# Video Question Answering on NExT-QA v1 (val)

Source: [Video Question Answering on NExT-QA v1 (val)](<https://www.sota2.com/research/sota/video-question-answering-on-next-qa-v1-val>)

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

Data updated: 2026-02-26T05:30:26.805Z

Evaluation of model performance on the validation split (v1) of the NExT-QA dataset for Video Question Answering, 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 Question Answering |
| Dataset (including any stated split) | NExT-QA v1 (val) |
| Metric | Accuracy |
| Unit | PERCENT |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-next-qa-v1-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SeViLa | 73.8 | Not recorded | 68fa77a41e209131cea748f6 |
| MoReVQA | 69.2 | Not recorded | 68fa77a41e209131cea748f6 |
| JCEF | 66.7 | Not recorded | 68fa77a41e209131cea748f6 |
| SeViLA | 63.6 | Not recorded | 68fa77a41e209131cea748f6 |
| HiTeA | 63.1 | Not recorded | 68fa77a41e209131cea748f6 |
| BLIP-2voting | 62.7 | Not recorded | 68fa77a41e209131cea748f6 |
| BLIP-2concat | 62.4 | Not recorded | 68fa77a41e209131cea748f6 |
| ViperGPT | 60 | Not recorded | 68fa77a41e209131cea748f6 |
| MIST-CLIP | 57.2 | Not recorded | 68fa77a41e209131cea748f6 |

### SeViLa

Accuracy: 73.8. Result ID: 69955a653badfaffe64baf8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

Recorded evaluation configuration: {"fine-tuned":true}. This record does not assert independent reproduction.

### MoReVQA

Accuracy: 69.2. Result ID: 69955a653badfaffe64baf90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Implementation](<http://juhongm999.github.io/morevqa>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### JCEF

Accuracy: 66.7. Result ID: 69955a653badfaffe64baf8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Implementation](<http://juhongm999.github.io/morevqa>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### SeViLA

Accuracy: 63.6. Result ID: 69955a653badfaffe64baf8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa715a1e209131cea50c7b.md>)

[Implementation](<https://github.com/Yui010206/SeViLA>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### HiTeA

Accuracy: 63.1. Result ID: 69955a653badfaffe64baf89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e4b1e209131cea3f143.md>)

Recorded evaluation configuration: {"fine-tuned":true}. This record does not assert independent reproduction.

### BLIP-2voting

Accuracy: 62.7. Result ID: 69955a653badfaffe64baf8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### BLIP-2concat

Accuracy: 62.4. Result ID: 69955a653badfaffe64baf8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### ViperGPT

Accuracy: 60. Result ID: 69955a653badfaffe64baf8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ec31e209131cea41d4d.md>)

[Implementation](<https://www.sota2.com/viper.cs.columbia.edu/>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

### MIST-CLIP

Accuracy: 57.2. Result ID: 69955a653badfaffe64baf88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e431e209131cea3ed48.md>)

[Implementation](<https://github.com/showlab/mist>)

Recorded evaluation configuration: {"fine-tuned":false}. This record does not assert independent reproduction.

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