

Post by cxie »

The new Mistral OCR release looks impressive - 94.89% overall accuracy and significantly better multilingual support than competitors. As someone who's built document processing systems at scale, I'm curious about the real-world implications.

Has anyone tried this on specialized domains like medical or legal documents? The benchmarks are promising, but OCR has always faced challenges with domain-specific terminology and formatting.

Also interesting to see the pricing model ($1/1000 pages) in a landscape where many expected this functionality to eventually be bundled into base LLM offerings. This feels like a trend where previously encapsulated capabilities are being unbundled into specialized APIs with separate pricing.

I wonder if this is the beginning of the componentization of AI infrastructure - breaking monolithic models into specialized services that each do one thing extremely well.

Post reply on HN