# Video Question Answering on EgoSchema 5031 videos (test)

Source: [Video Question Answering on EgoSchema 5031 videos (test)](<https://www.sota2.com/research/sota/video-question-answering-on-egoschema-5031-videos-test>)

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

Data updated: 2026-02-26T06:07:07.416Z

Evaluation of model performance on the test split of the EgoSchema 5031 videos 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 5031 videos (test) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 26 of 26 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-egoschema-5031-videos-test.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LifelongMemory | 62.4 | Not recorded | 68fa795c1e209131cea7d42d |
| Tarsier | 61.7 | Not recorded | 68fa795c1e209131cea7d42d |
| LVNet + MVU | 61.3 | Not recorded | 68fa795c1e209131cea7d42d |
| VideoTree | 61.1 | Not recorded | 68fa795c1e209131cea7d42d |
| LVNet | 61.1 | Not recorded | 68fa795c1e209131cea7d42d |
| InternVideo2 | 55.8 | Not recorded | 68fa795c1e209131cea7d42d |
| VideoAgent | 54.1 | Not recorded | 68fa795c1e209131cea7d42d |
| MoreVQA | 51.7 | Not recorded | 68fa795c1e209131cea7d42d |
| LLoVi | 50.3 | Not recorded | 68fa795c1e209131cea7d42d |
| Tarsier | 49.9 | Not recorded | 68fa795c1e209131cea7d42d |
| Vamos | 48.3 | Not recorded | 68fa795c1e209131cea7d42d |
| MC-ViT-L | 44.4 | Not recorded | 68fa795c1e209131cea7d42d |
| LangRepo | 41.2 | Not recorded | 68fa795c1e209131cea7d42d |
| SF-VLM + MVU | 37.6 | Not recorded | 68fa795c1e209131cea7d42d |
| Vamos | 36.7 | Not recorded | 68fa795c1e209131cea7d42d |
| SF-VLM | 36.4 | Not recorded | 68fa795c1e209131cea7d42d |
| LLoVi | 33.5 | Not recorded | 68fa795c1e209131cea7d42d |
| LongViViT | 33.3 | Not recorded | 68fa795c1e209131cea7d42d |
| InternVideo | 32.1 | Not recorded | 68fa795c1e209131cea7d42d |
| SeViLA+ShortViViT | 31.3 | Not recorded | 68fa795c1e209131cea7d42d |
| mPLUG-Owl | 31.1 | Not recorded | 68fa795c1e209131cea7d42d |
| ImageViT | 30.9 | Not recorded | 68fa795c1e209131cea7d42d |
| FrozenBiLM | 26.9 | Not recorded | 68fa795c1e209131cea7d42d |
| SeViLA | 22.7 | Not recorded | 68fa795c1e209131cea7d42d |
| Random Selection | 20 | Not recorded | 68fa795c1e209131cea7d42d |
| VIOLET | 19.9 | Not recorded | 68fa795c1e209131cea7d42d |

### LifelongMemory

Top-1 Accuracy: 62.4. Result ID: 6995dc713badfaffe6e31ff1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa758c1e209131cea6887b.md>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":true,"Params":"1.8T"}. This record does not assert independent reproduction.

### Tarsier

Top-1 Accuracy: 61.7. Result ID: 6995dc713badfaffe6e31feb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e41e209131cea64782.md>)

[Implementation](<https://github.com/bytedance/tarsier>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":true,"Closed Model":false,"Params":"34B"}. This record does not assert independent reproduction.

### LVNet + MVU

Top-1 Accuracy: 61.3. Result ID: 6995dc713badfaffe6e31ff8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Implementation](<https://github.com/kahnchana/mvu>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":true,"Params":"1.8T"}. This record does not assert independent reproduction.

### VideoTree

Top-1 Accuracy: 61.1. Result ID: 6995dc713badfaffe6e31ff4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

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

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

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":true,"Params":"1.8T"}. This record does not assert independent reproduction.

### LVNet

Top-1 Accuracy: 61.1. Result ID: 6995dc713badfaffe6e31ff5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77981e209131cea7438f.md>)

[Implementation](<https://github.com/jongwoopark7978/LVNet>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":true,"Params":"1.8T"}. This record does not assert independent reproduction.

### InternVideo2

Top-1 Accuracy: 55.8. Result ID: 6995dc713badfaffe6e31fe9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74871e209131cea623f3.md>)

[Implementation](<https://github.com/OpenGVLab/InternVideo2>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":true,"Closed Model":false,"Params":"7B"}. This record does not assert independent reproduction.

### VideoAgent

Top-1 Accuracy: 54.1. Result ID: 6995dc713badfaffe6e31ff3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

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

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

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":true,"Params":"1.8T"}. This record does not assert independent reproduction.

### MoreVQA

Top-1 Accuracy: 51.7. Result ID: 6995dc713badfaffe6e31ff2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Implementation](<http://juhongm999.github.io/morevqa>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":false,"Params":null}. This record does not assert independent reproduction.

### LLoVi

Top-1 Accuracy: 50.3. Result ID: 6995dc713badfaffe6e31ff0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6629c.md>)

[Implementation](<https://github.com/CeeZh/LLoVi>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":true,"Params":"1.8T"}. This record does not assert independent reproduction.

