# Augmented Knowledge-based Visual Question Answering on A-OKVQA

Source: [Augmented Knowledge-based Visual Question Answering on A-OKVQA](<https://www.sota2.com/research/sota/augmented-knowledge-based-visual-question-answering-on-a-okvqa>)

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

Data updated: 2026-03-16T09:15:02.180Z

Evaluation of model performance on the A-OKVQA dataset for Augmented Knowledge-based Visual Question Answering tasks, typically reporting 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 | Augmented Knowledge-based Visual Question Answering |
| Dataset (including any stated split) | A-OKVQA |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/augmented-knowledge-based-visual-question-answering-on-a-okvqa.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ToolTree | 73.48 | Not recorded | 69b78e650636e5bf4afbda98 |
| ToolTree | 70.54 | Not recorded | 69b78e650636e5bf4afbda98 |
| OctoTools | 68.33 | Not recorded | 69b78e650636e5bf4afbda98 |
| Few-Shot | 65.91 | Not recorded | 69b78e650636e5bf4afbda98 |
| OctoTools | 62.15 | Not recorded | 69b78e650636e5bf4afbda98 |
| HuggingGPT | 60.33 | Not recorded | 69b78e650636e5bf4afbda98 |
| Few-Shot | 60.28 | Not recorded | 69b78e650636e5bf4afbda98 |
| HuggingGPT | 55.81 | Not recorded | 69b78e650636e5bf4afbda98 |

### ToolTree

Accuracy: 73.48. Result ID: 69b7c9fe47f34ce9249faed6.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

Recorded evaluation configuration: {"Backbone Model":"GPT-4o"}. This record does not assert independent reproduction.

### ToolTree

Accuracy: 70.54. Result ID: 69b7c9fe47f34ce9249faed2.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

Recorded evaluation configuration: {"Backbone Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### OctoTools

Accuracy: 68.33. Result ID: 69b7c9fe47f34ce9249faed5.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76fe1e209131cea704b3.md>)

Recorded evaluation configuration: {"Backbone Model":"GPT-4o"}. This record does not assert independent reproduction.

### Few-Shot

Accuracy: 65.91. Result ID: 69b7c9fe47f34ce9249faed3.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

Recorded evaluation configuration: {"Backbone Model":"GPT-4o"}. This record does not assert independent reproduction.

### OctoTools

Accuracy: 62.15. Result ID: 69b7c9fe47f34ce9249faed1.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76fe1e209131cea704b3.md>)

Recorded evaluation configuration: {"Backbone Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### HuggingGPT

Accuracy: 60.33. Result ID: 69b7c9fe47f34ce9249faed4.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea5091f.md>)

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

Recorded evaluation configuration: {"Backbone Model":"GPT-4o"}. This record does not assert independent reproduction.

### Few-Shot

Accuracy: 60.28. Result ID: 69b7c9fe47f34ce9249faecf.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

Recorded evaluation configuration: {"Backbone Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### HuggingGPT

Accuracy: 55.81. Result ID: 69b7c9fe47f34ce9249faed0.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e650636e5bf4afbda98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea5091f.md>)

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

Recorded evaluation configuration: {"Backbone Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

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