Mistral OCR 4.1

130

sspelk about 3 hours ago 40 commentsRead Article on docs.mistral.ai

⚡ Community Insights

Discussion Sentiment

75% Positive

Analyzed from 975 words in the discussion.

Discussion (40 Comments)Read Original on HackerNews

ComputerPerson•about 2 hours ago

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.

kmitz•about 1 hour ago

I got the opposite experience very recently : tried to OCR a bunch of handwritten emails addresses with chatGPT and I had to make so many corrections that I gave up. Whereas Mistral nailed it on first pass.

rtaylorgarlock•about 2 hours ago

Yet: how is pricing? Evaluating contents and routing appropriately isn't a new challenge in OCR, one of the oldest fields of applications in ML. Thus, how do the smaller open models perform in tandem with relatively pricy $/pg models & APIs? Your use case is remarkably rare relative to the volume and price sensitivity of enterprise data warehouse ops.

petcat•about 2 hours ago

> the "pro" models from OpenAI dominate. Not surprising considering the price difference, but it would ne nice if an OCR-specific model could do better.

I haven't been impressed with any of Mistral's models. They obviously realized that they couldn't compete at the frontier so they decided to go for smaller focused models but even those have not been that good.

king_crimson•about 2 hours ago

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.

kubb•about 2 hours ago

It's not a race. You don't get anything for winning.

Palpatineli•about 1 hour ago

How about "being able to align ASI somewhat to your values"?

ben_w•about 1 hour ago

True, but that isn't EU/US/China, it's OpenAI/Anthropic/Grok/ …/DeepMind (based in UK)/… DeepSeek

With a lot of Chinese nationals in American companies, and an American corporation owning DeepMind, and a lot of people very upset with all of them at the same time, this is very messy.

BenzeneDream•29 minutes ago

? It absolutely is a race. Whether thats a positive thing or not is debatable but every lab is definitely in a race. What prize do you win? Imagine a world where only one country has AGI/ASI. Or a world where Europe only gets access to frontier models 6 months later. Far from ideal.

vrganj•3 minutes ago

This presupposes AGI or ASI are a real, reachable thing. My read is they might be, but not as LLMs. Until there's a fundamental rearchitecture, I'm AGI-agnostic and given that view, it doesn't seem rational to bet the house on it.

We'll see.

ux266478•22 minutes ago

> What prize do you win? Imagine a world where only one country has AGI/ASI.

"Winning the race" doesn't give you that in any meaningful capacity. It gives you, at the absolute most, a temporary window where that's the case. See: nuclear weapons.

tedggh•13 minutes ago

A race to the bottom.

procgen•about 2 hours ago

The only prize is control of the light cone.

bpodgursky•about 2 hours ago

It's red queen. You stay alive by winning, you lose everything by losing.

ben_w•about 1 hour ago

Not sure you get either outcome in either case.

Race dynamics increases p(doom) for everyone.

The non-doom scenarios include "utopia for all", and "power flows to investors, not citizens of whichever nation the winning model's corp. was registered in".

Independently, "oh look all the investors went bankrupt" can happen in both "doom" and "normal technology" timelines.

ChrisClark•about 1 hour ago

Unless you manage to build a god, and keep it under control... okay, we're all going to lose

thadt•about 2 hours ago

Yeah? And here I've been a happy Transkribus customer for some time now. If there are better models or interfaces out there for analyzing historical handwriting, I'll definitely take a look.

piterrro•about 1 hour ago

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…

aliljet•about 1 hour ago

Accuracy is truly what people die for in the OCR game. Price isn't the primary function here.. it's an equation of price, accuracy, speed, and in mayn cases regulation.

merb•39 minutes ago

Tbf even with tesseract you already get shit ton of accuracy and you can probably do these 1000 pages for way less than 3.5€. For 3.5€ you can spin up a cloud instance with 8vCPU+32gb on gcloud for 11 hours (or 11 instances for an hour) which can do way more than 1000 pages per hour on tesseract. It takes you around 6 second per page +-4 seconds start/stop depending on what you are doing on that instance size without too much optimization (you can probably even run multiple processes on a single node)

Google documentai costs 1.5$ per 1000 which is probably better in quality and speed.

piterrro•37 minutes ago

Most use cases dont need that kind of accuracy, just doesnt justify the 3-4usd range. I build for that exact case (tender documents, we’re processing north of 100k pages per day), it doesnt need to recognize scanned written text from 1930s, its usually pdf/docs/scanned printed pages. The accuracy is great, bounding boxes are must have for proper grounding for building answers by LLMs. Tesseract was too slow and not enough in some cases (for example tables or images which we also recognize and describe)

pogue•17 minutes ago

If you're getting inaccurate results from OCR what's the purpose of even doing it? Inaccuracy of text of any kind seems like a completely obvious failure of the entire purpose of scanning text into a computer.

x3ro•about 1 hour ago

You should put contact details in your profile :)

merb•about 2 hours ago

1000 Pages / 3.5€ this is expensive as hell. If this is not fastly superior than something like tesseract it is not worth it.

beernet•about 1 hour ago

Agreed. Does the GTM team there really sit together like "oh yeah, that sounds reasonable" while being totally beyond typical market prices?

mainecoder•about 2 hours ago

The chinese did it better, mistral is alive thanks to regulations.

maelito•21 minutes ago

No it's the other way round : the Chinese do better thanks to regulations : massive amounts of money from Big tech and public money.

mangecoeur•about 1 hour ago

i.e. it's one AI company that's basically guaranteed to never fail since it has a market niche guaranteed by European companies and governments.

petcat•about 1 hour ago

Which is also why their most recent model "Shieldstral" does nothing except monitor and moderate internet content.

After stuff like Chat Control I think they're obviously seeing a big demand for this kind of "internet safety" technology in Europe.

rtaylorgarlock•about 2 hours ago

I've been a bit more careful about complaining about regulations broadly due to competitive advantage, e.g. ITAR

ad_fontes•about 1 hour ago

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.

Johnny_Bonk•about 2 hours ago

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.

spiderfarmer•about 1 hour ago

Where do your documents go?

rescbr•about 1 hour ago

They go to the decent computer hosting the model, which can be yours if you pay the electricity costs

ianhawes•about 2 hours ago

I won't comment on accuracy, but in internal benchmarks, Mistral OCR is significantly faster than comparable APIs.

hmokiguess•33 minutes ago

Whoever is paying all that for OCR is being scammed.

raverbashing•16 minutes ago

* scanned

maz1b•about 2 hours ago

How does this compare to 4?