# Video Question Answering on TGIF-QA zero-shot (test)

Source: [Video Question Answering on TGIF-QA zero-shot (test)](<https://www.sota2.com/research/sota/video-question-answering-on-tgif-qa-zero-shot-test>)

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

Data updated: 2026-02-26T05:30:14.556Z

Evaluation of model performance on the zero-shot test split of the TGIF-QA dataset for Video Question Answering tasks, focusing on general accuracy and derived 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) | TGIF-QA zero-shot (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

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

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LinVT-Qwen2-VL | 81.3 | Not recorded | 68fa762f1e209131cea6bbab |
| LinVT-InternVL2 | 79.4 | Not recorded | 68fa762f1e209131cea6bbab |
| LinVT-Molmo | 79.3 | Not recorded | 68fa762f1e209131cea6bbab |
| Tarsier | 79.2 | Not recorded | 68fa762f1e209131cea6bbab |
| SlowFast-LLaVA | 78.7 | Not recorded | 68fa762f1e209131cea6bbab |
| LinVT-BLIP-3 | 78.7 | Not recorded | 68fa762f1e209131cea6bbab |
| PLLaVA | 77.5 | Not recorded | 68fa762f1e209131cea6bbab |
| BLIP-3-Video | 76.5 | Not recorded | 68fa762f1e209131cea6bbab |
| LinVT-Aquila | 73.6 | Not recorded | 68fa762f1e209131cea6bbab |
| MiniGPT4-Video | 72.2 | Not recorded | 68fa762f1e209131cea6bbab |
| LinVT-Mipha | 71.1 | Not recorded | 68fa762f1e209131cea6bbab |
| Video-LLaVA | 70 | Not recorded | 68fa762f1e209131cea6bbab |
| Chat-UniVi | 69 | Not recorded | 68fa762f1e209131cea6bbab |
| Video-ChatGPT | 51.4 | Not recorded | 68fa762f1e209131cea6bbab |
| VideoChat | 34.4 | Not recorded | 68fa762f1e209131cea6bbab |

### LinVT-Qwen2-VL

Accuracy: 81.3. Result ID: 69942ab03a6c3148491b8330.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Implementation](<https://github.com/gls0425/LinVT>)

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### LinVT-InternVL2

Accuracy: 79.4. Result ID: 69942ab03a6c3148491b8331.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Implementation](<https://github.com/gls0425/LinVT>)

Recorded evaluation configuration: {"Size":"8B","Zero-shot":true}. This record does not assert independent reproduction.

### LinVT-Molmo

Accuracy: 79.3. Result ID: 69942ab03a6c3148491b832f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Implementation](<https://github.com/gls0425/LinVT>)

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### Tarsier

Accuracy: 79.2. Result ID: 69942ab03a6c3148491b832a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e41e209131cea64782.md>)

[Implementation](<https://github.com/bytedance/tarsier>)

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### SlowFast-LLaVA

Accuracy: 78.7. Result ID: 69942ab03a6c3148491b8329.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

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

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

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### LinVT-BLIP-3

Accuracy: 78.7. Result ID: 69942ab03a6c3148491b832e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Implementation](<https://github.com/gls0425/LinVT>)

Recorded evaluation configuration: {"Size":"4B","Zero-shot":true}. This record does not assert independent reproduction.

### PLLaVA

Accuracy: 77.5. Result ID: 69942aaf3a6c3148491b8328.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a3ea.md>)

[Implementation](<https://pllava.github.io/>)

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### BLIP-3-Video

Accuracy: 76.5. Result ID: 69942ab03a6c3148491b832b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa793a1e209131cea7cb96.md>)

Recorded evaluation configuration: {"Size":"4B","Zero-shot":true}. This record does not assert independent reproduction.

### LinVT-Aquila

Accuracy: 73.6. Result ID: 69942ab03a6c3148491b832d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Implementation](<https://github.com/gls0425/LinVT>)

Recorded evaluation configuration: {"Size":"2B","Zero-shot":true}. This record does not assert independent reproduction.

### MiniGPT4-Video

Accuracy: 72.2. Result ID: 69942aaf3a6c3148491b8327.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d21e209131cea58b79.md>)

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### LinVT-Mipha

Accuracy: 71.1. Result ID: 69942ab03a6c3148491b832c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

[Implementation](<https://github.com/gls0425/LinVT>)

Recorded evaluation configuration: {"Size":"1.6B","Zero-shot":true}. This record does not assert independent reproduction.

### Video-LLaVA

Accuracy: 70. Result ID: 69942aaf3a6c3148491b8326.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

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

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

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### Chat-UniVi

Accuracy: 69. Result ID: 69942aaf3a6c3148491b8325.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

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

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

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### Video-ChatGPT

Accuracy: 51.4. Result ID: 69942aaf3a6c3148491b8324.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

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

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

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

### VideoChat

Accuracy: 34.4. Result ID: 69942aaf3a6c3148491b8323.

[Reporting paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbab.md>)

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

Recorded evaluation configuration: {"Size":"7B","Zero-shot":true}. This record does not assert independent reproduction.

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