Project AURIONAI Use-Cases Research & Innovation
Baidu
OCR and document

PaddleOCR-VL-1.5

Baidu compact document VLM, parent of 1.6.

BaiduBaiduChina
Overview figure of PaddleOCR-VL-1.5 from the model card.
Levelmodel
ClassOCR and document
Parameters900M
Contextnot in the notes
Released29 Jan 2026
Opennessunknown
Runs onsingle datacentre GPU
Statusactive

Benchmark Results

vendor-reported
OmniDocBench v1.6multimodal
overallvendor-reported
94.93
050100

Score in score. Higher is better.

PaddleOCR-VL-1.6 paper table2 Jun 2026 arxiv.org
Real5-OmniDocBenchmultimodal
overallvendor-reported
92.05
050100

Score in score. Higher is better.

PaddleOCR-VL-1.6 paper table2 Jun 2026 arxiv.org
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

finetunesuccessor
ERNIE-4.5-0.3B to PaddleOCR-VL-1.6: finetune, high confidencePaddleOCR-VL-1.5 to PaddleOCR-VL-1.6: successor, high confidencePaddleOCR-VL to PaddleOCR-VL-1.5: successor, high confidencePaddleOCR-VLPaddleOCR-VLBaidu, Oct 2025ERNIE-4.5-0.3BERNIE-4.5-0.3BBaiduPaddleOCR-VL-1.5PaddleOCR-VL-1.5Baidu, Jan 2026PaddleOCR-VL-1.6PaddleOCR-VL-1.6Baidu, Jun 2026
BaiduPaddleOCR-VL-1.6 is a child (successor)high confidencemodel card
BaiduPaddleOCR-VL is the parent (successor)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 4 models. Confidence and evidence are the notes' own.

R&D Topics

Document parsing vision-language modelsproduced by

Identity

Developer
Baidu
Family
not in the notes
Released
29 Jan 2026 sourcesannouncement page
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
autoregressive
Total parameters
900M sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
single datacentre GPU
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/pdf/2606.03264 https://arxiv.org/pdf/2606.03264
  2. huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5 https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "PaddleOCR-VL-1.5", https://aurion.semai.id/models/baidu-paddleocr-vl-1-5/, records of October 2026.