Model card
dots.ocr 3B.
RedNote HILabopen-source3B paramsVision-Language ModelApache 2.0
Unified document parsing model. Single 1.7B LLM foundation with prompt-based switching. SOTA on multilingual OCR across 100+ languages including Tibetan, Kannada, Russian.
§ 01 · Benchmarks
Every benchmark dots.ocr 3B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | olmOCR-Bench | Computer Vision · Document Parsing | tables | 88.3% | #2 | — | source ↗ |
| 02 | olmOCR-Bench | Computer Vision · Document Parsing | pass-rate | 79.1% | #9 | — | source ↗ |
| 03 | OmniDocBench | Computer Vision · Document Parsing | composite | 88.4% | #12 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 04 · Related models
Other RedNote HILab models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
github-readme
2
results
OmniDocBench GitHub
1
result
0 of 3 rows marked verified.