A tangential observation: the video on the linked page wasn't what I expected. I thought Mistral was a european AI company, so I didnt expect the video to be filmed in San Francisco featuring three people who don't seem to be european.
I'm not against them being a global organization, that's wonderful. I was just surprised. I expected a parisian office and european accents.
rjzzleep 29 minutes ago [-]
Unfortunately Europeans are terrible customers for making money. They ask a lot of questions and they're very stingy with their wallets. Americans on the other hand ...
"A note on out-of-scope use. OCR 4 is a document-understanding model, not a decision-maker. It is not intended for medical diagnosis, legal advice or judgment, high-stakes financial decisions, safety-critical systems, real-time/latency-sensitive processing, or non-document inputs (raw audio, video, etc.). "
Can't wait for the "oh so innovative" manager who will suggest during the next meeting "Ok... but what if WE used it for high-stakes financial decisions on non-document inputs like a photo from my phone?"
I guarantee you somebody on HN is going to comment about this "idea" next week.
weird-eye-issue 54 minutes ago [-]
Why would anybody do that you would simply get terrible results compared to dozens of other more capable models. It's for converting to text not answering questions. Just seems like you need some sort of weird angle to bring out an anti AI stance
alex43578 37 minutes ago [-]
I think his comment is referring to a scenario where a decision is made on financial numbers that are misrecognized. E.g. 9.0% actual is OCR’d as 90%
leoc 17 minutes ago [-]
“I delegated critical financial decisions to my OCR software, and you won’t believe what happened next.”
I was processing 55 year old paper files, most of them severely degraded, with its predecessor model. I was very impressed! I also tried Abbyy Finereader but it didn't even come close in my experience.
philipkglass 58 minutes ago [-]
I used Abbyy Finereader for several years. I loved it. I completed some large projects with it. Modern VLMs put classic FineReader to shame for processing low-resolution/degraded/non-standard text.
I'm personally using the small Qwen 3.5 models. If you have an OCR problem, Mistral OCR 4 is probably great. Open weights models that you can run on a laptop may also work great.
mcbetz 48 minutes ago [-]
Little on differences other than bounding boxes and double the price compared to their previous OCR v3 model from December - https://mistral.ai/news/mistral-ocr-3/ - other benchmarks were used back then.
MostlyStable 47 minutes ago [-]
Does anyone know of OCR benchmarks that include hand-written documents? I'm currently using Gemini pro 3 for this, and error rates are quite good, but it's a little bit pricey, and I'd be interested in a cheaper model that could perform as well, but almost all the OCR benchmarks I'm aware of (and I believe all the ones included in this announcement) are about printed/typeset text.
jimmypk 34 minutes ago [-]
[flagged]
greenleafone7 48 minutes ago [-]
After paying for Mistral and using it for a while I genuinely hated it. It's a productivity black hole and can't realistically compete with anyone. I chose it only because it was European, but no. I'd rather let my one year subscription go to waste than use anything 'Mistral'.
lxgr 4 minutes ago [-]
> After paying for Mistral and using it for a while I genuinely hated it
For OCR?
InsideOutSanta 12 minutes ago [-]
Mistral's coding models aren't on par with current SOTA US and Chinese models if that's what you're referring to, but I rather like their OCR models.
maelito 18 minutes ago [-]
Opposite advice. It's very useful to me for dev and general tasks.
Been using Claude in parallele, it's better not not that much, just 10x (or 100x ?) more expensive.
amunozo 27 minutes ago [-]
Same, I got a refund 3 days later. It is unusable.
adlk 37 minutes ago [-]
what did you use it for and when?
Insanity 57 minutes ago [-]
Recently I tied OCR with Opus 4.8. (I know, not technically right tool for the job). All I needed to do was extract dates from receipts. It got about 20% of the dates wrong yet rated all as “high confidence”.
Should have probably tried a more OCR specific model
nik736 56 minutes ago [-]
Opus is very good at OCR. Way better than the small 1-4B VLMs. If Opus failed, most likely those smaller models will fail as well.
