Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- This runs for free on CPU https://github.com/kouhxp/textsnapby mrkn1
- 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.by Ducki
- 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.
by philipkglass - 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?by bastawhiz
- 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.by abi
- "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.
by utopiah - “I delegated critical financial decisions to my OCR software, and you won’t believe what happened next.”by leoc
- All AI companies are working on models with specialisms. Which are really good at one task.
Mistral is just a bit more forward about this. I guess because they don't need/want to "wow" an audience with generalist user-facing tools (chat) that seem to be experts in everything (but in reality quite often will be a lot of such specialist models chained together).
Here, what you want, is really just a few python scripts away. Voxtral to turn your spoken prompt into text, piped into mistral large 3 with extra system prompts that creates a prompt for ocr and paths to files. It could do this in a loop to actually find those files. which you throw at ocr3, is pased back to misteal large 3 to interpret and turn into decisions.
This is common. It's rather uncommon, really, to build something like this using only one model for everything.
by berkes - 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
- 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
by Insanity - 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.by nik736
- I don't know about Opus but I can tell you with Gemini the subscription product OCR is apparently not done by the model. It used a separate old fashioned OCR tool and gives bad results in my tests.
But with Gemini the API the model does do the OCR resulting in much better accuracy.
by staticman2 - 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.
by bpodgursky - > 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.
by rsynnott - 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.by sreekanth850
- I am making (open) finetunes for malayalam and kannada (and bengali, gujarati, hebrew), and need someone to transcribe a few images for me. Could you contact me if you are interested in helping?by deivid
- 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).
by civet_java - 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.by mcbetz
- All AI labs really need to stop using truncated y-axes for benchmark bar charts...
https://mistral.ai/_astro/cm-engish_ZhlvoT.webp?dpl=6a3a94bd...
by beklein - No, they need to keep using truncated y-axes to increase the hype cycle.by HDBaseT
- 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.
https://getomni.ai/blog/benchmarking-open-source-models-for-...
by themanmaran - That's extremely cheap. I wonder how the companies making a living out of this will survive. They certainly don't charge $0.004 per scan.by menaerus
- True, same conclusion, but the few samples I tried showed some real improvements since dec 2025 version.by coulix
- It'll be interesting to see how this ranks against https://github.com/baidu/Unlimited-OCRby mdrzn
- Right, just announced https://x.com/BaiduAI_News/status/2069322806748410291by cdnsteve
- 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.by ericyd
- >... US addresses are absurdly non-standardized.
Laughs in Indian addresses.
by keeda - There's a lot of weird edge cases with US addresses. Carmel by the sea doesn't have street numbers. Florida keys addresses are often just a mile marker. The mail gets delivered because a human on the route is familiar with them.by TurdF3rguson
- The USPS Remote Encoding Center in Salt Lake City examined 841,260,847 images of poorly written addresses in fiscal year 2025. [0]
Unfortunately the page does not have a base rate--the total number of mail pieces that were not prepared for automated processing. Total first class mail, which includes a lot of bills prepared for automation was 25.7 billion [1]. If 10% of that are non-automated, then .8 / 2.57 = .31 or a third of mail not prepared for automation is handled by "employees look at the image and type in address information"
0. https://facts.usps.com/remote-encoding-center-rec-decipherin...
1. https://about.usps.com/what/financials/10k-reports/fy2025.pd...
by adolph