# Video Understanding on MMEB Video v2

Source: [Video Understanding on MMEB Video v2](<https://www.sota2.com/research/sota/video-understanding-on-mmeb-video-v2>)

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

Data updated: 2026-04-03T09:06:42.324Z

Evaluation of video understanding capabilities using the MMEB Video v2 dataset, reporting scores across Classification (CLS), Question Answering (QA), Retrieval (RET), and Multimodal Retrieval (MRET) subtasks, along with an overall score.

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 Understanding |
| Dataset (including any stated split) | MMEB Video v2 |
| Metric | Classification Score (CLS) |
| 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

- [Classification Score (CLS)](<https://www.sota2.com/research/sota/video-understanding-on-mmeb-video-v2.md?metric=Classification%20Score%20(CLS)>): Higher is better; unit: PERCENT.

- [Overall Score](<https://www.sota2.com/research/sota/video-understanding-on-mmeb-video-v2.md?metric=Overall%20Score>): Higher is better; unit: PERCENT.

- [QA Score](<https://www.sota2.com/research/sota/video-understanding-on-mmeb-video-v2.md?metric=QA%20Score>): Higher is better; unit: PERCENT.

- [Retrieval Score (RET)](<https://www.sota2.com/research/sota/video-understanding-on-mmeb-video-v2.md?metric=Retrieval%20Score%20(RET)>): Higher is better; unit: PERCENT.

- [MRET Score](<https://www.sota2.com/research/sota/video-understanding-on-mmeb-video-v2.md?metric=MRET%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Classification Score (CLS) | Result date | Report paper |
| --- | --- | --- | --- |
| WAVE | 57.8 | Not recorded | 68fa7ba91e209131cea89bb0 |
| Seed-1.6-Embedding | 55 | Not recorded | 68fa7ba91e209131cea89bb0 |
| OmniRet | 48.6 | Not recorded | 69a66c572d603e6de3e3d146 |
| PLUME | 45 | Not recorded | 69cf49bb0636e5bf4afcdba9 |
| UME-R1 | 44.3 | Not recorded | 69cf49bb0636e5bf4afcdba9 |
| LamRA | 39.3 | Not recorded | 68fa7ba91e209131cea89bb0 |
| VLM2VecV2 | 39.3 | Not recorded | 69a66c572d603e6de3e3d146 |
| LamRA | 39.3 | Not recorded | 69cf49bb0636e5bf4afcdba9 |
| VLM2Vec-V2 | 39.3 | Not recorded | 69cf49bb0636e5bf4afcdba9 |
| DUME | 37.7 | Not recorded | 69cf49bb0636e5bf4afcdba9 |
| GME | 37.4 | Not recorded | 68fa7ba91e209131cea89bb0 |
| CAFe | 35.8 | Not recorded | 68fa7ba91e209131cea89bb0 |
| GME | 34.9 | Not recorded | 69a66c572d603e6de3e3d146 |
| GME | 34.9 | Not recorded | 69cf49bb0636e5bf4afcdba9 |
| VLM2VecV1 | 33.4 | Not recorded | 69a66c572d603e6de3e3d146 |
| VLM2Vec | 33.4 | Not recorded | 69cf49bb0636e5bf4afcdba9 |
| ColPaliv1.3 | 26.7 | Not recorded | 69a66c572d603e6de3e3d146 |

### WAVE

Classification Score (CLS): 57.8. Result ID: 699e444d5698665ec401f0f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba91e209131cea89bb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba91e209131cea89bb0.md>)

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

### Seed-1.6-Embedding

Classification Score (CLS): 55. Result ID: 699e444d5698665ec401f0f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba91e209131cea89bb0.md>)

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

### OmniRet

Classification Score (CLS): 48.6. Result ID: 69a8644e6dbb7075b9500ed9.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c572d603e6de3e3d146.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c572d603e6de3e3d146.md>)

Recorded evaluation configuration: {"LLM Size":"1.5B"}. This record does not assert independent reproduction.

