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 3 hours 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 ...
touwer 2 hours ago [-]
You're american?
throwa356262 31 minutes ago [-]
Oh come on!
Mistral has a successful business model and is actually making money.
rsynnott 2 hours ago [-]
~Any borderline-large European tech company will have an office on the US west coast, for sales if nothing else. And probably sales engineering. The timezone difference is eight to ten hours; there is really no way around it.
(I did work for one which had an office in Vancouver, instead; same tz.)
euio757 2 hours ago [-]
Mistral just hired as CMO a Seattle based former Amazon/Google VP¹ , so seems their US based presence is growing.
And US users spend much more than their EU counterpart
flashfaffe2 2 hours ago [-]
To the best of my knowledge, most of the founding team started their careers in the US ( meta,etc..) and their primary investors are US VCs. In that regard, they smartly benefit on both side : US funding and European brains
dominotw 2 hours ago [-]
There is even like an american flag flying high in the background
ericyd 15 minutes ago [-]
I’ve always thought the US Postal Service is such a technological marvel. They somehow manage to identify and route billions of pieces of mail and I have to imagine their tech is significantly more primitive than this. Not only that but US addresses are absurdly non-standardized, you can often write the same address multiple ways and have it deliver to the same location. I’m sure there’s plenty of published knowledge in this area, but whenever I see announcements about OCR it feels like this should be a solved problem if it’s been accomplished at the scale of USPS for many years.
It's cheap at $4/1k, but I'm hesitant to even benchmark this one again since the previous versions were all "98% accurate based on internal benchmarks of 4 pdfs" and ended up falling short of almost everything else on the market [1].
Even in this one, they just report that OlmOCRBench and OmniDocBench have "known limitations" and that's why they report flagship numbers from their internal benchmark.
True, same conclusion, but the few samples I tried showed some real improvements since dec 2025 version.
sreekanth850 1 hours ago [-]
Tested with Malayalam, normal handwriting got accurate but a slight different style got detected as kannada. Have samples if required, which sarvam got done with 99% accuracy leaving one text error.
civet_java 43 minutes ago [-]
I'm curious what's been your experience with Sarvam outside of Indic languages - Indian English (perhaps mixed with romanised indic verbiage) and also documents with complex layouts (figures, tables, etc).
I've been quite curious but hesitant about Indian offerings, particularly because they seem to be priced a little higher than what I would think they should be (I could be wrong and simply be misrembering though).
Mistral keeps reminding us that doesn´t just brew great coffee they can build great AI too.
Hats off to the team.
Mistral O.C.R. (Only Cool Results)
bastawhiz 2 hours ago [-]
The comparisons rank it against GPT and Gemini but not Claude. Is Claude's vision support simply not competitive when it comes to OCR tasks?
abi 2 hours ago [-]
I think until Fable, Claude's vision was significantly worse than GPT and Gemini in my personal experience. I eval almost every vision model since I work on screenshot to code conversion project: https://github.com/abi/screenshot-to-code.
utopiah 3 hours ago [-]
"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 3 hours 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
utopiah 2 minutes ago [-]
Guess you haven't met management yet. Clearly nobody should do that but that's not going to stop them.
alex43578 3 hours 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 3 hours ago [-]
“I delegated critical financial decisions to my OCR software, and you won’t believe what happened next.”
mcbetz 3 hours 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.
Insanity 3 hours 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
rsynnott 2 hours ago [-]
> All I needed to do was extract dates from receipts
Was this... not basically a solved problem like 30 years ago? I'm pretty sure the shareware OCR tool that came with a black and white scanner I had at one point would do better than 20% wrong.
nik736 3 hours 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 3 hours 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 3 hours 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 3 hours 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)
apawloski 1 hours ago [-]
I’m curious what your findings are for the best model for your use case
bpodgursky 3 hours 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 3 hours 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.
2 hours ago [-]
bpodgursky 3 hours ago [-]
Are you sure you weren't using Sonnet or a low-effort reasoning mode?
Insanity 3 hours ago [-]
Yes, lol
9cb14c1ec0 3 hours ago [-]
I believe it. Makes me curious what your prompt was that got such a good result out of Opus.
Ducki 4 hours ago [-]
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 3 hours 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.
