# Visual Question Answering on xGQA yes/no (test)

Source: [Visual Question Answering on xGQA yes/no (test)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test>)

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

Data updated: 2026-02-26T05:34:31.984Z

Evaluation of multilingual Visual Question Answering performance on the yes/no subset of the xGQA test split, measured by exact-match accuracy across multiple languages.

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 | Visual Question Answering |
| Dataset (including any stated split) | xGQA yes/no (test) |
| Metric | Accuracy (en) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Accuracy (en)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Accuracy%20(en)>): Higher is better; unit: PERCENT.

- [Accuracy (bn)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Accuracy%20(bn)>): Higher is better; unit: PERCENT.

- [Accuracy (de)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Accuracy%20(de)>): Higher is better; unit: PERCENT.

- [Accuracy (id)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Accuracy%20(id)>): Higher is better; unit: PERCENT.

- [Accuracy (ko)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Accuracy%20(ko)>): Higher is better; unit: PERCENT.

- [Accuracy (pt)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Accuracy%20(pt)>): Higher is better; unit: PERCENT.

- [Accuracy (ru)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Accuracy%20(ru)>): Higher is better; unit: PERCENT.

- [Accuracy (zh)](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Accuracy%20(zh)>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/visual-question-answering-on-xgqa-yes-no-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (en) | Result date | Report paper |
| --- | --- | --- | --- |
| TAG | 53.22 | Not recorded | 68fa736e1e209131cea5c744 |
| MERGE | 53.15 | Not recorded | 68fa736e1e209131cea5c744 |
| Human | 53.03 | Not recorded | 68fa736e1e209131cea5c744 |
| MT | 51.41 | Not recorded | 68fa736e1e209131cea5c744 |

### TAG

Accuracy (en): 53.22. Result ID: 6992ea673a6c314849125712.

[Reporting paper](<https://www.sota2.com/research/paper/68fa736e1e209131cea5c744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736e1e209131cea5c744.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-Adapter-V2","Data Origin":"TAG","Evaluation Protocol":"Translate-Test"}. This record does not assert independent reproduction.

### MERGE

Accuracy (en): 53.15. Result ID: 6992ea673a6c314849125711.

[Reporting paper](<https://www.sota2.com/research/paper/68fa736e1e209131cea5c744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736e1e209131cea5c744.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-Adapter-V2","Data Origin":"MERGE","Evaluation Protocol":"Translate-Test"}. This record does not assert independent reproduction.

### Human

Accuracy (en): 53.03. Result ID: 6992ea673a6c31484912570f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa736e1e209131cea5c744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c131e209131cea31f15.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-Adapter-V2","Data Origin":"Human","Evaluation Protocol":"Translate-Test"}. This record does not assert independent reproduction.

### MT

Accuracy (en): 51.41. Result ID: 6992ea673a6c314849125710.

[Reporting paper](<https://www.sota2.com/research/paper/68fa736e1e209131cea5c744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d511e209131cea39201.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-Adapter-V2","Data Origin":"MT","Evaluation Protocol":"Translate-Test"}. This record does not assert independent reproduction.

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