# Text-oriented Visual Question Answering on InfoVQA

Source: [Text-oriented Visual Question Answering on InfoVQA](<https://www.sota2.com/research/sota/text-oriented-visual-question-answering-on-infovqa>)

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

Data updated: 2026-02-26T05:22:33.820Z

Evaluation of model performance on the InfoVQA dataset for Text-oriented Visual Question Answering.

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 | Text-oriented Visual Question Answering |
| Dataset (including any stated split) | InfoVQA |
| Metric | ANLS |
| 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

- [ANLS](<https://www.sota2.com/research/sota/text-oriented-visual-question-answering-on-infovqa.md?metric=ANLS>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ANLS | Result date | Report paper |
| --- | --- | --- | --- |
| HRVDA | 43.5 | Not recorded | 68fa72dc1e209131cea58fc6 |
| UReader | 42.2 | Not recorded | 68fa72dc1e209131cea58fc6 |
| Pix2Struct | 40 | Not recorded | 68fa72dc1e209131cea58fc6 |
| mPLUG-Doc | 38.2 | Not recorded | 68fa72dc1e209131cea58fc6 |
| Qwen-VL | 29.9 | Not recorded | 68fa72dc1e209131cea58fc6 |
| SeRum | 13.5 | Not recorded | 68fa72dc1e209131cea58fc6 |
| Donut | 11.6 | Not recorded | 68fa72dc1e209131cea58fc6 |

### HRVDA

ANLS: 43.5. Result ID: 699283ce3a6c3148490f786c.

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

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

Recorded evaluation configuration: {"Resolution":1536}. This record does not assert independent reproduction.

### UReader

ANLS: 42.2. Result ID: 699283ce3a6c3148490f786b.

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

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

Recorded evaluation configuration: {"Resolution":224}. This record does not assert independent reproduction.

### Pix2Struct

ANLS: 40. Result ID: 699283ce3a6c3148490f7868.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc91e209131cea4765e.md>)

[Implementation](<https://github.com/google-research/pix2struct>)

Recorded evaluation configuration: {"Resolution":1024}. This record does not assert independent reproduction.

### mPLUG-Doc

ANLS: 38.2. Result ID: 699283ce3a6c3148490f786a.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa70031e209131cea488f9.md>)

Recorded evaluation configuration: {"Resolution":224}. This record does not assert independent reproduction.

### Qwen-VL

ANLS: 29.9. Result ID: 699283ce3a6c3148490f7869.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d41e209131cea4d774.md>)

[Implementation](<https://github.com/QwenLM/Qwen-VL>)

Recorded evaluation configuration: {"Resolution":448,"Open-source evaluation":true}. This record does not assert independent reproduction.

### SeRum

ANLS: 13.5. Result ID: 699283ce3a6c3148490f7867.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa70801e209131cea4b862.md>)

Recorded evaluation configuration: {"Resolution":1280,"Fine-tuning":true}. This record does not assert independent reproduction.

### Donut

ANLS: 11.6. Result ID: 699283ce3a6c3148490f7866.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d8c1e209131cea3a81c.md>)

[Implementation](<https://github.com/clovaai/donut>)

Recorded evaluation configuration: {"Resolution":1280,"Fine-tuning":true}. This record does not assert independent reproduction.

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