# Video Question Answering on EgoSchema 2023 (test)

Source: [Video Question Answering on EgoSchema 2023 (test)](<https://www.sota2.com/research/sota/video-question-answering-on-egoschema-2023-test>)

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

Data updated: 2026-02-26T05:31:28.046Z

Evaluation of model performance on the test split of the EgoSchema 2023 dataset for Video Question Answering.

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) | EgoSchema 2023 (test) |
| 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/video-question-answering-on-egoschema-2023-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GSMT-CLIP | 58.55 | Not recorded | 69818174a8b01e76cc8e2525 |
| GSMT-AIO | 58.28 | Not recorded | 69818174a8b01e76cc8e2525 |
| MIST-CLIP | 56.42 | Not recorded | 69818174a8b01e76cc8e2525 |
| MIST-AIO | 56.27 | Not recorded | 69818174a8b01e76cc8e2525 |
| VideoReCap | 50.23 | Not recorded | 69818174a8b01e76cc8e2525 |
| EgoVLP | 34.86 | Not recorded | 69818174a8b01e76cc8e2525 |

### GSMT-CLIP

Accuracy: 58.55. Result ID: 699767f85698665ec4bb5b42.

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

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

Recorded evaluation configuration: {"Pre-trained model":"CLIP (ViT/B-32)"}. This record does not assert independent reproduction.

### GSMT-AIO

Accuracy: 58.28. Result ID: 699767f85698665ec4bb5b41.

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

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

Recorded evaluation configuration: {"Pre-trained model":"All-in-One-Base"}. This record does not assert independent reproduction.

### MIST-CLIP

Accuracy: 56.42. Result ID: 699767f85698665ec4bb5b40.

[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: {"Pre-trained model":"CLIP (ViT/B-32)"}. This record does not assert independent reproduction.

### MIST-AIO

Accuracy: 56.27. Result ID: 699767f85698665ec4bb5b3f.

[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: {"Pre-trained model":"All-in-One-Base"}. This record does not assert independent reproduction.

### VideoReCap

Accuracy: 50.23. Result ID: 699767f85698665ec4bb5b3e.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73311e209131cea5b079.md>)

[Implementation](<https://sites.google.com/view/vidrecap>)

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

### EgoVLP

Accuracy: 34.86. Result ID: 699767f85698665ec4bb5b3d.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d9f1e209131cea3aedd.md>)

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

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.