# Long-video understanding on EgoSchema (full)

Source: [Long-video understanding on EgoSchema (full)](<https://www.sota2.com/research/sota/long-video-understanding-on-egoschema-full>)

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

Data updated: 2026-06-23T09:34:29.765Z

Evaluation of model performance on the full set of the EgoSchema dataset for Long-video understanding 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 | Long-video understanding |
| Dataset (including any stated split) | EgoSchema (full) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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-understanding-on-egoschema-full.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o | 72.2 | Not recorded | 6a3a1354206542251d7c7323 |
| Gemini 1.5 Pro | 71.1 | Not recorded | 6a3a1354206542251d7c7323 |
| HPP | 70.4 | Not recorded | 6a3a1354206542251d7c7323 |
| LLaVA-Video | 65.6 | Not recorded | 6a3a1354206542251d7c7323 |
| VideoLLaMA-2 | 63.9 | Not recorded | 6a3a1354206542251d7c7323 |
| LLaVA-OneVision | 62 | Not recorded | 6a3a1354206542251d7c7323 |
| Dr. Video | 61.9 | Not recorded | 6a3a1354206542251d7c7323 |
| VideoTree | 61.1 | Not recorded | 6a3a1354206542251d7c7323 |
| LLaVA-Video | 57.3 | Not recorded | 6a3a1354206542251d7c7323 |
| VideoChat2 | 56.7 | Not recorded | 6a3a1354206542251d7c7323 |
| VideoAgent | 54.1 | Not recorded | 6a3a1354206542251d7c7323 |

### GPT-4o

Accuracy: 72.2. Result ID: 6a3a5315fbc373592c35e496.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction.

### Gemini 1.5 Pro

Accuracy: 71.1. Result ID: 6a3a5315fbc373592c35e497.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76361e209131cea6be11.md>)

Recorded evaluation configuration: {"Model":"Gemini 1.5 Pro"}. This record does not assert independent reproduction.

### HPP

Accuracy: 70.4. Result ID: 6a3a5315fbc373592c35e4a0.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

Recorded evaluation configuration: {"Model":"Ours HPP"}. This record does not assert independent reproduction.

### LLaVA-Video

Accuracy: 65.6. Result ID: 6a3a5315fbc373592c35e49a.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea82934.md>)

[Implementation](<https://llava-vl.github.io/blog/llava-video>)

Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction.

### VideoLLaMA-2

Accuracy: 63.9. Result ID: 6a3a5315fbc373592c35e49c.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

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

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

Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction.

### LLaVA-OneVision

Accuracy: 62. Result ID: 6a3a5315fbc373592c35e49b.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction.

### Dr. Video

Accuracy: 61.9. Result ID: 6a3a5315fbc373592c35e49f.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a009.md>)

Recorded evaluation configuration: {"Model":"Dr. Video"}. This record does not assert independent reproduction.

### VideoTree

Accuracy: 61.1. Result ID: 6a3a5315fbc373592c35e49e.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

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

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

Recorded evaluation configuration: {"Model":"VideoTree"}. This record does not assert independent reproduction.

### LLaVA-Video

Accuracy: 57.3. Result ID: 6a3a5315fbc373592c35e499.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea82934.md>)

[Implementation](<https://llava-vl.github.io/blog/llava-video>)

Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction.

### VideoChat2

Accuracy: 56.7. Result ID: 6a3a5315fbc373592c35e498.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

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

Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction.

### VideoAgent

Accuracy: 54.1. Result ID: 6a3a5315fbc373592c35e49d.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1354206542251d7c7323.md>)

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

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

Recorded evaluation configuration: {"Model":"VideoAgent"}. This record does not assert independent reproduction.

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