# Video Question Answering on EgoSchema (val)

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

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

Data updated: 2026-02-26T05:31:33.279Z

Evaluation of model performance on the validation split of the EgoSchema 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 (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/video-question-answering-on-egoschema-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HAVEN | 81.6 | Not recorded | 69705dc1e25ad2fa9d1ed4ba |
| DVD | 76.6 | Not recorded | 69705dc1e25ad2fa9d1ed4ba |
| GPT-4o | 70.4 | Not recorded | 69705dc1e25ad2fa9d1ed4ba |
| VideoTree | 67 | Not recorded | 69705dc1e25ad2fa9d1ed4ba |
| OpenAI o3 | 63.2 | Not recorded | 69705dc1e25ad2fa9d1ed4ba |
| VideoAgent | 63.2 | Not recorded | 69705dc1e25ad2fa9d1ed4ba |

### HAVEN

Accuracy: 81.6. Result ID: 6997a6525698665ec4fc67e3.

[Reporting paper](<https://www.sota2.com/research/paper/69705dc1e25ad2fa9d1ed4ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705dc1e25ad2fa9d1ed4ba.md>)

Recorded evaluation configuration: {"fps":"0.67"}. This record does not assert independent reproduction.

### DVD

Accuracy: 76.6. Result ID: 6997a6525698665ec4fc67e2.

[Reporting paper](<https://www.sota2.com/research/paper/69705dc1e25ad2fa9d1ed4ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a251e209131cea814c2.md>)

Recorded evaluation configuration: {"fps":"0.67"}. This record does not assert independent reproduction.

### GPT-4o

Accuracy: 70.4. Result ID: 6997a6525698665ec4fc67de.

[Reporting paper](<https://www.sota2.com/research/paper/69705dc1e25ad2fa9d1ed4ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"fps":"0.67"}. This record does not assert independent reproduction.

### VideoTree

Accuracy: 67. Result ID: 6997a6525698665ec4fc67e0.

[Reporting paper](<https://www.sota2.com/research/paper/69705dc1e25ad2fa9d1ed4ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73736.md>)

[Implementation](<https://videotree2024.github.io/>)

Recorded evaluation configuration: {"fps":"0.67"}. This record does not assert independent reproduction.

### OpenAI o3

Accuracy: 63.2. Result ID: 6997a6525698665ec4fc67df.

[Reporting paper](<https://www.sota2.com/research/paper/69705dc1e25ad2fa9d1ed4ba.md>)

Recorded evaluation configuration: {"fps":"0.67"}. This record does not assert independent reproduction.

### VideoAgent

Accuracy: 63.2. Result ID: 6997a6525698665ec4fc67e1.

[Reporting paper](<https://www.sota2.com/research/paper/69705dc1e25ad2fa9d1ed4ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72971e209131cea5761e.md>)

[Implementation](<https://wxh1996.github.io/VideoAgent-Website/>)

Recorded evaluation configuration: {"fps":"0.67"}. This record does not assert independent reproduction.

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