# Document Understanding, OCR & Charts on AI2D (test)

Source: [Document Understanding, OCR & Charts on AI2D (test)](<https://www.sota2.com/research/sota/document-understanding-ocr-and-charts-on-ai2d-test>)

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

Data updated: 2026-04-29T07:11:40.002Z

Evaluation of model performance on the test split of the AI2D dataset for Document Understanding, OCR, and Chart analysis tasks, measured by Score.

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) | AI2D (test) |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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-ai2d-test.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3.5-Omni | 89 | Not recorded | 69f1907355a3c32af89fb98b |
| Nemotron 3 Nano Omni | 88.5 | Not recorded | 69f1907355a3c32af89fb98b |
| Nemotron 3 Nano Omni | 88.5 | Not recorded | 69f1907355a3c32af89fb98b |
| Nemotron Nano V2 VL | 87.2 | Not recorded | 69f1907355a3c32af89fb98b |
| Qwen3-Omni | 86.62 | Not recorded | 69f1907355a3c32af89fb98b |
| Nemotron Nano V2 VL | 84.7 | Not recorded | 69f1907355a3c32af89fb98b |

### Qwen3.5-Omni

Score: 89. Result ID: 69f1ae5847f34ce924d7aecd.

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

Recorded evaluation configuration: {"Open-Source":"false","Size":"Flash"}. This record does not assert independent reproduction.

### Nemotron 3 Nano Omni

Score: 88.5. Result ID: 69f1ae5847f34ce924d7aec8.

[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.

### Nemotron 3 Nano Omni

Score: 88.5. Result ID: 69f1ae5847f34ce924d7aec9.

[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.

### Nemotron Nano V2 VL

Score: 87.2. Result ID: 69f1ae5847f34ce924d7aeca.

[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.

### Qwen3-Omni

Score: 86.62. Result ID: 69f1ae5847f34ce924d7aecc.

[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.

### Nemotron Nano V2 VL

Score: 84.7. Result ID: 69f1ae5847f34ce924d7aecb.

[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.

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