📊 Showing 3 results | 📏 Metric: F1
| Rank | Model | Paper | F1 | Date | Code |
|---|---|---|---|---|---|
| 1 | LayoutLMv2LARGE | LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding | 85.20 | 2020-12-29 | 📦 huggingface/transformers 📦 PaddlePaddle/PaddleOCR 📦 microsoft/unilm |
| 2 | LayoutLMv2BASE | LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding | 83.30 | 2020-12-29 | 📦 huggingface/transformers 📦 PaddlePaddle/PaddleOCR 📦 microsoft/unilm |
| 3 | LAMBERT (75M) | LAMBERT: Layout-Aware (Language) Modeling for information extraction | 80.42 | 2020-02-19 | 📦 applicaai/lambert |