# Visual Question Answering on FMIQA (val)

Source: [Visual Question Answering on FMIQA (val)](<https://www.sota2.com/research/sota/visual-question-answering-on-fmiqa-val>)

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

Data updated: 2026-02-26T06:07:44.484Z

Evaluation of model performance on the validation split of the FMIQA 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) | FMIQA (val) |
| Metric | Turing Test Passing Rate |
| 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

- [Turing Test Passing Rate](<https://www.sota2.com/research/sota/visual-question-answering-on-fmiqa-val.md?metric=Turing%20Test%20Passing%20Rate>): Higher is better; unit: PERCENT.

- [Avg Quality Score](<https://www.sota2.com/research/sota/visual-question-answering-on-fmiqa-val.md?metric=Avg%20Quality%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Turing Test Passing Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Human annotations | 97.5 | Not recorded | 68fa6b871e209131cea2eddf |
| Human annotations | 94.8 | Not recorded | 68fa6b871e209131cea2eddf |
| ERNIE-ViLG | 78.5 | Not recorded | 68fa6b871e209131cea2eddf |
| mQA | 64.7 | Not recorded | 68fa6b871e209131cea2eddf |

### Human annotations

Turing Test Passing Rate: 97.5. Result ID: 698e947dffc3901de09ed45b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2eddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622d1e209131ce9f7f4d.md>)

Recorded evaluation configuration: {"Source":"manual captions for our samples"}. This record does not assert independent reproduction.

### Human annotations

Turing Test Passing Rate: 94.8. Result ID: 698e947dffc3901de09ed459.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2eddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622d1e209131ce9f7f4d.md>)

Recorded evaluation configuration: {"Source":"from \[54\]"}. This record does not assert independent reproduction.

### ERNIE-ViLG

Turing Test Passing Rate: 78.5. Result ID: 698e947dffc3901de09ed45c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2eddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2eddf.md>)

Recorded evaluation configuration: {"Training Mode":"fine-tune"}. This record does not assert independent reproduction.

### mQA

Turing Test Passing Rate: 64.7. Result ID: 698e947dffc3901de09ed45a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b871e209131cea2eddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622d1e209131ce9f7f4d.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.