# Video Question Answering on VCGBench (test)

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

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

Data updated: 2026-02-26T06:03:46.359Z

Evaluation of Video Question Answering performance on the test split of the VCGBench dataset.

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 (test) |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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-question-answering-on-vcgbench-test.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| LLaVAOneVision-7B | 3.51 | Not recorded | 68fa75051e209131cea65504 |
| LLaVA-NeXT-Interleave-7B | 3.42 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-Video-7B | 3.22 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-Video-3B | 3.17 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-Video-1B | 3.14 | Not recorded | 68fa75051e209131cea65504 |
| Video-LLaMA2-7B | 3.13 | Not recorded | 68fa75051e209131cea65504 |
| LLaVAOneVision-0.5B | 3.12 | Not recorded | 68fa75051e209131cea65504 |
| LLaVA-NeXT-Interleave-0.5B | 3.07 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-Video-7B | 3.05 | Not recorded | 68fa75051e209131cea65504 |
| SlowFast-LLaVA-7B | 3.04 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-Video-3B | 3.04 | Not recorded | 68fa75051e209131cea65504 |
| IG-VLM-7B (LLaVA-v1.6) | 3.03 | Not recorded | 68fa75051e209131cea65504 |
| VideoChat2-7B | 2.98 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-Video-1B | 2.86 | Not recorded | 68fa75051e209131cea65504 |
| Video-LLaVA-7B | 2.84 | Not recorded | 68fa75051e209131cea65504 |
| VideoChatGPT-7B | 2.42 | Not recorded | 68fa75051e209131cea65504 |

### LLaVAOneVision-7B

Score: 3.51. Result ID: 699370673a6c31484915ee7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

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

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

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"7B"}. This record does not assert independent reproduction.

### LLaVA-NeXT-Interleave-7B

Score: 3.42. Result ID: 699370673a6c31484915ee7b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"7B"}. This record does not assert independent reproduction.

### MM1.5-Video-7B

Score: 3.22. Result ID: 699370673a6c31484915ee80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"7B"}. This record does not assert independent reproduction.

### MM1.5-Video-3B

Score: 3.17. Result ID: 699370673a6c31484915ee7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"3B"}. This record does not assert independent reproduction.

### MM1.5-Video-1B

Score: 3.14. Result ID: 699370673a6c31484915ee7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"1B"}. This record does not assert independent reproduction.

### Video-LLaMA2-7B

Score: 3.13. Result ID: 699370673a6c31484915ee79.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

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

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

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"7B"}. This record does not assert independent reproduction.

### LLaVAOneVision-0.5B

Score: 3.12. Result ID: 699370673a6c31484915ee7c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

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

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

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"0.5B"}. This record does not assert independent reproduction.

### LLaVA-NeXT-Interleave-0.5B

Score: 3.07. Result ID: 699370673a6c31484915ee7a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"0.5B"}. This record does not assert independent reproduction.

### MM1.5-Video-7B

Score: 3.05. Result ID: 699370673a6c31484915ee75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Training Mode":"Training-free","Video Data":false,"Model Size":"7B"}. This record does not assert independent reproduction.

### SlowFast-LLaVA-7B

Score: 3.04. Result ID: 699370673a6c31484915ee72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

[Implementation](<https://huggingface.co/collections/liuhaotian/llava-next-65b9e40155f60fd046a5ccf2>)

Recorded evaluation configuration: {"Training Mode":"Training-free","Video Data":false,"Model Size":"7B"}. This record does not assert independent reproduction.

### MM1.5-Video-3B

Score: 3.04. Result ID: 699370673a6c31484915ee74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Training Mode":"Training-free","Video Data":false,"Model Size":"3B"}. This record does not assert independent reproduction.

### IG-VLM-7B (LLaVA-v1.6)

Score: 3.03. Result ID: 699370673a6c31484915ee71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

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

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

Recorded evaluation configuration: {"Training Mode":"Training-free","Video Data":false,"Model Size":"7B"}. This record does not assert independent reproduction.

### VideoChat2-7B

Score: 2.98. Result ID: 699370673a6c31484915ee78.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

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

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"7B"}. This record does not assert independent reproduction.

### MM1.5-Video-1B

Score: 2.86. Result ID: 699370673a6c31484915ee73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Training Mode":"Training-free","Video Data":false,"Model Size":"1B"}. This record does not assert independent reproduction.

### Video-LLaVA-7B

Score: 2.84. Result ID: 699370673a6c31484915ee77.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

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

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

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"7B"}. This record does not assert independent reproduction.

### VideoChatGPT-7B

Score: 2.42. Result ID: 699370673a6c31484915ee76.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

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

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

Recorded evaluation configuration: {"Training Mode":"SFT","Video Data":true,"Model Size":"7B"}. This record does not assert independent reproduction.

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