# Full-page Document Parsing on OmniDocBench

Source: [Full-page Document Parsing on OmniDocBench](<https://www.sota2.com/research/sota/full-page-document-parsing-on-omnidocbench>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-31T08:40:30.679Z

Evaluation of Full-page Document Parsing performance on the OmniDocBench dataset, reporting key metrics including Overall score, Edit distance, CDM, and TEDS.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Full-page Document Parsing |
| Dataset (including any stated split) | OmniDocBench |
| Metric | Overall Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Overall Score](<https://www.sota2.com/research/sota/full-page-document-parsing-on-omnidocbench.md?metric=Overall%20Score>): Higher is better; unit: PERCENT.

- [Edit Distance](<https://www.sota2.com/research/sota/full-page-document-parsing-on-omnidocbench.md?metric=Edit%20Distance>): Lower is better; unit: PERCENT.

- [CDM Score](<https://www.sota2.com/research/sota/full-page-document-parsing-on-omnidocbench.md?metric=CDM%20Score>): Higher is better; unit: PERCENT.

- [TEDS Score](<https://www.sota2.com/research/sota/full-page-document-parsing-on-omnidocbench.md?metric=TEDS%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall Score | Result date | Report paper |
| --- | --- | --- | --- |
| PaddleOCR VL 1.5 | 94.37 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| PaddleOCR VL | 91.76 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| Chandra | 88.97 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| FalconOCR | 88.64 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| DeepSeek OCR v2 | 87.66 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| GPT 5.2 | 86.56 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| Mistral OCR 3 | 85.2 | Not recorded | 69cb54fe0636e5bf4afc9e7c |

### PaddleOCR VL 1.5

Overall Score: 94.37. Result ID: 69cb886b47f34ce924b3dcc7.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3b70a8b01e76cc8da769.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PaddleOCR VL

Overall Score: 91.76. Result ID: 69cb886b47f34ce924b3dcc8.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c451e209131cea8d4d4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Chandra

Overall Score: 88.97. Result ID: 69cb886b47f34ce924b3dcc9.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FalconOCR

Overall Score: 88.64. Result ID: 69cb886b47f34ce924b3dccd.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

Recorded evaluation configuration: {"Parameters":"300M"}. This record does not assert independent reproduction.

### DeepSeek OCR v2

Overall Score: 87.66. Result ID: 69cb886b47f34ce924b3dcca.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697ae9b8a2b28e761d87d127.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-OCR-2>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT 5.2

Overall Score: 86.56. Result ID: 69cb886b47f34ce924b3dccb.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Mistral OCR 3

Overall Score: 85.2. Result ID: 69cb886b47f34ce924b3dccc.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.