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

Mistral OCR 4

mistral.ai

Post reply on HN
Print view View original

21–30 of 143 posts

Re: Mistral OCR 4

#21

Post by 9cb14c1ec0 »

gpm wrote: post #11

Do these models (this one or its competitors) do handwriting recognition?

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).

Re: Mistral OCR 4

#22

Post by 9cb14c1ec0 »

bpodgursky wrote: post #16
Insanity wrote: post #13

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

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.

I believe it. Makes me curious what your prompt was that got such a good result out of Opus.

Re: Mistral OCR 4

#23

Post by greenleafone7 »

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'.

Re: Mistral OCR 4

#25

Post by MostlyStable »

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.

Re: Mistral OCR 4

#26

Post by observationist »

gpm wrote: post #11

Do these models (this one or its competitors) do handwriting recognition?

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.

Re: Mistral OCR 4

#27

Post by Insanity »

bpodgursky wrote: post #16
Insanity wrote: post #13

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

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.

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.

Re: Mistral OCR 4

#28

Post by ZiiS »

pmxi wrote: post #19

This has been a niche where Mistral has actually been successful. Btw, Hindi and Japanese are bucketed in "Rare Languages," which is odd.

I read that as "languages under-represented in the training set".

Re: Mistral OCR 4

#29

Post by aliljet »

ge96 wrote: post #6

1000 pages for $4? damn how does it compare to llama parse I wonder

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..

Re: Mistral OCR 4

#30

Post by MostlyStable »

nik736 wrote: post #14
Insanity wrote: post #13

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

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.

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.
Post reply on HN