Public KG record
jina-ocr-v1
Recorded overview
KG-recorded model related to jina-ocr-v1; detailed English notes are not yet available.
Extract text from images, scans, or PDFs while preserving layout, tables, and document structure.
Recorded details
- Benchmarks: OmniDocBench v1.6：91.14
- Benchmarks: olmOCR-Bench：83.4
- Benchmarks: OmniDocBench v1.6得分91.14
- Benchmarks: olmOCR-Bench得分83.4
- Benchmarks: 较DeepSeek-OCR高7.4分
- Benchmarks: olmOCR-bench
- Benchmarks: OmniDocBench v1.6
- Capabilities: 端到端视觉文档解析
Evidence coverage
The KG currently records 13 known information dimensions and has 5 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Jina AI — releases
- DeepSeek-OCR — based on
- olmOCR-bench — evaluated on
- OmniDocBench v1.6 — evaluated on
- A100 40 GB — evaluated on