# Document Understanding, OCR & Charts on DocVQA (test)

Source: [Document Understanding, OCR & Charts on DocVQA (test)](<https://www.sota2.com/research/sota/document-understanding-ocr-and-charts-on-docvqa-test>)

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

Data updated: 2026-05-12T08:54:34.511Z

Evaluation of model performance on the test split of the DocVQA dataset for Document Understanding, OCR, and Charts tasks, measured using the Score metric.

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 | Document Understanding, OCR & Charts |
| Dataset (including any stated split) | DocVQA (test) |
| Metric | Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Score](<https://www.sota2.com/research/sota/document-understanding-ocr-and-charts-on-docvqa-test.md?metric=Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| Nemotron 3 Nano Omni | 95.6 | Not recorded | 69f1907355a3c32af89fb98b |
| Qwen3-Omni | 95.3 | Not recorded | 69f1907355a3c32af89fb98b |
| Qwen3-VL-4B | 95.3 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| Nemotron Nano V2 VL | 94.7 | Not recorded | 69f1907355a3c32af89fb98b |
| Qwen2.5-VL-3B | 93.9 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| PLM-3B | 93.8 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| Nemotron 3 Nano Omni | 93.3 | Not recorded | 69f1907355a3c32af89fb98b |
| Qwen3-VL-2B | 93.3 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| Nemotron Nano V2 VL | 93.2 | Not recorded | 69f1907355a3c32af89fb98b |
| InternVL3.5-20B-A4B | 92.9 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| ZAYA1-VL-8B-A1B | 92.5 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| InternVL3.5-4B | 92.4 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| DeepSeek-VL2-16B-A2.4B | 92.3 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| InternVL3.5-2B | 89.4 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| Molmo2-4B | 87.8 | Not recorded | 6a02b42fdbc836b87d8247b1 |
| MolmoE-8B-A1B | 77.7 | Not recorded | 6a02b42fdbc836b87d8247b1 |

### Nemotron 3 Nano Omni

Score: 95.6. Result ID: 69f1ae5847f34ce924d7aec4.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"30B-A3B","Reasoning":"on"}. This record does not assert independent reproduction.

### Qwen3-Omni

Score: 95.3. Result ID: 69f1ae5847f34ce924d7aec7.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"30B-A3B"}. This record does not assert independent reproduction.

### Qwen3-VL-4B

Score: 95.3. Result ID: 6a02eab547f34ce924e5ce9a.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Model":"Qwen3-VL-4B"}. This record does not assert independent reproduction.

### Nemotron Nano V2 VL

Score: 94.7. Result ID: 69f1ae5847f34ce924d7aec5.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690d7d0b2828b7cc6937ce26.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"12B","Reasoning":"off"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B

Score: 93.9. Result ID: 6a02eab547f34ce924e5ce97.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-VL-3B"}. This record does not assert independent reproduction.

### PLM-3B

Score: 93.8. Result ID: 6a02eab547f34ce924e5ce98.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

Recorded evaluation configuration: {"Model":"PLM-3B"}. This record does not assert independent reproduction.

### Nemotron 3 Nano Omni

Score: 93.3. Result ID: 69f1ae5847f34ce924d7aec3.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"30B-A3B","Reasoning":"off"}. This record does not assert independent reproduction.

### Qwen3-VL-2B

Score: 93.3. Result ID: 6a02eab547f34ce924e5ce96.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Model":"Qwen3-VL-2B"}. This record does not assert independent reproduction.

### Nemotron Nano V2 VL

Score: 93.2. Result ID: 69f1ae5847f34ce924d7aec6.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690d7d0b2828b7cc6937ce26.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"12B","Reasoning":"on"}. This record does not assert independent reproduction.

### InternVL3.5-20B-A4B

Score: 92.9. Result ID: 6a02eab547f34ce924e5ce94.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Model":"InternVL3.5-20B-A4B"}. This record does not assert independent reproduction.

### ZAYA1-VL-8B-A1B

Score: 92.5. Result ID: 6a02eab547f34ce924e5ce91.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

Recorded evaluation configuration: {"Model":"ZAYA1-VL-8B-A1B"}. This record does not assert independent reproduction.

### InternVL3.5-4B

Score: 92.4. Result ID: 6a02eab547f34ce924e5ce9b.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Model":"InternVL3.5-4B"}. This record does not assert independent reproduction.

### DeepSeek-VL2-16B-A2.4B

Score: 92.3. Result ID: 6a02eab547f34ce924e5ce93.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa763a1e209131cea6bfb0.md>)

Recorded evaluation configuration: {"Model":"DeepSeek-VL2-16B-A2.4B"}. This record does not assert independent reproduction.

### InternVL3.5-2B

Score: 89.4. Result ID: 6a02eab547f34ce924e5ce95.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Model":"InternVL3.5-2B"}. This record does not assert independent reproduction.

### Molmo2-4B

Score: 87.8. Result ID: 6a02eab547f34ce924e5ce99.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c61ce25ad2fa9d1eca03.md>)

Recorded evaluation configuration: {"Model":"Molmo2-4B"}. This record does not assert independent reproduction.

### MolmoE-8B-A1B

Score: 77.7. Result ID: 6a02eab547f34ce924e5ce92.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42fdbc836b87d8247b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b37c.md>)

[Implementation](<https://molmo.allenai.org/>)

Recorded evaluation configuration: {"Model":"MolmoE-8B-A1B"}. This record does not assert independent reproduction.

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