MostlyStable 3 hours 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 3 hours ago [-]
[flagged]
JGB100 50 minutes ago [-]
Not well tested. It switched all U.S. (") double quotation marks to UK-style (') single quotation marks, ignoring the source document. Useless in the US.
pmxi 3 hours 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 3 hours ago [-]
I read that as "languages under-represented in the training set".
stri8ted 3 hours ago [-]
Way too expensive. Google vision OCR (which they failed to compare against), is $1.50 per 1k pages. Vs $4 from Mistral.
kojoru 2 hours ago [-]
interesting - an equivalent Azure Document Intelligence service (scanning with layout) is 10$/1k
coulix 2 hours ago [-]
I wonder how it does compare to reducto, pulse, extendai.
Ninjinka 2 hours ago [-]
Is there a complete list of the languages they support, and benchmarks by language, instead of just "Rare Languages"?
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 4 hours ago [-]
Is there something wrong with their certificate? Chromium is saying https isn't valid
collabs 4 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
sscaryterry 46 minutes ago [-]
Why the chart crimes?!
ge96 3 hours ago [-]
1000 pages for $4? damn how does it compare to llama parse I wonder
aliljet 3 hours 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 3 hours ago [-]
(jerry from llamaindex here) we're gonna benchmark on ParseBench and report the results!
thenthenthen 3 hours ago [-]
Or Apples local OCR/Vision models?
gpm 3 hours ago [-]
Do these models (this one or its competitors) do handwriting recognition?
thadt 56 minutes ago [-]
Yes, we've been using Transkribus for this extensively. My wife is a historian who spends quite a bit of time sorting through old letters and diaries, and it has been a considerable quality of life improvement.
Even if you are able to read someone's scratches, having a model to do the bulk lifting saves your eyes a lot of squinting. One thing that makes Transkribus useful for research vs a chat interface is that it can line up its interpretation alongside the original image so you can examine its work directly.
observationist 3 hours 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.
varenc 2 hours ago [-]
I think OP meant converting handwriting to text, not identifying a person based on their handwriting style! (but that sounds quite interesting)
9cb14c1ec0 3 hours 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 3 hours ago [-]
If you mean handwriting to text then yes
gpm 3 hours ago [-]
Yep that's what I mean, thanks :)
v3ss0n 2 hours ago [-]
Not opensource right?
verdverm 1 hours ago [-]
The weights do not appear to be downloadable, "contact sales for self hosting"
dominotw 2 hours ago [-]
starting y axis from 50 and 95 is a bit mileading
greenleafone7 3 hours 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'.
maelito 3 hours 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.
greenleafone7 1 hours ago [-]
Sure, well for me it isn't. It has been awful for even toy tasks that opencode's free plan did without an issue. The general sentiment about it is that it is really bad. I wish I knew before paying.
InsideOutSanta 2 hours 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.
lxgr 2 hours ago [-]
> After paying for Mistral and using it for a while I genuinely hated it
For OCR?
amunozo 3 hours ago [-]
Same, I got a refund 3 days later. It is unusable.
adlk 3 hours ago [-]
what did you use it for and when?
greenleafone7 1 hours ago [-]
The armies of people desperate to defend mistral, scouring the internet for any of the hundreds of negative posts made about it daily is pathetic. There's a reason it needs 'fanboys' and 'defenders'... it sucks. Id have loved to use a European alternative, but Europeans need to get serious and actually offer an alternative that has value other than "it's trash, but it has a Made in Europe badge".
Rendered at 18:26:36 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.
Mistral has a successful business model and is actually making money.
(I did work for one which had an office in Vancouver, instead; same tz.)
¹ The one locally famous for being sued by Amazon for non compete back when non compete were a thing: https://www.geekwire.com/2020/amazon-sues-former-aws-marketi...
https://www.youtube.com/watch?v=XxCha4Kez9c
https://mistral.ai/_astro/cm-engish_ZhlvoT.webp?dpl=6a3a94bd...
Even in this one, they just report that OlmOCRBench and OmniDocBench have "known limitations" and that's why they report flagship numbers from their internal benchmark.
https://getomni.ai/blog/benchmarking-open-source-models-for-...
I've been quite curious but hesitant about Indian offerings, particularly because they seem to be priced a little higher than what I would think they should be (I could be wrong and simply be misrembering though).
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.
Should have probably tried a more OCR specific model
Was this... not basically a solved problem like 30 years ago? I'm pretty sure the shareware OCR tool that came with a black and white scanner I had at one point would do better than 20% wrong.
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.
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.
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)
Even if you are able to read someone's scratches, having a model to do the bulk lifting saves your eyes a lot of squinting. One thing that makes Transkribus useful for research vs a chat interface is that it can line up its interpretation alongside the original image so you can examine its work directly.
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.
Been using Claude in parallele, it's better not not that much, just 10x (or 100x ?) more expensive.
For OCR?