Model card
PaddleOCR-VL.
Baiduopen-source0.9B-7B paramsVision-Language ModelApache 2.01 current SOTA
#1 on OmniDocBench
§ 02 · Benchmarks
Every benchmark PaddleOCR-VL has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | OmniDocBench | Computer Vision · Document Parsing | table-teds | 93.5% | #1 | — | source ↗ |
| 02 | OmniDocBench | Computer Vision · Document Parsing | accuracy | 92.6% | #4 | — | source ↗ |
| 03 | OmniDocBench | Computer Vision · Document Parsing | composite | 92.9% | #4 | — | source ↗ |
| 04 | olmOCR-Bench | Computer Vision · Document Parsing | pass-rate | 80.0% | #6 | — | source ↗ |
| 05 | olmOCR-Bench | Computer Vision · Document Parsing | accuracy | 80.0% | #9 | — | 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.
§ 03 · Strengths by area
Where PaddleOCR-VL actually performs.
§ 04 · Papers
1 paper with results for PaddleOCR-VL.
§ 05 · Related models
Other Baidu models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
alphaxiv-leaderboard
2
results
pwc-dump
2
results
AlphaXiv
1
result
0 of 5 rows marked verified.