| document-image-classification-on-rvl-cdip | LayoutLMv2LARGE | #4 | Accuracy: 95.64% |
| document-image-classification-on-rvl-cdip | LayoutLMv2BASE | #9 | Accuracy: 95.25%Parameters: 200M |
| key-information-extraction-on-cord | LayoutLMv2LARGE | #6 | F1: 96.01 |
| key-information-extraction-on-cord | LayoutLMv2BASE | #7 | F1: 94.95 |
| key-information-extraction-on-sroie | LayoutLMv2LARGE (Excluding OCR mismatch) | #1 | F1: 97.81 |
| key-information-extraction-on-sroie | LayoutLMv2LARGE | #3 | F1: 96.61 |
| key-information-extraction-on-sroie | LayoutLMv2BASE | #4 | F1: 96.25 |
| key-value-pair-extraction-on-rfund-en | LayoutLMv2_base | #12 | key-value pair F1: 49.06 |
| relation-extraction-on-funsd | LayoutLMv2 large | #7 | F1: 70.57 |
| semantic-entity-labeling-on-funsd | LayoutLMv2LARGE | #10 | F1: 84.2 |
| semantic-entity-labeling-on-funsd | LayoutLMv2BASE | #11 | F1: 82.76 |
| visual-question-answering-on-docvqa-test | LayoutLMv2LARGE | #13 | ANLS: 0.8672 |
| visual-question-answering-on-docvqa-test | LayoutLMv2BASE | #21 | ANLS: 0.7808 |