# Video Question Answering on NextQA (Score)

Source: [Video Question Answering on NextQA (Score)](<https://www.sota2.com/research/sota/video-question-answering-on-nextqa-score>)

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

Data updated: 2026-05-26T13:28:17.603Z

Evaluation of model performance on the NextQA dataset for Video Question Answering, reporting the primary 'Score' metric.

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) | NextQA |
| Metric | NextQA Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

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

## Recorded results

| Method | NextQA Score | Result date | Report paper |
| --- | --- | --- | --- |
| PLM | 84.1 | Not recorded | 6a15297adbd7150506f7e46c |
| Qwen3-VL | 83.4 | Not recorded | 6a15297adbd7150506f7e46c |
| LLaVA-OV-2 | 82.5 | Not recorded | 6a15297adbd7150506f7e46c |
| InternVL-3.5 | 82 | Not recorded | 6a15297adbd7150506f7e46c |
| Keye-VL-1.5 | 75.8 | Not recorded | 6a15297adbd7150506f7e46c |
| LLaVA-OV-1.5 | 73.7 | Not recorded | 6a15297adbd7150506f7e46c |

### PLM

NextQA Score: 84.1. Result ID: 6a159fdcfbc373592c0ead4c.

[Reporting paper](<https://www.sota2.com/research/paper/6a15297adbd7150506f7e46c.md>)

Recorded evaluation configuration: {"Model Class":"8B"}. This record does not assert independent reproduction.

### Qwen3-VL

NextQA Score: 83.4. Result ID: 6a159fdcfbc373592c0ead49.

[Reporting paper](<https://www.sota2.com/research/paper/6a15297adbd7150506f7e46c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Model Class":"8B"}. This record does not assert independent reproduction.

### LLaVA-OV-2

NextQA Score: 82.5. Result ID: 6a159fdcfbc373592c0ead48.

[Reporting paper](<https://www.sota2.com/research/paper/6a15297adbd7150506f7e46c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15297adbd7150506f7e46c.md>)

[Implementation](<https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-2>)

Recorded evaluation configuration: {"Model Class":"8B"}. This record does not assert independent reproduction.

### InternVL-3.5

NextQA Score: 82. Result ID: 6a159fdcfbc373592c0ead4b.

[Reporting paper](<https://www.sota2.com/research/paper/6a15297adbd7150506f7e46c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85dc9.md>)

Recorded evaluation configuration: {"Model Class":"8B"}. This record does not assert independent reproduction.

### Keye-VL-1.5

NextQA Score: 75.8. Result ID: 6a159fdcfbc373592c0ead4a.

[Reporting paper](<https://www.sota2.com/research/paper/6a15297adbd7150506f7e46c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b2d1e209131cea87107.md>)

Recorded evaluation configuration: {"Model Class":"8B"}. This record does not assert independent reproduction.

### LLaVA-OV-1.5

NextQA Score: 73.7. Result ID: 6a159fdcfbc373592c0ead4d.

[Reporting paper](<https://www.sota2.com/research/paper/6a15297adbd7150506f7e46c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c031e209131cea8bdde.md>)

Recorded evaluation configuration: {"Model Class":"8B"}. This record does not assert independent reproduction.

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