### Tarsier

Top-1 Accuracy: 49.9. Result ID: 6995dc713badfaffe6e31fea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e41e209131cea64782.md>)

[Implementation](<https://github.com/bytedance/tarsier>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":true,"Closed Model":false,"Params":"7B"}. This record does not assert independent reproduction.

### Vamos

Top-1 Accuracy: 48.3. Result ID: 6995dc713badfaffe6e31fef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa741f1e209131cea5fc7b.md>)

[Implementation](<https://brown-palm.github.io/Vamos/>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":true,"Params":"1.8T"}. This record does not assert independent reproduction.

### MC-ViT-L

Top-1 Accuracy: 44.4. Result ID: 6995dc713badfaffe6e31fe8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73611e209131cea5c115.md>)

Recorded evaluation configuration: {"Zero Shot":false,"Video Training":true,"Closed Model":false,"Params":"424M"}. This record does not assert independent reproduction.

### LangRepo

Top-1 Accuracy: 41.2. Result ID: 6995dc713badfaffe6e31fee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c30b.md>)

[Implementation](<https://www.sota2.com/github.com/kkahatapitiya/LangRepo>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":false,"Params":"12B"}. This record does not assert independent reproduction.

### SF-VLM + MVU

Top-1 Accuracy: 37.6. Result ID: 6995dc713badfaffe6e31ff7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Implementation](<https://github.com/kahnchana/mvu>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":false,"Params":"13B"}. This record does not assert independent reproduction.

### Vamos

Top-1 Accuracy: 36.7. Result ID: 6995dc713badfaffe6e31fec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa741f1e209131cea5fc7b.md>)

[Implementation](<https://brown-palm.github.io/Vamos/>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":false,"Params":"13B"}. This record does not assert independent reproduction.

### SF-VLM

Top-1 Accuracy: 36.4. Result ID: 6995dc713badfaffe6e31ff6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Implementation](<https://github.com/kahnchana/mvu>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":false,"Params":"13B"}. This record does not assert independent reproduction.

### LLoVi

Top-1 Accuracy: 33.5. Result ID: 6995dc713badfaffe6e31fed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6629c.md>)

[Implementation](<https://github.com/CeeZh/LLoVi>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":false,"Closed Model":false,"Params":"13B"}. This record does not assert independent reproduction.

### LongViViT

Top-1 Accuracy: 33.3. Result ID: 6995dc713badfaffe6e31fe7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76721e209131cea6d0cf.md>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":true,"Closed Model":false,"Params":"1B"}. This record does not assert independent reproduction.

### InternVideo

Top-1 Accuracy: 32.1. Result ID: 6995dc713badfaffe6e31fe4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfc3.md>)

[Implementation](<https://github.com/OpenGVLab/InternVideo>)

Recorded evaluation configuration: {"Zero Shot":false,"Video Training":true,"Closed Model":false,"Params":"478M"}. This record does not assert independent reproduction.

### SeViLA+ShortViViT

Top-1 Accuracy: 31.3. Result ID: 6995dc713badfaffe6e31fe6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76721e209131cea6d0cf.md>)

Recorded evaluation configuration: {"Zero Shot":false,"Video Training":true,"Closed Model":false,"Params":"5B"}. This record does not assert independent reproduction.

### mPLUG-Owl

Top-1 Accuracy: 31.1. Result ID: 6995dc713badfaffe6e31fe3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d83.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-Owl>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":true,"Closed Model":false,"Params":"7.2B"}. This record does not assert independent reproduction.

### ImageViT

Top-1 Accuracy: 30.9. Result ID: 6995dc713badfaffe6e31fe5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76721e209131cea6d0cf.md>)

Recorded evaluation configuration: {"Zero Shot":false,"Video Training":false,"Closed Model":false,"Params":"1B"}. This record does not assert independent reproduction.

### FrozenBiLM

Top-1 Accuracy: 26.9. Result ID: 6995dc713badfaffe6e31fe1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da21e209131cea3b08c.md>)

[Implementation](<https://antoyang.github.io/frozenbilm.html>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":true,"Closed Model":false,"Params":"1.2B"}. This record does not assert independent reproduction.

### SeViLA

Top-1 Accuracy: 22.7. Result ID: 6995dc713badfaffe6e31fe2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa715a1e209131cea50c7b.md>)

[Implementation](<https://github.com/Yui010206/SeViLA>)

Recorded evaluation configuration: {"Zero Shot":true,"Video Training":true,"Closed Model":false,"Params":"4B"}. This record does not assert independent reproduction.

### Random Selection

Top-1 Accuracy: 20. Result ID: 6995dc713badfaffe6e31fdf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

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

### VIOLET

Top-1 Accuracy: 19.9. Result ID: 6995dc713badfaffe6e31fe0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d42d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f8b1e209131cea461d6.md>)

[Implementation](<https://github.com/tsujuifu/pytorch_empirical-mvm>)

Recorded evaluation configuration: {"Zero Shot":false,"Video Training":true,"Closed Model":false,"Params":"198M"}. This record does not assert independent reproduction.

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