# Video Multi-choice Question Answering on MSR-VTT 3k (val)

Source: [Video Multi-choice Question Answering on MSR-VTT 3k (val)](<https://www.sota2.com/research/sota/video-multi-choice-question-answering-on-msr-vtt-3k-val>)

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

Data updated: 2026-02-26T05:28:48.616Z

Evaluation of model performance on the validation split of the MSR-VTT 3k dataset for the Video Multi-choice Question Answering task, reporting Accuracy.

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 Multi-choice Question Answering |
| Dataset (including any stated split) | MSR-VTT 3k (val) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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-multi-choice-question-answering-on-msr-vtt-3k-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| C4CL-mP | 96.2 | Not recorded | 68fa6f071e209131cea4364e |
| VFC | 96.2 | Not recorded | 68fa6f071e209131cea4364e |
| VFC | 95.1 | Not recorded | 68fa6f071e209131cea4364e |
| MMT (CLIP features) | 95 | Not recorded | 68fa6f071e209131cea4364e |
| CLIP-straight | 94.1 | Not recorded | 68fa6f071e209131cea4364e |
| InternVideo | 93.4 | Not recorded | 68fa6f071e209131cea4364e |
| MMT | 92.4 | Not recorded | 68fa6f071e209131cea4364e |
| VideoCLIP | 92.1 | Not recorded | 68fa6f071e209131cea4364e |
| CLIP | 91.1 | Not recorded | 68fa6f071e209131cea4364e |
| ClipBERT | 88.2 | Not recorded | 68fa6f071e209131cea4364e |
| VideoCLIP | 73.9 | Not recorded | 68fa6f071e209131cea4364e |

### C4CL-mP

Accuracy: 96.2. Result ID: 699090893a6c314849017b10.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"FINE-TUNED","# params.":"151M"}. This record does not assert independent reproduction.

### VFC

Accuracy: 96.2. Result ID: 699090893a6c314849017b11.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"FINE-TUNED","# params.":"164M"}. This record does not assert independent reproduction.

### VFC

Accuracy: 95.1. Result ID: 699090893a6c314849017b0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"ZERO-SHOT","# params.":"164M"}. This record does not assert independent reproduction.

### MMT (CLIP features)

Accuracy: 95. Result ID: 699090893a6c314849017b0f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680d1e209131cea19dc1.md>)

[Implementation](<http://thoth.inrialpes.fr/research/MMT>)

Recorded evaluation configuration: {"Evaluation Protocol":"FINE-TUNED"}. This record does not assert independent reproduction.

### CLIP-straight

Accuracy: 94.1. Result ID: 699090893a6c314849017b0e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69561e209131cea21a44.md>)

[Implementation](<https://github.com/Deferf/CLIP_Video_Representation>)

Recorded evaluation configuration: {"Evaluation Protocol":"FINE-TUNED","# params.":"151M"}. This record does not assert independent reproduction.

### InternVideo

Accuracy: 93.4. Result ID: 699090893a6c314849017b09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfc3.md>)

[Implementation](<https://github.com/OpenGVLab/InternVideo>)

Recorded evaluation configuration: {"Evaluation Protocol":"ZERO-SHOT","# params.":"≈ 460M"}. This record does not assert independent reproduction.

### MMT

Accuracy: 92.4. Result ID: 699090893a6c314849017b0c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680d1e209131cea19dc1.md>)

[Implementation](<http://thoth.inrialpes.fr/research/MMT>)

Recorded evaluation configuration: {"Evaluation Protocol":"FINE-TUNED"}. This record does not assert independent reproduction.

### VideoCLIP

Accuracy: 92.1. Result ID: 699090893a6c314849017b0d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af21e209131cea2b4a1.md>)

[Implementation](<https://github.com/pytorch/fairseq/tree/main/examples/MMPT>)

Recorded evaluation configuration: {"Evaluation Protocol":"FINE-TUNED"}. This record does not assert independent reproduction.

### CLIP

Accuracy: 91.1. Result ID: 699090893a6c314849017b08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Evaluation Protocol":"ZERO-SHOT","# params.":"151M"}. This record does not assert independent reproduction.

### ClipBERT

Accuracy: 88.2. Result ID: 699090893a6c314849017b0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa694e1e209131cea216c8.md>)

[Implementation](<https://github.com/jayleicn/ClipBERT>)

Recorded evaluation configuration: {"Evaluation Protocol":"FINE-TUNED"}. This record does not assert independent reproduction.

### VideoCLIP

Accuracy: 73.9. Result ID: 699090893a6c314849017b07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f071e209131cea4364e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af21e209131cea2b4a1.md>)

[Implementation](<https://github.com/pytorch/fairseq/tree/main/examples/MMPT>)

Recorded evaluation configuration: {"Evaluation Protocol":"ZERO-SHOT"}. This record does not assert independent reproduction.

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