All tasks / Models
PaddleOCR-VL-1.6
Baidu's open-weights 0.9B vision-language model for page-level document parsing of text, tables and formulas.
- Baidu (PaddlePaddle)
- Open weights
- Released 28 May 2026
Where it ranks
- SDocuments & OCRModels · Local · 96 on OmniDocBench v1.6 (end-to-end, v1.6_full)
Facts
- Vendor
- Baidu (PaddlePaddle)
- Family
- PaddleOCR-VL
- Released
- 28 May 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 0.96B
- GPU memory to run locally
- ~4 GB (Estimate, no official figure: BF16 weights ≈ 0.96 B × 2 GB + ~1.5 GB runtime overhead.)
- 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 |
|---|---|---|---|---|
| MDPBench (multilingual document parsing) | 78.9% | PaddleOCR-VL-1.6Overall (public split, page-level mean of text, formula and table scores) from the board's leaderboard.json (updated 2026-10-04). | 4 Oct 2026 | huggingface.co |
| OmniDocBench v1.6 (end-to-end, v1.6_full) | 96 | PaddleOCR-VL-1.6Overall 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) | 67.4% | PaddleOCR-VL-1.6Overall (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
- SPaddleOCRParsers & APIs · Local
Earlier versions
- PaddleOCR-VL-1.5 · 28 Jan 2026
- PaddleOCR-VL · 16 Oct 2025