MostlyStable 45 minutes ago [-]
How long have you been testing this? Have you noted a large improvement? I tested Opus for this quite a while ago (maybe 4.5? Whatever was out about a year ago), and it performed quite poorly on my use case.
nik736 41 minutes ago [-]
I have put together an internal benchmark on 1000s of business documents with weird tables, structure, etc. that I run on every relevant model release. Opus 4.8 performs very very well. But it is obviously overkill for the task (and expensive at doing so). I just wanted to respond to the OP.
Insanity 25 minutes ago [-]
I'm assuming that the reason I didn't have good success rate is because it was not scanned documents, but photographs, and lighting conditions weren't always ideal. I think scanned business documents are a happy-case scenario in a way. (obv, you seem to run it against some complex documents, so that's impressive)
bpodgursky 54 minutes ago [-]
I do not believe this story.
Opus 4.8 scanned hundreds of PDFs for me recently with the worst handwriting imaginable. 100% successful, other than one record where even I could not figure out what was written.
Insanity 45 minutes ago [-]
I do not believe this story, because of the message I just posted above.
That's not really productive lol, I'm glad it worked for you but these models are non-deterministic and 'YMMV' very much applies everywhere. I had it parse receipts (in fairness, in variable lightning), all taken from iPhone cameras in the past year. And yeah, not a great job, about 20% failed to get the date correct. (Not outrageously wrong, e.g 05/20/2026 becomes 05/23/2026.
YMMV, glad it worked for you.
pwython 1 minutes ago [-]
Were your images larger than 3.75 megapixels (Opus max resolution)? iPhones generally take 24MP photos.
bpodgursky 39 minutes ago [-]
Are you sure you weren't using Sonnet or a low-effort reasoning mode?
Insanity 32 minutes ago [-]
Yes, lol
9cb14c1ec0 50 minutes ago [-]
I believe it. Makes me curious what your prompt was that got such a good result out of Opus.
pmxi 52 minutes ago [-]
This has been a niche where Mistral has actually been successful. Btw, Hindi and Japanese are bucketed in "Rare Languages," which is odd.
ZiiS 45 minutes ago [-]
I read that as "languages under-represented in the training set".
tdubey 1 hours ago [-]
Are there benchmarks for how this performs on charts, or maybe more accurately, plots? I've yet to find a model that can digitize a plot into X,Y points with some accuracy in my use case of digitizing old datasheets.
jppope 1 hours ago [-]
Is there something wrong with their certificate? Chromium is saying https isn't valid
collabs 1 hours ago [-]
Looks good to me on both brave (on android) and firefox (on windows 11). Lets see what ssl labs says (it is running now)
Edit: I also asked Gemini 3.1 Pro to analyze the certificate and it looks good
It looks like you have shared an `about:certificate` URL containing a chain of three Base64-encoded X.509 TLS/SSL certificates. This specific chain is used to secure connections to *mistral.ai*.
Here is the decoded breakdown of the certificate chain you provided:
## Certificate Chain Overview
This is a standard three-tier certificate chain issued by Google Trust Services for the Mistral AI domain.
---
### 1. Leaf Certificate (End-Entity)
This is the specific certificate issued to the website to verify its identity and encrypt traffic.
thanks I'm going to have to check whats going on with my setup then
ge96 1 hours ago [-]
1000 pages for $4? damn how does it compare to llama parse I wonder
aliljet 45 minutes ago [-]
I was just using infinity parser 2 (flash, to be fair) for pennies self-hosted to run through thousands of pages of documents with remarkable confidence. I decided to use https://huggingface.co/datasets/allenai/olmOCR-bench to determine what was the best OCR tool, yesterday, but I've got no idea what the best is now. What is the dominant OCR eval right now? Between Baidu and Mistral this morning, I wonder if there's a new tool to switch to..
freezed8 36 minutes ago [-]
(jerry from llamaindex here) we're gonna benchmark on ParseBench and report the results!
thenthenthen 1 hours ago [-]
Or Apples local OCR/Vision models?
stri8ted 55 minutes ago [-]
Way too expensive. Google vision OCR (which they failed to compare against), is $1.50 per 1k pages. Vs $4 from Mistral.
gpm 59 minutes ago [-]
Do these models (this one or its competitors) do handwriting recognition?
observationist 46 minutes ago [-]
In the sense that you can get similarity scores for individual characters referenced against a known database of characters written by various individuals. You can get stylometry scores out of small LLMs that do demographic segmentation based on writing style using the same methods.
