# Video Understanding on VKnowU

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

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

Data updated: 2026-07-07T11:49:49.229Z

Evaluation of video understanding capabilities using the VKnowU dataset, reporting the Score metric.

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) | VKnowU |
| Metric | Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

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

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| VideoKnow+ | 67.7 | Not recorded | 692689a5d6b0dd33429304dd |
| Video-R1-7B | 65.3 | Not recorded | 692689a5d6b0dd33429304dd |
| VideoRFT-7B | 64.6 | Not recorded | 692689a5d6b0dd33429304dd |
| GRPO-Zero | 64.3 | Not recorded | 692689a5d6b0dd33429304dd |
| mPLUG-Owl3-8B | 64.2 | Not recorded | 692689a5d6b0dd33429304dd |
| Zero-Shot | 64 | Not recorded | 692689a5d6b0dd33429304dd |
| See-Think-Answer SFT | 63.9 | Not recorded | 692689a5d6b0dd33429304dd |
| LLaVA-OneVision-7B | 63.3 | Not recorded | 692689a5d6b0dd33429304dd |
| VideoLLaMA2 | 55.7 | Not recorded | 692689a5d6b0dd33429304dd |

### VideoKnow+

Score: 67.7. Result ID: 6a4ce7cd60b88bb339cbf549.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL-7B-Instruct","Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

### Video-R1-7B

Score: 65.3. Result ID: 6a4ce7cd60b88bb339cbf544.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6f1e209131cea8e0ec.md>)

Recorded evaluation configuration: {"Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

### VideoRFT-7B

Score: 64.6. Result ID: 6a4ce7cd60b88bb339cbf545.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c241e209131cea8ca8e.md>)

Recorded evaluation configuration: {"Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

### GRPO-Zero

Score: 64.3. Result ID: 6a4ce7cd60b88bb339cbf548.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL-7B-Instruct","Evaluation Protocol":"GRPO-Zero","Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

### mPLUG-Owl3-8B

Score: 64.2. Result ID: 6a4ce7cd60b88bb339cbf542.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa746c1e209131cea61a16.md>)

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

Recorded evaluation configuration: {"Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

### Zero-Shot

Score: 64. Result ID: 6a4ce7cd60b88bb339cbf546.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL-7B-Instruct","Evaluation Protocol":"Zero-Shot","Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

### See-Think-Answer SFT

Score: 63.9. Result ID: 6a4ce7cd60b88bb339cbf547.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL-7B-Instruct","Evaluation Protocol":"SFT","Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

### LLaVA-OneVision-7B

Score: 63.3. Result ID: 6a4ce7cd60b88bb339cbf543.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e58.md>)

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

Recorded evaluation configuration: {"Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

### VideoLLaMA2

Score: 55.7. Result ID: 6a4ce7cd60b88bb339cbf541.

[Reporting paper](<https://www.sota2.com/research/paper/692689a5d6b0dd33429304dd.md>)

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

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

Recorded evaluation configuration: {"Resolution":"256x28x28","Max Frames":"32"}. This record does not assert independent reproduction.

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