←back to thread

Show HN: Qwen-2.5-32B is now the best open source OCR model

(github.com)
208 points themanmaran | 1 comments | 01 Apr 25 17:00 UTC | HN request time: 0.209s | source

Last week was big for open source LLMs. We got:

- Qwen 2.5 VL (72b and 32b)

- Gemma-3 (27b)

- DeepSeek-v3-0324

And a couple weeks ago we got the new mistral-ocr model. We updated our OCR benchmark to include the new models.

We evaluated 1,000 documents for JSON extraction accuracy. Major takeaways:

- Qwen 2.5 VL (72b and 32b) are by far the most impressive. Both landed right around 75% accuracy (equivalent to GPT-4o’s performance). Qwen 72b was only 0.4% above 32b. Within the margin of error.

- Both Qwen models passed mistral-ocr (72.2%), which is specifically trained for OCR.

- Gemma-3 (27B) only scored 42.9%. Particularly surprising given that it's architecture is based on Gemini 2.0 which still tops the accuracy chart.

The data set and benchmark runner is fully open source. You can check out the code and reproduction steps here:

- https://getomni.ai/blog/benchmarking-open-source-models-for-...

- https://github.com/getomni-ai/benchmark

- https://huggingface.co/datasets/getomni-ai/ocr-benchmark

Show context
azinman2 ◴[01 Apr 25 20:05 UTC] No.43550807[source]▶
News update: OCR company touts new benchmark that shows its own products are the most performant.
replies(3): >>43550853 #>>43551091 #>>43551815 #
johnisgood ◴[01 Apr 25 20:38 UTC] No.43551091[source]▶
Someone should try to reproduce and post it here. I can't, my PC is about 15 years old. :(

(It is not a joke.)

replies(1): >>43551213 #
rustc ◴[01 Apr 25 20:53 UTC] No.43551213[source]▶
Reproducing the whole benchmark would be expensive, OmniAi starts at $250/month.
replies(2): >>43551436 #>>43551449 #
1. themanmaran ◴[01 Apr 25 21:16 UTC] No.43551436[source]▶
Generally running the whole benchmark is ~$200, since all the providers cost money. But if anyone wants to specifically benchmark Omni just drop us a note and we'll make the credits available.