Benchmarking the Most Reliable Document Parsing API • Hacker News Board

Re: Benchmarking the Most Reliable Document Parsing API

#11

Post by diptanu » Thu, Nov 06, 2025, 7:50 PM UTC

ianhawes wrote: post #7

diptanu wrote: post #4

Earlier quoted context omitted.

Hey! I am the founder of Tensorlake. We benchmarked the models that our customers consider using in enterprises or regulated industries where there is a big need for processing documents for various automation. Benchmarking takes a lot of time so we focussed on the ones that we get asked about. On Gemini and other VLMs - we excluded these models because they don't do visual grounding - aka they don't provide page lay…

I just tested a non-English document and it rendered English text. Does your model not support anything other than English?

It does, we have users in Europe and Asia using it with non English languages. Can you please send me a message at diptanu at tensorlake dot ai, would love to see why it didn’t work.

Re: Benchmarking the Most Reliable Document Parsing API

#12

Post by diptanu » Thu, Nov 06, 2025, 7:53 PM UTC

recursive4 wrote: post #9

Curious how it compares to https://github.com/datalab-to/chandra

We haven’t tested Chandra yet, because it’s very new. Under the hood Tensorlake is very similar to Marker - it’s a pipeline based OCR API, we do layout detection, Text Recognition and Detection, Table Structure Understanding, etc. We then use VLMs to enrich the results. Our models are much bigger than marker, and thus takes a little longer to parse documents. We optimized for accuracy. We will have a faster API soon.

Re: Benchmarking the Most Reliable Document Parsing API

#13

Post by kissgyorgy » Thu, Nov 06, 2025, 8:05 PM UTC

I just tried it out and docling finished in 20s (with pretty good results) the same document which in Tensorlake is still pending for 10 minutes. I won't even wait for the results.

Re: Benchmarking the Most Reliable Document Parsing API

#14

Post by goldenjm » Thu, Nov 06, 2025, 8:19 PM UTC

This would be more helpful if it included DeepSeek-OCR, PaddleOCR-VL and MinerU 2.5. In general, I've found that OmniDocBench is a reliable benchmark, perhaps surprisingly because it is made by the same team as MinerU. They updated their benchmark table recently: https://github.com/opendatalab/OmniDocBench#end-to-end-evalu.... There are some other models that score above DeepSeek-OCR as well that I'm not as familiar with.

Re: Benchmarking the Most Reliable Document Parsing API

#15

Post by diptanu » Thu, Nov 06, 2025, 9:24 PM UTC

kissgyorgy wrote: post #13

I just tried it out and docling finished in 20s (with pretty good results) the same document which in Tensorlake is still pending for 10 minutes. I won't even wait for the results.

There was an unusual traffic spike around that time, if you try now it should be a lot faster. We were calling up but there was not enough GPU capacity at that time.