Codesota · Models · dots.ocr 3BRedNote HILab3 results · 2 benchmarks
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.

§ 02 · Benchmarks

Every benchmark dots.ocr 3B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01OmniDocBenchVision & Documents · Document Parsingcomposite88.4%#18/402026-04-20source ↗
02olmOCR-BenchVision & Documents · Document Parsingtables88.3%#2/52026-04-20source ↗
03olmOCR-BenchVision & Documents · Document Parsingpass-rate79.1%#14/332026-04-20source ↗
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.
§ 03 · Strengths by area

Where dots.ocr 3B actually performs.

Vision & Documents
2
benchmarks
avg rank #11.3
§ 06 · Sources & freshness

Where these numbers come from.

codesota-api
3
results
0 of 3 rows marked verified.