# Video Question Answering on Env-QA

Source: [Video Question Answering on Env-QA](<https://www.sota2.com/research/sota/video-question-answering-on-env-qa>)

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

Data updated: 2026-02-26T05:35:07.415Z

Evaluation of model performance on the Env-QA dataset for Video Question Answering tasks.

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 | Video Question Answering |
| Dataset (including any stated split) | Env-QA |
| Metric | Attribute Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Attribute Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-env-qa.md?metric=Attribute%20Accuracy>): Higher is better; unit: PERCENT.

- [State Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-env-qa.md?metric=State%20Accuracy>): Higher is better; unit: PERCENT.

- [Event Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-env-qa.md?metric=Event%20Accuracy>): Higher is better; unit: PERCENT.

- [Order Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-env-qa.md?metric=Order%20Accuracy>): Higher is better; unit: PERCENT.

- [Number Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-env-qa.md?metric=Number%20Accuracy>): Higher is better; unit: PERCENT.

- [Overall Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-env-qa.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Attribute Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GSMT | 49.23 | Not recorded | 69818174a8b01e76cc8e2525 |
| GSMT | 48.76 | Not recorded | 69818174a8b01e76cc8e2525 |
| MIST | 44.05 | Not recorded | 69818174a8b01e76cc8e2525 |
| MIST | 43.63 | Not recorded | 69818174a8b01e76cc8e2525 |
| ATP | 42.87 | Not recorded | 69818174a8b01e76cc8e2525 |
| AIO | 41.78 | Not recorded | 69818174a8b01e76cc8e2525 |
| STAGE | 39.49 | Not recorded | 69818174a8b01e76cc8e2525 |

### GSMT

Attribute Accuracy: 49.23. Result ID: 699767f85698665ec4bb5b33.

[Reporting paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

Recorded evaluation configuration: {"backbone":"CLIP"}. This record does not assert independent reproduction.

### GSMT

Attribute Accuracy: 48.76. Result ID: 699767f85698665ec4bb5b32.

[Reporting paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

Recorded evaluation configuration: {"backbone":"AIO"}. This record does not assert independent reproduction.

### MIST

Attribute Accuracy: 44.05. Result ID: 699767f85698665ec4bb5b31.

[Reporting paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e431e209131cea3ed48.md>)

[Implementation](<https://github.com/showlab/mist>)

Recorded evaluation configuration: {"backbone":"CLIP"}. This record does not assert independent reproduction.

### MIST

Attribute Accuracy: 43.63. Result ID: 699767f85698665ec4bb5b30.

[Reporting paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e431e209131cea3ed48.md>)

[Implementation](<https://github.com/showlab/mist>)

Recorded evaluation configuration: {"backbone":"AIO"}. This record does not assert independent reproduction.

### ATP

Attribute Accuracy: 42.87. Result ID: 699767f85698665ec4bb5b2f.

[Reporting paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cba1e209131cea359da.md>)

[Implementation](<https://stanfordvl.github.io/atp-revisit-video-lang/>)

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

### AIO

Attribute Accuracy: 41.78. Result ID: 699767f85698665ec4bb5b2e.

[Reporting paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c001e209131cea31982.md>)

[Implementation](<https://github.com/showlab/all-in-one>)

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

### STAGE

Attribute Accuracy: 39.49. Result ID: 699767f85698665ec4bb5b2d.

[Reporting paper](<https://www.sota2.com/research/paper/69818174a8b01e76cc8e2525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa678e1e209131cea16f7a.md>)

[Implementation](<https://github.com/jayleicn/TVQAplus>)

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.