They won't have the capacity to be fed an image of handwritten text and say "Ahh, this is a note written by Winston Churchill!". You could very easily use these models and your agent framework of choice, like Hermes, the Segment Anything models, and other foss tooling to build a dedicated, specialist handwriting recognition system. Or facial recognition, or fingerprint recognition, etc - these sorts of things can be done very procedurally, without a lot of interpretive AI.
9cb14c1ec0 51 minutes ago [-]
Yes, we have successfully used Mistral OCR for digitizing handwritten forms. You always have low percentage that need human review and adjustment, but overall Mistral has been highly accurate (their price is amazing, too).
weird-eye-issue 53 minutes ago [-]
If you mean handwriting to text then yes
gpm 51 minutes ago [-]
Yep that's what I mean, thanks :)
Rendered at 16:11:10 GMT+0000 (Coordinated Universal Time) with Vercel.
I'm not against them being a global organization, that's wonderful. I was just surprised. I expected a parisian office and european accents.
Can't wait for the "oh so innovative" manager who will suggest during the next meeting "Ok... but what if WE used it for high-stakes financial decisions on non-document inputs like a photo from my phone?"
I guarantee you somebody on HN is going to comment about this "idea" next week.
I'm personally using the small Qwen 3.5 models. If you have an OCR problem, Mistral OCR 4 is probably great. Open weights models that you can run on a laptop may also work great.
For OCR?
Been using Claude in parallele, it's better not not that much, just 10x (or 100x ?) more expensive.
Should have probably tried a more OCR specific model
Opus 4.8 scanned hundreds of PDFs for me recently with the worst handwriting imaginable. 100% successful, other than one record where even I could not figure out what was written.
That's not really productive lol, I'm glad it worked for you but these models are non-deterministic and 'YMMV' very much applies everywhere. I had it parse receipts (in fairness, in variable lightning), all taken from iPhone cameras in the past year. And yeah, not a great job, about 20% failed to get the date correct. (Not outrageously wrong, e.g 05/20/2026 becomes 05/23/2026.
YMMV, glad it worked for you.
https://www.ssllabs.com/ssltest/analyze.html?d=mistral.ai&la...
Looks good so far, A+ on ipv4 as well as ipv6
Edit: I also asked Gemini 3.1 Pro to analyze the certificate and it looks good
It looks like you have shared an `about:certificate` URL containing a chain of three Base64-encoded X.509 TLS/SSL certificates. This specific chain is used to secure connections to *mistral.ai*.
Here is the decoded breakdown of the certificate chain you provided:
## Certificate Chain Overview
This is a standard three-tier certificate chain issued by Google Trust Services for the Mistral AI domain.
---
### 1. Leaf Certificate (End-Entity)
This is the specific certificate issued to the website to verify its identity and encrypt traffic.
* *Subject (Common Name):* `mistral.ai` * *Subject Alternative Names (SANs):* `mistral.ai`, `workers.mistral.ai` * *Issuer:* WE1 (Google Trust Services) * *Valid From:* June 13, 2026 * *Valid To:* September 11, 2026 * *Key Type:* Elliptic Curve (ECDSA)
### 2. Intermediate Certificate
This certificate acts as a bridge between the website's certificate and the trusted Root CA.
* *Subject:* WE1 (Google Trust Services) * *Issuer:* GTS Root R4 (Google Trust Services LLC) * *Valid From:* December 13, 2023 * *Valid To:* February 20, 2029 * *Key Type:* Elliptic Curve (ECDSA)
### 3. Root Certificate
This is the foundational trust anchor pre-installed in browsers and operating systems.
* *Subject:* GTS Root R4 (Google Trust Services LLC) * *Issuer:* GTS Root R4 (Self-signed) * *Valid From:* June 22, 2016 * *Valid To:* June 22, 2036 * *Key Type:* Elliptic Curve (ECDSA)
They won't have the capacity to be fed an image of handwritten text and say "Ahh, this is a note written by Winston Churchill!". You could very easily use these models and your agent framework of choice, like Hermes, the Segment Anything models, and other foss tooling to build a dedicated, specialist handwriting recognition system. Or facial recognition, or fingerprint recognition, etc - these sorts of things can be done very procedurally, without a lot of interpretive AI.