PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Open paper
Benchmark
Model
Rank
Results
optical-character-recognition-ocr-on-omnidocbench-v1-6
PaddleOCR-VL-1.6
#2
Accuracy: 96.33
Rank counts only results with a code link.