# Video Question Answering on MVP

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

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

Data updated: 2026-02-26T05:57:14.829Z

Evaluation of model performance on the MVP dataset for video question answering capabilities.

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) | MVP |
| Metric | Paired Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

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

## Recorded results

| Method | Paired Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| V-JEPA 2 | 44.5 | Not recorded | 68fa79651e209131cea7d6a4 |
| InternVL-2.5 | 39.9 | Not recorded | 68fa79651e209131cea7d6a4 |
| PLM 8B | 39.7 | Not recorded | 68fa79651e209131cea7d6a4 |
| Qwen2.5VL | 36.7 | Not recorded | 68fa79651e209131cea7d6a4 |
| Qwen2VL | 29.2 | Not recorded | 68fa79651e209131cea7d6a4 |

### V-JEPA 2

Paired Accuracy: 44.5. Result ID: 698b4b518d67a41d0a6cddce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a4.md>)

[Implementation](<https://github.com/facebookresearch/vjepa2>)

Recorded evaluation configuration: {"Params Enc / LLM":"1B/8B","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### InternVL-2.5

Paired Accuracy: 39.9. Result ID: 698b4b518d67a41d0a6cddca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bab1e209131cea89c7f.md>)

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

Recorded evaluation configuration: {"Params Enc / LLM":"300M/7B","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### PLM 8B

Paired Accuracy: 39.7. Result ID: 698b4b518d67a41d0a6cddcd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a291e209131cea816f4.md>)

Recorded evaluation configuration: {"Params Enc / LLM":"1B/8B","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### Qwen2.5VL

Paired Accuracy: 36.7. Result ID: 698b4b518d67a41d0a6cddcc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Params Enc / LLM":"1B/7B","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### Qwen2VL

Paired Accuracy: 29.2. Result ID: 698b4b518d67a41d0a6cddcb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75151e209131cea65976.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-VL>)

Recorded evaluation configuration: {"Params Enc / LLM":"675M/7B","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

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