Codesota · Benchmark · DocLayNetHome/Leaderboards/DocLayNet
Unknown

DocLayNet.

IBM Research's large-scale document layout analysis dataset with 80,863 annotated pages across 6 document categories: financial reports, scientific papers, patents, government tenders, manuals, and laws & regulations. 11 semantic region labels. The standard benchmark for general-domain document layout segmentation.

Paper ↗Leaderboard ↓
§ 01 · SOTA history

Year over year.

Not enough data to show trend.
§ 02 · Leaderboard

Results by metric.

mAP

MAP is the reported evaluation metric for DocLayNet. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for mAPverifiedpapervendorcommunityunverified
RankModelTrustScoreYearSource
01DocFormerv2-Large
DocFormerv2-Large on DocLayNet. 84.1 mAP (COCO-style). Table 2 in DocFormerv2 paper (arXiv 2306.01733, 2023). Adobe Research.
paper84.12026Source ↗
02DocFormerv2-Large
DocFormerv2-Large on DocLayNet. 84.1 mAP (COCO-style). Table 2 in DocFormerv2 paper (arXiv 2306.01733, 2023). Adobe Research.
paper84.12026Source ↗
03DiT-L (Cascade R-CNN)
DiT-L with Cascade R-CNN on DocLayNet. 82.6 mAP (COCO-style). Table 4 of DocLayNet paper (arXiv 2206.01062). Best result in the original IBM benchmark paper at publication.
paper82.62026Source ↗
04DiT-L (Cascade R-CNN)
DiT-L with Cascade R-CNN on DocLayNet. 82.6 mAP (COCO-style). Table 4 of DocLayNet paper (arXiv 2206.01062). Best result in the original IBM benchmark paper at publication.
paper82.62026Source ↗
05DiT-Large
DiT-Large fine-tuned on DocLayNet. Object detection formulation.
paper79.52026Source ↗
06LayoutLMv3-Large
LayoutLMv3-Large on DocLayNet object detection. 79.5 mAP. Table 3 in LayoutLMv3 paper (arXiv 2204.08387, ACM MM 2022). Microsoft Research.
paper79.52026Source ↗
07LayoutLMv3-Large
LayoutLMv3-Large on DocLayNet object detection. 79.5 mAP. Table 3 in LayoutLMv3 paper (arXiv 2204.08387, ACM MM 2022). Microsoft Research.
paper79.52026Source ↗
08LayoutLMv3
LayoutLMv3 on DocLayNet. Multimodal (text+layout+image).
paper76.82026Source ↗
09DINO (ResNet-50)
DINO detector with ResNet-50 backbone on DocLayNet. 73.4 mAP. Reported in DocLayNet follow-up comparisons as strong detection baseline. arXiv 2203.03605.
paper73.42026Source ↗
10DINO (ResNet-50)
DINO detector with ResNet-50 backbone on DocLayNet. 73.4 mAP. Reported in DocLayNet follow-up comparisons as strong detection baseline. arXiv 2203.03605.
paper73.42026Source ↗
11YOLOv8-DocLayNet
YOLOv8-L fine-tuned on DocLayNet. Fast inference.
vendor73.22026Source ↗
§ 04 · Submit a result

Add to the leaderboard.

← Back to Leaderboards
DocLayNet Leaderboard | CodeSOTA | CodeSOTA