Levelmodel
ClassOCR and document
Parameters900M
Contextnot in the notes
Released30 Jan 2026
Opennessopen weights permissive
Runs onsingle datacentre GPU
Statusactive
Benchmark Results
vendor-reported
OmniDocBench v1.6multimodal
overallvendor-reported
95.22
050100
Score in score. Higher is better.
PaddleOCR-VL-1.6 paper table
Real5-OmniDocBenchmultimodal
overallvendor-reported
90.32
050100
Score in score. Higher is better.
PaddleOCR-VL-1.6 paper table
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).
Identity
- Developer
- Z.ai (Zhipu)
- Family
- not in the notes
- Released
- 30 Jan 2026 sourcesregistry date
- 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 0.4B CogViT visual encoder + 0.5B GLM language decoder; checkpoint also holds an untied output head and one MTP layer
- Total parameters
- 900M sources
- Active parameters
- –
- Checkpoint parameters
- 1.33B
- Note
- 0.9B is Z.ai's official figure; 1.33B (1,325,258,240) is the full stored checkpoint
- 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
- open weights permissive
- Licence
- MIT License 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.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
Developer
Z.ai (Zhipu)company, China
Z.ai (Zhipu)company, ChinaModelGLM-OCRZ.ai (Zhipu), OCR and document
GLM-OCRZ.ai (Zhipu), OCR and documentR&D TopicsDocument Parsing Vision-Language Models
Use CaseseKYC Document ExtractionFinanceDocument and Archive ProcessingPublic SectorUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Bank Tabungan Negara (BTN)In production, 1 Jul 2026
GrabIn production, 4 Nov 2025
Komisi Pemilihan Umum (KPU)In production, 4 Mar 2024Deployments of these use cases; none names this model.
PT Bank Tabungan Negara (BTN)In production, 1 Jul 2026GrabIn production, 4 Nov 2025Komisi Pemilihan Umum (KPU)In production, 4 Mar 2024Deployments of these use cases; none names this model.Organisations 1
Sources
- arxiv.org/pdf/2606.03264 https://arxiv.org/pdf/2606.03264
- huggingface.co/api/models/zai-org/GLM-OCR https://huggingface.co/api/models/zai-org/GLM-OCR
- huggingface.co/zai-org/GLM-OCR https://huggingface.co/zai-org/GLM-OCR
- GLM-OCR Technical Report arxiv.org https://arxiv.org/abs/2603.10910
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GLM-OCR", https://aurion.semai.id/models/zhipu-zai-glm-ocr/, records of October 2026.