# Video Understanding on Video Detailed Caption (VDC) (test)

Source: [Video Understanding on Video Detailed Caption (VDC) (test)](<https://www.sota2.com/research/sota/video-understanding-on-video-detailed-caption-vdc-test>)

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

Data updated: 2026-02-26T06:08:00.849Z

Evaluation of Video Understanding performance on the test split of the Video Detailed Caption (VDC) dataset, using GPT-3.5 for scoring.

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) | Video Detailed Caption (VDC) (test) |
| Metric | VDC GPT-3.5 Score |
| Unit | SCALAR |
| 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

- [VDC GPT-3.5 Score](<https://www.sota2.com/research/sota/video-understanding-on-video-detailed-caption-vdc-test.md?metric=VDC%20GPT-3.5%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | VDC GPT-3.5 Score | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4V | 4 | Not recorded | 68fa772c1e209131cea71918 |
| Oryx | 3.76 | Not recorded | 68fa772c1e209131cea71918 |
| LLaVA-OneVision | 3.75 | Not recorded | 68fa772c1e209131cea71918 |
| Oryx-1.5 | 3.74 | Not recorded | 68fa772c1e209131cea71918 |
| Oryx | 3.66 | Not recorded | 68fa772c1e209131cea71918 |
| Oryx-1.5 | 3.63 | Not recorded | 68fa772c1e209131cea71918 |
| LLaVA-OneVision | 3.6 | Not recorded | 68fa772c1e209131cea71918 |
| LLaVA-Next-Video | 3.48 | Not recorded | 68fa772c1e209131cea71918 |
| VILA-1.5 | 3.37 | Not recorded | 68fa772c1e209131cea71918 |

### GPT-4V

VDC GPT-3.5 Score: 4. Result ID: 699476db3a6c3148491d6b01.

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

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

### Oryx

VDC GPT-3.5 Score: 3.76. Result ID: 699476db3a6c3148491d6b06.

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

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

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

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

### LLaVA-OneVision

VDC GPT-3.5 Score: 3.75. Result ID: 699476db3a6c3148491d6b02.

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

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

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

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

### Oryx-1.5

VDC GPT-3.5 Score: 3.74. Result ID: 699476db3a6c3148491d6b08.

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

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

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

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

### Oryx

VDC GPT-3.5 Score: 3.66. Result ID: 699476db3a6c3148491d6b07.

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

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

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

Recorded evaluation configuration: {"Size":"34B"}. This record does not assert independent reproduction.

### Oryx-1.5

VDC GPT-3.5 Score: 3.63. Result ID: 699476db3a6c3148491d6b09.

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

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

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

Recorded evaluation configuration: {"Size":"32B"}. This record does not assert independent reproduction.

### LLaVA-OneVision

VDC GPT-3.5 Score: 3.6. Result ID: 699476db3a6c3148491d6b05.

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

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

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

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

### LLaVA-Next-Video

VDC GPT-3.5 Score: 3.48. Result ID: 699476db3a6c3148491d6b03.

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

Recorded evaluation configuration: {"Size":"34B"}. This record does not assert independent reproduction.

### VILA-1.5

VDC GPT-3.5 Score: 3.37. Result ID: 699476db3a6c3148491d6b04.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73311e209131cea5b06b.md>)

[Implementation](<https://github.com/NVlabs/VILA>)

Recorded evaluation configuration: {"Size":"40B"}. This record does not assert independent reproduction.

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