TeleOCR for Chemical Companies: A Free Model That Tops One Document Test
TeleOCR is a small, free model that reads documents, and it is first on OmniDocBench, the independent document test, on whole documents and on tables. A second test ranks it 88th. For a chemical distributor or producer reading supplier documents, the gap between the two says what to check before you rely on it.
TeleOCR at a glance
What TeleOCR is.
TeleOCR is a document reading model of about 1.2 billion parameters, small enough to run on your own servers. You give it a page as an image, and it returns the text, the tables, and the formulas in order. Its weights are free to download under the Apache 2.0 license.
Its makers released it on 17 August 2026 as NaviDC-OCR and renamed it TeleOCR on 10 September. They built it for both digital documents and pages photographed with a camera. Its model card lists Chinese and English.
How TeleOCR reads on OmniDocBench.
OmniDocBench scores whole pages: text, tables, and formulas together. It is run by OpenDataLab, which also makes MinerU, a free model it ranks; MinerU places fourth.
Whole-document reading score: text, tables, and formulas, out of 100
The five best readers are small free models. TeleOCR is first by 0.44 points, a small lead. Gemini 3 Pro is 4 points back.
OmniDocBench leaderboard11 Sep 2026
First on one test, 88th on another.
ParseBench, run by LlamaIndex, which sells a rival tool, scores five things a document reader must get right. TeleOCR is near the top on one of them and in the bottom half on the other four. Each track runs from first place on the left to last on the right.
OmniDocBench35 results
Whole documents
Text, tables, and formulas together
1stof 35score 96.91Tables
Table structure
1stof 35score 96.82
OmniDocBench leaderboard11 Sep 2026
ParseBench142 results
Overall
The average of the five below
88thof 142score 58.67Tables
Merged cells and headers that span rows
102ndof 142score 72.74Charts
Data points read off a chart
100thof 142score 9.97Content
Nothing left out, nothing made up, read in order
83rdof 142score 85.39Formatting
Bold, strikethrough, superscripts, and headings kept
117thof 142score 45.13Tracing to the Page
Each piece of text traced back to its place on the page
5thof 142score 80.14
ParseBench leaderboard29 Sep 2026
TeleOCR for chemical distributors and producers.
Where its results point. No public test used a chemical company's own documents, so treat each of these as a job to test, not a result.
Read Supplier Documents
Pull the fields you need from a TDS, an SDS, or a CoA into your own systems.
Run it on 20 of your own documents, including a scan and a multi-page SDS, and check every value against the page.
Pull Price Lists Into Rows
Turn a supplier's multi-page price list into rows you can quote from.
Check merged cells and footnotes. The second test scored it low on merged cells and headers that span rows.
Keep Documents In House
Read documents on your own servers when a file should not leave your company.
Someone has to own the setup. Compare its running cost with a paid reader's price per page.
Where TeleOCR goes wrong.
The second test finds gaps the first one does not score.
Charts Are a Blind Spot
It scored 9.97 out of 100 on reading data points from charts, 100th of 142. Do not let it read a chart on a spec sheet or a report unchecked.
ParseBench leaderboard29 Sep 2026
Formatting Gets Lost
It scored 45.13 on keeping bold, strikethrough, superscripts, and headings, 117th of 142. A superscript in a unit or a struck-out price can change the meaning of a line.
ParseBench leaderboard29 Sep 2026
Two Languages Listed
Its model card lists Chinese and English. A supplier document in German or Spanish needs its own test.
TeleOCR model cardNo date stated
You Run It Yourself
It is free, but it runs on your own servers, so someone has to set it up and keep it running. There is no published price to compare with a paid service.
TeleOCR model cardNo date stated
Questions about TeleOCR.
Short answers, from the same sources as the rest of this page.
What is TeleOCR?
A free document reading model of about 1.2 billion parameters, published on Hugging Face under the Apache 2.0 license. It was released as NaviDC-OCR on 17 August 2026 and renamed TeleOCR on 10 September.
Is TeleOCR the best OCR model?
It is first of 35 on OmniDocBench, the independent document test, on whole documents and on tables. On ParseBench, a test run by a company that sells a rival tool, it ranks 88th of 142 overall.
Is TeleOCR free?
Its weights are free under the Apache 2.0 license. You pay for the servers that run it.
Can TeleOCR read safety data sheets and certificates of analysis?
No public test used them. It reads whole documents and tables well on OmniDocBench, but scored low on charts and formatting on ParseBench. Test it on your own SDSs and CoAs, and check every value.
Why do the two document tests disagree?
They use different documents and score different things. OmniDocBench scores text, tables, and formulas. ParseBench also scores charts, formatting, and tracing text to the page, and it ranks a product its maker sells.
Sources.
- OmniDocBench leaderboard OpenDataLab (Shanghai AI Lab), which also makes MinerU, a free model it ranks.Published 11 Sep 2026 · Vailent checked 30 Sep 2026
- ParseBench leaderboard LlamaIndex, which sells LlamaParse, a product it ranks.Published 29 Sep 2026 · Vailent checked 30 Sep 2026
- TeleOCR model card The makers' own page.States no date · Vailent checked 30 Sep 2026