# Visual Question Answering on VQA v2 (Accuracy Only)

Source: [Visual Question Answering on VQA v2 (Accuracy Only)](<https://www.sota2.com/research/sota/visual-question-answering-on-vqa-v2-accuracy-only>)

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

Data updated: 2026-02-27T08:59:25.410Z

Evaluation of model performance on the VQA v2 dataset for visual question answering, reporting only the standard Accuracy 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 | Visual Question Answering |
| Dataset (including any stated split) | VQA v2 |
| Metric | Accuracy |
| 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](<https://www.sota2.com/research/sota/visual-question-answering-on-vqa-v2-accuracy-only.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GroundingGPT | 78.7 | Not recorded | 68fa72601e209131cea56081 |
| LLaVA-1.5 | 78.5 | Not recorded | 68fa72601e209131cea56081 |
| Shikra | 77.4 | Not recorded | 68fa72601e209131cea56081 |
| BLIP-2 | 41 | Not recorded | 68fa72601e209131cea56081 |

### GroundingGPT

Accuracy: 78.7. Result ID: 69a15cec35dfcabb00e68ba5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72601e209131cea56081.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72601e209131cea56081.md>)

[Implementation](<https://github.com/lzw-lzw/GroundingGPT>)

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

### LLaVA-1.5

Accuracy: 78.5. Result ID: 69a15cec35dfcabb00e68ba4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72601e209131cea56081.md>)

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

### Shikra

Accuracy: 77.4. Result ID: 69a15cec35dfcabb00e68ba3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72601e209131cea56081.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe61e209131cea47fbc.md>)

[Implementation](<https://github.com/shikras/shikra>)

Recorded evaluation configuration: {"LLM Size":"13B"}. This record does not assert independent reproduction.

### BLIP-2

Accuracy: 41. Result ID: 69a15cec35dfcabb00e68ba2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72601e209131cea56081.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"LLM Size":"13B"}. This record does not assert independent reproduction.

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