Model card
PaddleOCR-VL 0.9B.
Baiduopen-source0.9B paramsVision-Language ModelApache 2.0
Lightweight version
§ 01 · Benchmarks
Every benchmark PaddleOCR-VL 0.9B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | OmniDocBench | Computer Vision · Document Parsing | composite | 92.6% | #5 | — | 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.
§ 02 · Strengths by area
Where PaddleOCR-VL 0.9B actually performs.
§ 04 · Related models
Other Baidu models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
AlphaXiv
1
result
0 of 1 rows marked verified.