PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
Open paper
Benchmark
Model
Rank
Results
optical-character-recognition-ocr-on-omnidocbench-v1-5
PaddleOCR-VL-1.5
#2
Accuracy: 94.5
Rank counts only results with a code link.