# Text-intensive Visual Question Answering on VQAInfo

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

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

Data updated: 2026-05-26T09:58:51.205Z

Evaluation of model performance on the VQAInfo dataset for Text-intensive Visual Question Answering, 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 | Text-intensive Visual Question Answering |
| Dataset (including any stated split) | VQAInfo |
| 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/text-intensive-visual-question-answering-on-vqainfo.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| LBR (ours) | 25.9 | Not recorded | 6a15291bdbd7150506f7df32 |
| LLaVA-NEXT-3B | 25 | Not recorded | 6a15291bdbd7150506f7df32 |
| LBR (ours) | 23.9 | Not recorded | 6a15291bdbd7150506f7df32 |
| LLaVA-1.5-13B | 23.7 | Not recorded | 6a15291bdbd7150506f7df32 |
| LBR (ours) | 21.7 | Not recorded | 6a15291bdbd7150506f7df32 |
| LLaVA-1.5-7B | 21.5 | Not recorded | 6a15291bdbd7150506f7df32 |

### LBR (ours)

Score: 25.9. Result ID: 6a156d89fbc373592c0d51eb.

[Reporting paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-NEXT","Parameter Scale":"3B","LBR Mitigation":"true"}. This record does not assert independent reproduction.

### LLaVA-NEXT-3B

Score: 25. Result ID: 6a156d89fbc373592c0d51ea.

[Reporting paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-NEXT","Parameter Scale":"3B","LBR Mitigation":"false"}. This record does not assert independent reproduction.

### LBR (ours)

Score: 23.9. Result ID: 6a156d89fbc373592c0d51e9.

[Reporting paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-1.5","Parameter Scale":"13B","LBR Mitigation":"true"}. This record does not assert independent reproduction.

### LLaVA-1.5-13B

Score: 23.7. Result ID: 6a156d89fbc373592c0d51e8.

[Reporting paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

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

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

Recorded evaluation configuration: {"Backbone":"LLaVA-1.5","Parameter Scale":"13B","LBR Mitigation":"false"}. This record does not assert independent reproduction.

### LBR (ours)

Score: 21.7. Result ID: 6a156d89fbc373592c0d51e7.

[Reporting paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-1.5","Parameter Scale":"7B","LBR Mitigation":"true"}. This record does not assert independent reproduction.

### LLaVA-1.5-7B

Score: 21.5. Result ID: 6a156d89fbc373592c0d51e6.

[Reporting paper](<https://www.sota2.com/research/paper/6a15291bdbd7150506f7df32.md>)

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

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

Recorded evaluation configuration: {"Backbone":"LLaVA-1.5","Parameter Scale":"7B","LBR Mitigation":"false"}. This record does not assert independent reproduction.

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