Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Tasks · Document ParsingHome/Tasks/Computer Vision/Document Parsing

Document Parsing.

Parsing document structure and content

3
Datasets
149
Results
composite
Canonical metric
§ 02 · Canonical benchmark

The reference dataset.

OmniDocBench

981 annotated PDF pages across 9 document categories. Tests end-to-end document parsing including text, tables, and formulas.

Primary metric: composite
View full leaderboard →
§ 03 · Top 10

Leading models.

Leading models on OmniDocBench.

#Modellayout-mapYearSource
MinerU 2.597.52025paper ↗
2GLM-OCR94.62026paper ↗
3GLM-OCR94.62026paper ↗
4PaddleOCR-VL-1.594.52026paper ↗
5PaddleOCR-VL93.52025paper ↗
6Qianfan-OCR93.12026paper ↗
7Qianfan-OCR93.12026paper ↗
8FireRed-OCR-2B92.92026paper ↗
9PaddleOCR-VL92.92025paper ↗
10PaddleOCR-VL 0.9B92.62025paper ↗

What were you looking for on Document Parsing?

Didn't find the model, metric, or dataset you needed? Tell us in one line. We read every message and reply within 48 hours.

§ 04 · All datasets

Tracked datasets.

3 datasets tracked for this task.

OmniDocBench
CANONICAL
61 results · composite
Top: MinerU 2.5 97.5
olmOCR-Bench
74 results · pass-rate
Top: Chandra v0.1.0 99.9
ParseBench
14 results · accuracy
Top: LlamaParse Agentic 84.9
§ 05 · Related tasks

Other tasks in Computer Vision.

Document Image ClassificationDocument Layout AnalysisDocument UnderstandingGeneral OCR CapabilitiesHandwriting RecognitionImage Feature ExtractionImage-to-3DImage-to-Image
Reply within 48 hours · No newsletter

Didn't find what you came for?

Still looking for something on Document Parsing? A missing model, a stale score, a benchmark we should cover — drop it here and we'll handle it.

Real humans read every message. We track what people are asking for and prioritize accordingly.