# Open-Ended Visual Question Answering on VizWiz (val)

Source: [Open-Ended Visual Question Answering on VizWiz (val)](<https://www.sota2.com/research/sota/open-ended-visual-question-answering-on-vizwiz-val>)

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

Data updated: 2026-02-26T05:31:09.042Z

Evaluation of Open-Ended Visual Question Answering performance on the validation split of the VizWiz dataset, measured by 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 | Open-Ended Visual Question Answering |
| Dataset (including any stated split) | VizWiz (val) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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/open-ended-visual-question-answering-on-vizwiz-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Llama-2 Chat 7B | 56.39 | Not recorded | 69535c5953fdd5c36173d630 |
| Llama-2 7B | 55.98 | Not recorded | 69535c5953fdd5c36173d630 |
| Mistral v0.1 7B | 55.32 | Not recorded | 69535c5953fdd5c36173d630 |
| Mistral Instruct v0.1 7B | 54.35 | Not recorded | 69535c5953fdd5c36173d630 |
| LLaVa v1.5 7B (Base) | 54.25 | Not recorded | 69535c5953fdd5c36173d630 |
| Moxin-7B | 54.08 | Not recorded | 69535c5953fdd5c36173d630 |

### Llama-2 Chat 7B

Accuracy: 56.39. Result ID: 6996b62f5698665ec400b4e9.

[Reporting paper](<https://www.sota2.com/research/paper/69535c5953fdd5c36173d630.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"LLM backbone":"Llama-2","Model Size":"7B","Variant":"Chat"}. This record does not assert independent reproduction.

### Llama-2 7B

Accuracy: 55.98. Result ID: 6996b62f5698665ec400b4ec.

[Reporting paper](<https://www.sota2.com/research/paper/69535c5953fdd5c36173d630.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"LLM backbone":"Llama-2","Model Size":"7B"}. This record does not assert independent reproduction.

### Mistral v0.1 7B

Accuracy: 55.32. Result ID: 6996b62f5698665ec400b4ea.

[Reporting paper](<https://www.sota2.com/research/paper/69535c5953fdd5c36173d630.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"LLM backbone":"Mistral","Model Size":"7B","Variant":"v0.1"}. This record does not assert independent reproduction.

### Mistral Instruct v0.1 7B

Accuracy: 54.35. Result ID: 6996b62f5698665ec400b4eb.

[Reporting paper](<https://www.sota2.com/research/paper/69535c5953fdd5c36173d630.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"LLM backbone":"Mistral","Model Size":"7B","Variant":"Instruct v0.1"}. This record does not assert independent reproduction.

### LLaVa v1.5 7B (Base)

Accuracy: 54.25. Result ID: 6996b62f5698665ec400b4e8.

[Reporting paper](<https://www.sota2.com/research/paper/69535c5953fdd5c36173d630.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732e1e209131cea5af59.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"LLM backbone":"LLaVa v1.5","Model Size":"7B","Variant":"Base"}. This record does not assert independent reproduction.

### Moxin-7B

Accuracy: 54.08. Result ID: 6996b62f5698665ec400b4ed.

[Reporting paper](<https://www.sota2.com/research/paper/69535c5953fdd5c36173d630.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c5953fdd5c36173d630.md>)

Recorded evaluation configuration: {"LLM backbone":"Moxin-7B","Model Size":"7B"}. This record does not assert independent reproduction.

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