### PLUME

Classification Score (CLS): 45. Result ID: 69cf830447f34ce924b99775.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49bb0636e5bf4afcdba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cf49bb0636e5bf4afcdba9.md>)

[Implementation](<https://github.com/haoxiangzhao12138/PLUME>)

Recorded evaluation configuration: {"Venue":"Ours","Backbone":"Qwen2-VL-2B"}. This record does not assert independent reproduction.

### UME-R1

Classification Score (CLS): 44.3. Result ID: 69cf830447f34ce924b99774.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49bb0636e5bf4afcdba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6909887c3ef7ccd74e5e5b46.md>)

[Implementation](<https://github.com/XMUDeepLIT/UME-R1>)

Recorded evaluation configuration: {"Venue":"ICLR’26","Backbone":"Qwen2-VL-2B"}. This record does not assert independent reproduction.

### LamRA

Classification Score (CLS): 39.3. Result ID: 699e444d5698665ec401f0f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba91e209131cea89bb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76081e209131cea6b06a.md>)

[Implementation](<https://code-kunkun.github.io/LamRA/>)

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

### VLM2VecV2

Classification Score (CLS): 39.3. Result ID: 69a8644e6dbb7075b9500ed8.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c572d603e6de3e3d146.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d61e209131cea7fa13.md>)

Recorded evaluation configuration: {"LLM Size":"1.5B"}. This record does not assert independent reproduction.

### LamRA

Classification Score (CLS): 39.3. Result ID: 69cf830447f34ce924b9976f.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49bb0636e5bf4afcdba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76081e209131cea6b06a.md>)

[Implementation](<https://code-kunkun.github.io/LamRA/>)

Recorded evaluation configuration: {"Venue":"CVPR’25","Backbone":"Qwen2-VL-2B"}. This record does not assert independent reproduction.

### VLM2Vec-V2

Classification Score (CLS): 39.3. Result ID: 69cf830447f34ce924b99772.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49bb0636e5bf4afcdba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d61e209131cea7fa13.md>)

Recorded evaluation configuration: {"Venue":"TMLR’26","Backbone":"Qwen2-VL-2B"}. This record does not assert independent reproduction.

### DUME

Classification Score (CLS): 37.7. Result ID: 69cf830447f34ce924b99773.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49bb0636e5bf4afcdba9.md>)

Recorded evaluation configuration: {"Venue":"ICLR’26","Backbone":"Qwen2-VL-2B"}. This record does not assert independent reproduction.

### GME

Classification Score (CLS): 37.4. Result ID: 699e444d5698665ec401f0f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba91e209131cea89bb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b01e209131cea74c2c.md>)

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

### CAFe

Classification Score (CLS): 35.8. Result ID: 699e444d5698665ec401f0f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba91e209131cea89bb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746ef.md>)

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

### GME

Classification Score (CLS): 34.9. Result ID: 69a8644e6dbb7075b9500ed6.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c572d603e6de3e3d146.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b01e209131cea74c2c.md>)

Recorded evaluation configuration: {"LLM Size":"1.5B"}. This record does not assert independent reproduction.

### GME

Classification Score (CLS): 34.9. Result ID: 69cf830447f34ce924b99771.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49bb0636e5bf4afcdba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b01e209131cea74c2c.md>)

Recorded evaluation configuration: {"Venue":"CVPR’25","Backbone":"Qwen2-VL-2B"}. This record does not assert independent reproduction.

### VLM2VecV1

Classification Score (CLS): 33.4. Result ID: 69a8644e6dbb7075b9500ed7.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c572d603e6de3e3d146.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766b1e209131cea6cd6f.md>)

Recorded evaluation configuration: {"LLM Size":"1.5B"}. This record does not assert independent reproduction.

### VLM2Vec

Classification Score (CLS): 33.4. Result ID: 69cf830447f34ce924b99770.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49bb0636e5bf4afcdba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766b1e209131cea6cd6f.md>)

Recorded evaluation configuration: {"Venue":"ICLR’25","Backbone":"Qwen2-VL-2B"}. This record does not assert independent reproduction.

### ColPaliv1.3

Classification Score (CLS): 26.7. Result ID: 69a8644e6dbb7075b9500ed5.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c572d603e6de3e3d146.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77261e209131cea7161f.md>)

Recorded evaluation configuration: {"LLM Size":"2B"}. This record does not assert independent reproduction.

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