# Video Question Answering on Video-ChatGPT benchmark zero-shot (test)

Source: [Video Question Answering on Video-ChatGPT benchmark zero-shot (test)](<https://www.sota2.com/research/sota/video-question-answering-on-video-chatgpt-benchmark-zero-shot-test>)

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

Data updated: 2026-02-26T05:38:21.404Z

Evaluation of model performance on the zero-shot test split of the Video-ChatGPT benchmark for Video Question Answering, reporting CI, DO, CU, TU, and CO scores.

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) | Video-ChatGPT benchmark zero-shot (test) |
| Metric | CI |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [CI](<https://www.sota2.com/research/sota/video-question-answering-on-video-chatgpt-benchmark-zero-shot-test.md?metric=CI>): Higher is better; unit: SCALAR.

- [DO](<https://www.sota2.com/research/sota/video-question-answering-on-video-chatgpt-benchmark-zero-shot-test.md?metric=DO>): Higher is better; unit: SCALAR.

- [CU](<https://www.sota2.com/research/sota/video-question-answering-on-video-chatgpt-benchmark-zero-shot-test.md?metric=CU>): Higher is better; unit: SCALAR.

- [TU](<https://www.sota2.com/research/sota/video-question-answering-on-video-chatgpt-benchmark-zero-shot-test.md?metric=TU>): Higher is better; unit: SCALAR.

- [CO](<https://www.sota2.com/research/sota/video-question-answering-on-video-chatgpt-benchmark-zero-shot-test.md?metric=CO>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CI | Result date | Report paper |
| --- | --- | --- | --- |
| LLaMA-VID | 3.07 | Not recorded | 68fa75b11e209131cea69555 |
| DC+FreeVA | 3 | Not recorded | 68fa75b11e209131cea69555 |
| LLaVA+FreeVA | 2.9 | Not recorded | 68fa75b11e209131cea69555 |
| LLaVA+FreeVA | 2.88 | Not recorded | 68fa75b11e209131cea69555 |
| LLaVA+FreeVA | 2.88 | Not recorded | 68fa75b11e209131cea69555 |
| DC+FreeVA | 2.85 | Not recorded | 68fa75b11e209131cea69555 |
| DC+FreeVA | 2.8 | Not recorded | 68fa75b11e209131cea69555 |
| BT-Adapter | 2.68 | Not recorded | 68fa75b11e209131cea69555 |
| Video-ChatGPT | 2.5 | Not recorded | 68fa75b11e209131cea69555 |
| VideoChat | 2.23 | Not recorded | 68fa75b11e209131cea69555 |
| LLaMA-Adapter | 2.03 | Not recorded | 68fa75b11e209131cea69555 |
| Video-LLaMA | 1.96 | Not recorded | 68fa75b11e209131cea69555 |

### LLaMA-VID

CI: 3.07. Result ID: 6993f5ff3a6c31484919d2b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea50559.md>)

[Implementation](<https://github.com/dvlab-research/LLaMA-VID>)

Recorded evaluation configuration: {"LLM Size":"13B","GPT-3.5 Version":"JUN","Train Free":false}. This record does not assert independent reproduction.

### DC+FreeVA

CI: 3. Result ID: 6993f5ff3a6c31484919d2b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Implementation](<https://github.com/HJYao00/DenseConnector>)

Recorded evaluation configuration: {"LLM Size":"34B","GPT-3.5 Version":"JAN","Train Free":true}. This record does not assert independent reproduction.

### LLaVA+FreeVA

CI: 2.9. Result ID: 6993f5ff3a6c31484919d2b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf32.md>)

Recorded evaluation configuration: {"LLM Size":"13B","GPT-3.5 Version":"JUN","Train Free":true}. This record does not assert independent reproduction.

### LLaVA+FreeVA

CI: 2.88. Result ID: 6993f5ff3a6c31484919d2b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf32.md>)

Recorded evaluation configuration: {"LLM Size":"7B","GPT-3.5 Version":"MAR","Train Free":true}. This record does not assert independent reproduction.

### LLaVA+FreeVA

CI: 2.88. Result ID: 6993f5ff3a6c31484919d2b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf32.md>)

Recorded evaluation configuration: {"LLM Size":"13B","GPT-3.5 Version":"JAN","Train Free":true}. This record does not assert independent reproduction.

### DC+FreeVA

CI: 2.85. Result ID: 6993f5ff3a6c31484919d2b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Implementation](<https://github.com/HJYao00/DenseConnector>)

Recorded evaluation configuration: {"LLM Size":"13B","GPT-3.5 Version":"JAN","Train Free":true}. This record does not assert independent reproduction.

### DC+FreeVA

CI: 2.8. Result ID: 6993f5ff3a6c31484919d2b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Implementation](<https://github.com/HJYao00/DenseConnector>)

Recorded evaluation configuration: {"LLM Size":"7B","GPT-3.5 Version":"JAN","Train Free":true}. This record does not assert independent reproduction.

### BT-Adapter

CI: 2.68. Result ID: 6993f5ff3a6c31484919d2b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d41e209131cea5e620.md>)

[Implementation](<https://github.com/farewellthree/BT-Adapter>)

Recorded evaluation configuration: {"LLM Size":"7B","GPT-3.5 Version":"JUN","Train Free":false}. This record does not assert independent reproduction.

### Video-ChatGPT

CI: 2.5. Result ID: 6993f5ff3a6c31484919d2b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73841e209131cea5ce32.md>)

[Implementation](<https://github.com/mbzuai-oryx/Video-ChatGPT>)

Recorded evaluation configuration: {"LLM Size":"7B","GPT-3.5 Version":"MAR","Train Free":false}. This record does not assert independent reproduction.

### VideoChat

CI: 2.23. Result ID: 6993f5ff3a6c31484919d2af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ba1e209131cea52cc7.md>)

Recorded evaluation configuration: {"LLM Size":"7B","GPT-3.5 Version":"MAR","Train Free":false}. This record does not assert independent reproduction.

### LLaMA-Adapter

CI: 2.03. Result ID: 6993f5ff3a6c31484919d2ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74d81e209131cea641d1.md>)

[Implementation](<https://github.com/OpenGVLab/LLaMA-Adapter>)

Recorded evaluation configuration: {"LLM Size":"7B","GPT-3.5 Version":"MAR","Train Free":false}. This record does not assert independent reproduction.

### Video-LLaMA

CI: 1.96. Result ID: 6993f5ff3a6c31484919d2ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75b11e209131cea69555.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e393.md>)

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

Recorded evaluation configuration: {"LLM Size":"7B","GPT-3.5 Version":"MAR","Train Free":false}. This record does not assert independent reproduction.

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