# Multiple-choice Video Question Answering on MLVU (test)

Source: [Multiple-choice Video Question Answering on MLVU (test)](<https://www.sota2.com/research/sota/multiple-choice-video-question-answering-on-mlvu-test>)

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

Data updated: 2026-02-26T05:30:14.995Z

Evaluation of model performance on the test split of the MLVU dataset for Multiple-choice Video Question Answering, measured using Accuracy.

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 | Multiple-choice Video Question Answering |
| Dataset (including any stated split) | MLVU (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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/multiple-choice-video-question-answering-on-mlvu-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LLaVA-Video + Video-RAG | 73.8 | Not recorded | 68fa764b1e209131cea6c370 |
| LLaVA-Video | 73.1 | Not recorded | 68fa764b1e209131cea6c370 |
| LLaVA-Video + Video-RAG | 72.4 | Not recorded | 68fa764b1e209131cea6c370 |
| Oryx-1.5 | 72.3 | Not recorded | 68fa764b1e209131cea6c370 |
| LLaVA-Video | 70.8 | Not recorded | 68fa764b1e209131cea6c370 |
| Aria | 70.6 | Not recorded | 68fa764b1e209131cea6c370 |
| Video-XL | 64.9 | Not recorded | 68fa764b1e209131cea6c370 |
| GPT-4o | 64.6 | Not recorded | 68fa764b1e209131cea6c370 |
| Video-CCAM | 63.1 | Not recorded | 68fa764b1e209131cea6c370 |
| VITA-1.5 | 60.4 | Not recorded | 68fa764b1e209131cea6c370 |

### LLaVA-Video + Video-RAG

Accuracy: 73.8. Result ID: 699437243a6c3148491bd0fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Implementation](<https://github.com/Leon1207/Video-RAG-master>)

Recorded evaluation configuration: {"#Params":"72B","Frames":64}. This record does not assert independent reproduction.

### LLaVA-Video

Accuracy: 73.1. Result ID: 699437243a6c3148491bd0fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

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

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

Recorded evaluation configuration: {"#Params":"72B","Frames":64,"is\_replicated":true}. This record does not assert independent reproduction.

### LLaVA-Video + Video-RAG

Accuracy: 72.4. Result ID: 699437243a6c3148491bd0fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Implementation](<https://github.com/Leon1207/Video-RAG-master>)

Recorded evaluation configuration: {"#Params":"7B","Frames":64}. This record does not assert independent reproduction.

### Oryx-1.5

Accuracy: 72.3. Result ID: 699437243a6c3148491bd0fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa772c1e209131cea71918.md>)

[Implementation](<https://github.com/Oryx-mllm/Oryx>)

Recorded evaluation configuration: {"#Params":"32B","Frames":128}. This record does not assert independent reproduction.

### LLaVA-Video

Accuracy: 70.8. Result ID: 699437243a6c3148491bd0fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

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

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

Recorded evaluation configuration: {"#Params":"7B","Frames":64,"is\_replicated":true}. This record does not assert independent reproduction.

### Aria

Accuracy: 70.6. Result ID: 699437243a6c3148491bd0f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76921e209131cea6dd17.md>)

[Implementation](<https://github.com/rhymes-ai/Aria>)

Recorded evaluation configuration: {"#Params":"25.3B","Frames":256}. This record does not assert independent reproduction.

### Video-XL

Accuracy: 64.9. Result ID: 699437243a6c3148491bd0f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762a1e209131cea6b9cb.md>)

Recorded evaluation configuration: {"#Params":"7B","Frames":256}. This record does not assert independent reproduction.

### GPT-4o

Accuracy: 64.6. Result ID: 699437243a6c3148491bd0f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

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

Recorded evaluation configuration: {"Frames":"0.5 fps"}. This record does not assert independent reproduction.

### Video-CCAM

Accuracy: 63.1. Result ID: 699437243a6c3148491bd0f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a21e209131cea62cc7.md>)

Recorded evaluation configuration: {"#Params":"14B","Frames":96}. This record does not assert independent reproduction.

### VITA-1.5

Accuracy: 60.4. Result ID: 699437243a6c3148491bd0f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764b1e209131cea6c370.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ae1e209131cea6e684.md>)

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

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