# Video Question Answering on VCGBench ActivityNet

Source: [Video Question Answering on VCGBench ActivityNet](<https://www.sota2.com/research/sota/video-question-answering-on-vcgbench-activitynet>)

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

Data updated: 2026-02-26T05:38:21.306Z

Evaluation of Video Question Answering performance using the VCGBench ActivityNet dataset, reporting metrics including CI, DO, CU, TU, and CO.

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) | VCGBench ActivityNet |
| Metric | CI |
| 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

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

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

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

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

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

- [Average Score](<https://www.sota2.com/research/sota/video-question-answering-on-vcgbench-activitynet.md?metric=Average%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CI | Result date | Report paper |
| --- | --- | --- | --- |
| VideoGPT+ | 3.27 | Not recorded | 68fa73961e209131cea5d657 |
| IG-VLM | 3.11 | Not recorded | 68fa73961e209131cea5d657 |
| VideoChat2 | 3.02 | Not recorded | 68fa73961e209131cea5d657 |
| LLAMA-VID | 2.96 | Not recorded | 68fa73961e209131cea5d657 |
| Chat-UniVi | 2.89 | Not recorded | 68fa73961e209131cea5d657 |
| Video-LLaVA | 2.84 | Not recorded | 68fa73961e209131cea5d657 |
| VTimeLLM | 2.78 | Not recorded | 68fa73961e209131cea5d657 |
| BT-Adapter | 2.68 | Not recorded | 68fa73961e209131cea5d657 |
| Video-ChatGPT | 2.4 | Not recorded | 68fa73961e209131cea5d657 |

### VideoGPT+

CI: 3.27. Result ID: 6992f8cb3a6c31484912c1cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

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

Recorded evaluation configuration: {"Number of frames":"16"}. This record does not assert independent reproduction.

### IG-VLM

CI: 3.11. Result ID: 6992f8cb3a6c31484912c1ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581e0.md>)

[Implementation](<https://github.com/imagegridworth/IG-VLM>)

Recorded evaluation configuration: {"Number of frames":"16"}. This record does not assert independent reproduction.

### VideoChat2

CI: 3.02. Result ID: 6992f8cb3a6c31484912c1c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73411e209131cea5b4b7.md>)

Recorded evaluation configuration: {"Number of frames":"16"}. This record does not assert independent reproduction.

### LLAMA-VID

CI: 2.96. Result ID: 6992f8cb3a6c31484912c1c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

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

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

Recorded evaluation configuration: {"Number of frames":"16"}. This record does not assert independent reproduction.

### Chat-UniVi

CI: 2.89. Result ID: 6992f8cb3a6c31484912c1c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d31e209131cea58bff.md>)

[Implementation](<https://github.com/PKU-YuanGroup/Chat-UniVi>)

Recorded evaluation configuration: {"Number of frames":"64"}. This record does not assert independent reproduction.

### Video-LLaVA

CI: 2.84. Result ID: 6992f8cb3a6c31484912c1c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65534.md>)

[Implementation](<https://github.com/PKU-YuanGroup/Video-LLaVA>)

Recorded evaluation configuration: {"Number of frames":"16"}. This record does not assert independent reproduction.

### VTimeLLM

CI: 2.78. Result ID: 6992f8cb3a6c31484912c1c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa715b1e209131cea50d56.md>)

[Implementation](<https://github.com/huangb23/VTimeLLM>)

Recorded evaluation configuration: {"Number of frames":"16"}. This record does not assert independent reproduction.

### BT-Adapter

CI: 2.68. Result ID: 6992f8cb3a6c31484912c1c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

Recorded evaluation configuration: {"Number of frames":"16"}. This record does not assert independent reproduction.

### Video-ChatGPT

CI: 2.4. Result ID: 6992f8cb3a6c31484912c1c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d657.md>)

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

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

Recorded evaluation configuration: {"Number of frames":"100"}. This record does not assert independent reproduction.

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