# OCR-VQA Average on DOCVQA, INFOVQA, CHARTQA, and TEXTVQA

Source: [OCR-VQA Average on DOCVQA, INFOVQA, CHARTQA, and TEXTVQA](<https://www.sota2.com/research/sota/ocr-vqa-average-on-docvqa-infovqa-chartqa-and-textvqa>)

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

Data updated: 2026-05-20T08:03:49.380Z

Evaluation of OCR Visual Question Answering performance averaged across the DOCVQA, INFOVQA, CHARTQA, and TEXTVQA datasets, measured by the Final FR 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 | OCR-VQA |
| Dataset (including any stated split) | DOCVQA, INFOVQA, CHARTQA, and TEXTVQA Average |
| Metric | Final FR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Final FR](<https://www.sota2.com/research/sota/ocr-vqa-average-on-docvqa-infovqa-chartqa-and-textvqa.md?metric=Final%20FR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Final FR | Result date | Report paper |
| --- | --- | --- | --- |
| LLaVA-1.5 | 14.4 | Not recorded | 6a0d4000f984739ed6737751 |
| UReader | 14.2 | Not recorded | 6a0d4000f984739ed6737751 |
| Monkey | 12.1 | Not recorded | 6a0d4000f984739ed6737751 |
| TextHawk | 11.6 | Not recorded | 6a0d4000f984739ed6737751 |
| MM1.5 | 10.3 | Not recorded | 6a0d4000f984739ed6737751 |
| HRVDA | 9.3 | Not recorded | 6a0d4000f984739ed6737751 |
| Vary | 9.2 | Not recorded | 6a0d4000f984739ed6737751 |
| InternVL2 | 9.1 | Not recorded | 6a0d4000f984739ed6737751 |
| DocOwl-1.5 | 9.1 | Not recorded | 6a0d4000f984739ed6737751 |
| DocOwl-1.5-Chat | 9 | Not recorded | 6a0d4000f984739ed6737751 |
| Marten | 8.6 | Not recorded | 6a0d4000f984739ed6737751 |
| CogAgent | 8.2 | Not recorded | 6a0d4000f984739ed6737751 |
| TextHawk2 | 8 | Not recorded | 6a0d4000f984739ed6737751 |

### LLaVA-1.5

Final FR: 14.4. Result ID: 6a0d6971fbc373592c054269.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732e1e209131cea5af59.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

### UReader

Final FR: 14.2. Result ID: 6a0d6971fbc373592c054267.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cb1e209131cea4d29d.md>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

### Monkey

Final FR: 12.1. Result ID: 6a0d6971fbc373592c05426d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62ebc.md>)

[Implementation](<https://github.com/Yuliang-Liu/Monkey>)

Recorded evaluation configuration: {"Size":"9B"}. This record does not assert independent reproduction.

### TextHawk

Final FR: 11.6. Result ID: 6a0d6971fbc373592c05426e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f46.md>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

### MM1.5

Final FR: 10.3. Result ID: 6a0d6971fbc373592c054272.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

### HRVDA

Final FR: 9.3. Result ID: 6a0d6971fbc373592c054270.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72dc1e209131cea58fc6.md>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

### Vary

Final FR: 9.2. Result ID: 6a0d6971fbc373592c054271.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71621e209131cea5109f.md>)

[Implementation](<https://varybase.github.io/>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

### InternVL2

Final FR: 9.1. Result ID: 6a0d6971fbc373592c054268.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction.

### DocOwl-1.5

Final FR: 9.1. Result ID: 6a0d6971fbc373592c05426a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72901e209131cea571df.md>)

Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction.

### DocOwl-1.5-Chat

Final FR: 9. Result ID: 6a0d6971fbc373592c05426b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72901e209131cea571df.md>)

Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction.

### Marten

Final FR: 8.6. Result ID: 6a0d6971fbc373592c054273.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77811e209131cea73ac1.md>)

Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction.

### CogAgent

Final FR: 8.2. Result ID: 6a0d6971fbc373592c05426c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76711e209131cea6d06f.md>)

[Implementation](<https://github.com/THUDM/CogVLM>)

Recorded evaluation configuration: {"Size":"17B"}. This record does not assert independent reproduction.

### TextHawk2

Final FR: 8. Result ID: 6a0d6971fbc373592c05426f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4000f984739ed6737751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75161e209131cea65a8a.md>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

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