# Visual Question Answering on GuessWhat?! (test)

Source: [Visual Question Answering on GuessWhat?! (test)](<https://www.sota2.com/research/sota/visual-question-answering-on-guesswhat-test>)

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

Data updated: 2026-02-26T05:27:37.942Z

Evaluation of model performance on the test split of the GuessWhat?! dataset for visual question answering capabilities.

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) | GuessWhat?! (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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-guesswhat-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Our SAT-\>ST | 65.69 | Not recorded | 68fa676c1e209131cea1603c |
| Our SAT | 65.04 | Not recorded | 68fa676c1e209131cea1603c |
| SOTA \[13\] | 61.3 | Not recorded | 68fa676c1e209131cea1603c |

### Our SAT-\>ST

Accuracy: 65.69. Result ID: 698d332b8b517eb4331fbc66.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Implementation](<https://github.com/facebookresearch/vilbert-multi-task>)

Recorded evaluation configuration: {"Backbone":"BERTB","Training Strategy":"All-Task Pretraining + Single-Task Finetuning","Number of Parameters":"3B","Number of Models":"12 x 250M"}. This record does not assert independent reproduction.

### Our SAT

Accuracy: 65.04. Result ID: 698d332b8b517eb4331fbc65.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Implementation](<https://github.com/facebookresearch/vilbert-multi-task>)

Recorded evaluation configuration: {"Backbone":"BERTB","Training Strategy":"All-Task (AT)","Number of Parameters":"270M","Number of Models":"1 x 270M"}. This record does not assert independent reproduction.

### SOTA \[13\]

Accuracy: 61.3. Result ID: 698d332b8b517eb4331fbc64.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63191e209131ce9fcbd9.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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