# Long Video Question Answering on EgoSchema (full set)

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

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

Data updated: 2026-02-26T05:30:15.656Z

Evaluation of model performance using Long Video Question Answering metrics (including Accuracy and Throughput) on the full set of the EgoSchema dataset.

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 | Long Video Question Answering |
| Dataset (including any stated split) | EgoSchema (full set) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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/long-video-question-answering-on-egoschema-full-set.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Throughput](<https://www.sota2.com/research/sota/long-video-question-answering-on-egoschema-full-set.md?metric=Throughput>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Dispider | 55.6 | Not recorded | 68fa767f1e209131cea6d744 |
| VideoChat2 | 54.4 | Not recorded | 68fa767f1e209131cea6d744 |
| MovieChat | 53.5 | Not recorded | 68fa767f1e209131cea6d744 |
| LLoVi | 52.2 | Not recorded | 68fa75261e209131cea6629c |
| Video-LLaMA2 | 51.7 | Not recorded | 68fa767f1e209131cea6d744 |
| Vamos | 48.3 | Not recorded | 68fa75261e209131cea6629c |
| VLog | 44 | Not recorded | 68fa75261e209131cea6629c |
| LLaVA-Next-Video | 43.9 | Not recorded | 68fa767f1e209131cea6d744 |
| LLoVi | 42.8 | Not recorded | 68fa75261e209131cea6629c |
| Video ChatCaptioner | 39 | Not recorded | 68fa75261e209131cea6629c |
| LLaMA-VID | 38.5 | Not recorded | 68fa767f1e209131cea6d744 |
| Video-LLaVA | 38.4 | Not recorded | 68fa767f1e209131cea6d744 |
| LongViViT | 33.3 | Not recorded | 68fa75261e209131cea6629c |
| TimeChat | 33 | Not recorded | 68fa767f1e209131cea6d744 |
| InternVideo | 32.1 | Not recorded | 68fa75261e209131cea6629c |
| mPLUG-Owl | 31.1 | Not recorded | 68fa75261e209131cea6629c |
| FrozenBiLM | 26.9 | Not recorded | 68fa75261e209131cea6629c |

### Dispider

Accuracy: 55.6. Result ID: 69943ee23a6c3148491c07e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Implementation](<https://github.com/Mark12Ding/Dispider>)

Recorded evaluation configuration: {"LLM Size":"7B","Frames":"1 FPS"}. This record does not assert independent reproduction.

### VideoChat2

Accuracy: 54.4. Result ID: 69943ee23a6c3148491c07e4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73411e209131cea5b4b7.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Frames":"16"}. This record does not assert independent reproduction.

### MovieChat

Accuracy: 53.5. Result ID: 69943ee23a6c3148491c07e1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56563.md>)

[Implementation](<https://rese1f.github.io/MovieChat>)

Recorded evaluation configuration: {"LLM Size":"7B","Frames":"2048"}. This record does not assert independent reproduction.

### LLoVi

Accuracy: 52.2. Result ID: 6993908b3a6c31484916e5ba.

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

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

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

Recorded evaluation configuration: {"LM":"GPT-3.5","Params":"175B","Prompting Strategy":"Summarization Prompt"}. This record does not assert independent reproduction.

### Video-LLaMA2

Accuracy: 51.7. Result ID: 69943ee23a6c3148491c07e2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75761e209131cea681dd.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/VideoLLaMA2>)

Recorded evaluation configuration: {"LLM Size":"7B","Frames":"16"}. This record does not assert independent reproduction.

### Vamos

Accuracy: 48.3. Result ID: 6993908b3a6c31484916e5b8.

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

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

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

Recorded evaluation configuration: {"LM":"GPT-4","Params":"1.5T"}. This record does not assert independent reproduction.

### VLog

Accuracy: 44. Result ID: 6993908b3a6c31484916e5b7.

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

Recorded evaluation configuration: {"LM":"GPT-3.5","Params":"175B"}. This record does not assert independent reproduction.

### LLaVA-Next-Video

Accuracy: 43.9. Result ID: 69943ee23a6c3148491c07e3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Frames":"32"}. This record does not assert independent reproduction.

### LLoVi

Accuracy: 42.8. Result ID: 6993908b3a6c31484916e5b9.

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

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

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

Recorded evaluation configuration: {"LM":"GPT-3.5","Params":"175B","Prompting Strategy":"Standard Prompt"}. This record does not assert independent reproduction.

### Video ChatCaptioner

Accuracy: 39. Result ID: 6993908b3a6c31484916e5b6.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6b1e209131cea45754.md>)

Recorded evaluation configuration: {"LM":"GPT-3.5","Params":"175B"}. This record does not assert independent reproduction.

### LLaMA-VID

Accuracy: 38.5. Result ID: 69943ee23a6c3148491c07df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea50559.md>)

[Implementation](<https://github.com/dvlab-research/LLaMA-VID>)

Recorded evaluation configuration: {"LLM Size":"7B","Frames":"1 FPS"}. This record does not assert independent reproduction.

### Video-LLaVA

Accuracy: 38.4. Result ID: 69943ee23a6c3148491c07de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65534.md>)

[Implementation](<https://github.com/PKU-YuanGroup/Video-LLaVA>)

Recorded evaluation configuration: {"LLM Size":"7B","Frames":"8"}. This record does not assert independent reproduction.

### LongViViT

Accuracy: 33.3. Result ID: 6993908b3a6c31484916e5b5.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa473a1e209131ce926666.md>)

Recorded evaluation configuration: {"LM":"BERT","Params":"1B"}. This record does not assert independent reproduction.

### TimeChat

Accuracy: 33. Result ID: 69943ee23a6c3148491c07e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57c30.md>)

[Implementation](<https://github.com/RenShuhuai-Andy/TimeChat>)

Recorded evaluation configuration: {"LLM Size":"7B","Frames":"96"}. This record does not assert independent reproduction.

### InternVideo

Accuracy: 32.1. Result ID: 6993908b3a6c31484916e5b4.

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

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

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

Recorded evaluation configuration: {"LM":"Transformer","Params":"478M"}. This record does not assert independent reproduction.

### mPLUG-Owl

Accuracy: 31.1. Result ID: 6993908b3a6c31484916e5b3.

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

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

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

Recorded evaluation configuration: {"LM":"LLaMA","Params":"7B"}. This record does not assert independent reproduction.

### FrozenBiLM

Accuracy: 26.9. Result ID: 6993908b3a6c31484916e5b2.

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

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

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

Recorded evaluation configuration: {"LM":"DeBERTa","Params":"300M"}. This record does not assert independent reproduction.

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