All tasks / Models
TeleOCR
Open-weights ~1.2B vision-language model for parsing digital and camera-captured documents; formerly NaviDC-OCR.
- XingChen-AGI
- Open weights
- Released 17 Aug 2026
Where it ranks
- SDocuments & OCRModels · Local · 97 on OmniDocBench v1.6 (end-to-end, v1.6_full)
Facts
- Vendor
- XingChen-AGI
- Family
- TeleOCR
- Released
- 17 Aug 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 1.42B
- GPU memory to run locally
- ~5 GB (Estimate, no official figure: BF16 weights ≈ 1.42 B × 2 GB + ~1.5 GB runtime overhead. Size is the Hugging Face safetensors total; the model card says ~1.2B.)
- Access
- Free (open weights)
- Last verified
- 18 Oct 2026
Price from huggingface.co, 18 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| OmniDocBench v1.6 (end-to-end, v1.6_full) | 97 | TeleOCROverall score in the README's end-to-end table 'OmniDocBench (v1.6_full)' (last leaderboard update 2026-09-11). | 11 Sep 2026 | github.com |
| ParseBench (models) | 58.7% | TeleOCROverall (mean of tables, charts, content faithfulness, semantic formatting, visual grounding) from leaderboard.csv in the ParseBench repo (last leaderboard commit 2026-10-09). | 9 Oct 2026 | github.com |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.