# Direct-Answer on A-OKVQA 1.0 (val)

Source: [Direct-Answer on A-OKVQA 1.0 (val)](<https://www.sota2.com/research/sota/direct-answer-on-a-okvqa-1-0-val>)

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

Data updated: 2026-02-26T05:30:30.115Z

Evaluation of model performance on the validation split of A-OKVQA version 1.0, specifically focusing on the Direct-Answer Visual Question Answering task, measured using 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 | Direct-Answer |
| Dataset (including any stated split) | A-OKVQA 1.0 (val) |
| Metric | Accuracy |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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/direct-answer-on-a-okvqa-1-0-val.md?metric=Accuracy>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Prophet++ | 0.683 | Not recorded | 68fa78401e209131cea776dd |
| Prophet | 0.647 | Not recorded | 68fa78401e209131cea776dd |
| mPLUG | 0.591 | Not recorded | 68fa78401e209131cea776dd |
| Prophet | 0.582 | Not recorded | 68fa78401e209131cea776dd |
| PromptCap | 0.563 | Not recorded | 68fa78401e209131cea776dd |
| MCAN | 0.52 | Not recorded | 68fa78401e209131cea776dd |
| GPV-2 | 0.486 | Not recorded | 68fa78401e209131cea776dd |
| KRISP | 0.337 | Not recorded | 68fa78401e209131cea776dd |
| ClipCap | 0.309 | Not recorded | 68fa78401e209131cea776dd |
| LXMERT | 0.307 | Not recorded | 68fa78401e209131cea776dd |
| ViLBERT | 0.306 | Not recorded | 68fa78401e209131cea776dd |

### Prophet++

Accuracy: 0.683. Result ID: 699581ed3badfaffe67a1a0c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Implementation](<https://github.com/MILVLG/prophet>)

Recorded evaluation configuration: {"Backbone":"mPLUG"}. This record does not assert independent reproduction.

### Prophet

Accuracy: 0.647. Result ID: 699581ed3badfaffe67a1a0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Implementation](<https://github.com/MILVLG/prophet>)

Recorded evaluation configuration: {"Backbone":"mPLUG"}. This record does not assert independent reproduction.

### mPLUG

Accuracy: 0.591. Result ID: 699581ed3badfaffe67a1a08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ffa1e209131cea484a8.md>)

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

### Prophet

Accuracy: 0.582. Result ID: 699581ed3badfaffe67a1a0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Implementation](<https://github.com/MILVLG/prophet>)

Recorded evaluation configuration: {"Backbone":"MCAN"}. This record does not assert independent reproduction.

### PromptCap

Accuracy: 0.563. Result ID: 699581ed3badfaffe67a1a09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

Recorded evaluation configuration: {"Backbone":"OFA"}. This record does not assert independent reproduction.

### MCAN

Accuracy: 0.52. Result ID: 699581ed3badfaffe67a1a07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

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

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

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

### GPV-2

Accuracy: 0.486. Result ID: 699581ed3badfaffe67a1a06.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cba1e209131cea359d9.md>)

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

### KRISP

Accuracy: 0.337. Result ID: 699581ed3badfaffe67a1a05.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cba1e209131cea359d9.md>)

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

### ClipCap

Accuracy: 0.309. Result ID: 699581ed3badfaffe67a1a02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cba1e209131cea359d9.md>)

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

### LXMERT

Accuracy: 0.307. Result ID: 699581ed3badfaffe67a1a04.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cba1e209131cea359d9.md>)

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

### ViLBERT

Accuracy: 0.306. Result ID: 699581ed3badfaffe67a1a03.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78401e209131cea776dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cba1e209131cea359d9.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.
