# Visual Question Answering on GQA (Orig.)

Source: [Visual Question Answering on GQA (Orig.)](<https://www.sota2.com/research/sota/visual-question-answering-on-gqa-orig>)

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

Data updated: 2026-02-26T05:54:23.886Z

Evaluation of model performance on the original split of the GQA dataset for visual question answering capabilities, typically measured by Overall Accuracy.

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) | GQA (Orig.) |
| Metric | Overall Accuracy |
| 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

- [Overall Accuracy](<https://www.sota2.com/research/sota/visual-question-answering-on-gqa-orig.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MCAN-Small | 58.35 | Not recorded | 68fa6cc21e209131cea35d61 |
| RelViT | 57.87 | Not recorded | 68fa6cc21e209131cea35d61 |
| EsViT | 56.95 | Not recorded | 68fa6cc21e209131cea35d61 |
| ViT-only | 56.62 | Not recorded | 68fa6cc21e209131cea35d61 |
| MAC | 54.06 | Not recorded | 68fa6cc21e209131cea35d61 |
| BottomUp | 53.21 | Not recorded | 68fa6cc21e209131cea35d61 |
| MCAN-Small | 51.1 | Not recorded | 68fa6cc21e209131cea35d61 |

### MCAN-Small

Overall Accuracy: 58.35. Result ID: 698f3c683a6c314849f755c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cc21e209131cea35d61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f11e209131cea0d447.md>)

[Implementation](<https://github.com/MILVLG/mcan-vqa>)

Recorded evaluation configuration: {"Faster R-CNN bbox features":true,"Backbone":"ResNet-101"}. This record does not assert independent reproduction.

### RelViT

Overall Accuracy: 57.87. Result ID: 698f3c683a6c314849f755c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cc21e209131cea35d61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cc21e209131cea35d61.md>)

Recorded evaluation configuration: {"Faster R-CNN bbox features":false,"Backbone":"PVTv2-b2"}. This record does not assert independent reproduction.

### EsViT

Overall Accuracy: 56.95. Result ID: 698f3c683a6c314849f755c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cc21e209131cea35d61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfa1e209131cea37111.md>)

[Implementation](<https://github.com/microsoft/esvit>)

Recorded evaluation configuration: {"Faster R-CNN bbox features":false,"Backbone":"PVTv2-b2"}. This record does not assert independent reproduction.

### ViT-only

Overall Accuracy: 56.62. Result ID: 698f3c683a6c314849f755c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cc21e209131cea35d61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43b6a.md>)

[Implementation](<https://github.com/whai362/PVT>)

Recorded evaluation configuration: {"Faster R-CNN bbox features":false,"Backbone":"PVTv2-b2"}. This record does not assert independent reproduction.

### MAC

Overall Accuracy: 54.06. Result ID: 698f3c683a6c314849f755c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cc21e209131cea35d61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64421e209131cea038c6.md>)

[Implementation](<https://github.com/stanfordnlp/mac-network>)

Recorded evaluation configuration: {"Faster R-CNN bbox features":true,"Backbone":"ResNet-101"}. This record does not assert independent reproduction.

### BottomUp

Overall Accuracy: 53.21. Result ID: 698f3c683a6c314849f755c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cc21e209131cea35d61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642b1e209131cea031b7.md>)

[Implementation](<http://www.panderson.me/up-down-attention>)

Recorded evaluation configuration: {"Faster R-CNN bbox features":true,"Backbone":"ResNet-101"}. This record does not assert independent reproduction.

### MCAN-Small

Overall Accuracy: 51.1. Result ID: 698f3c683a6c314849f755c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cc21e209131cea35d61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f11e209131cea0d447.md>)

[Implementation](<https://github.com/MILVLG/mcan-vqa>)

Recorded evaluation configuration: {"Faster R-CNN bbox features":false,"Backbone":"ResNet-101"}. This record does not assert independent reproduction.

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