Model card
PaddleOCR-VL-1.5.
Baidu PaddlePaddleopen-source0.9B paramsMulti-Task VLM (0.9B params)Apache 2.0
Next-gen of PaddleOCR-VL with 0.9B params. SOTA on OmniDocBench v1.5 (94.5%).
§ 01 · Benchmarks
Every benchmark PaddleOCR-VL-1.5 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | olmOCR-Bench | Computer Vision · Document Parsing | pass-rate | 79.1% | #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.
§ 02 · Strengths by area
Where PaddleOCR-VL-1.5 actually performs.
§ 05 · Sources & freshness
Where these numbers come from.
paper
1
result
0 of 1 rows marked verified.