# Video Question Answering on NExT-QA de-biased set

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

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

Data updated: 2026-02-26T06:06:10.256Z

Evaluation of model performance on the de-biased set split of the NExT-QA dataset for Video Question Answering, focusing on Temporal and Causal reasoning metrics.

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 de-biased set |
| Metric | Temporal Reasoning Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Temporal Reasoning Score](<https://www.sota2.com/research/sota/video-question-answering-on-next-qa-de-biased-set.md?metric=Temporal%20Reasoning%20Score>): Higher is better; unit: PERCENT.

- [Causal Reasoning Score](<https://www.sota2.com/research/sota/video-question-answering-on-next-qa-de-biased-set.md?metric=Causal%20Reasoning%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Temporal Reasoning Score | Result date | Report paper |
| --- | --- | --- | --- |
| video-grounded entailment tree reasoning | 60.8 | Not recorded | 68fa77931e209131cea7410b |
| VideoTree | 60.2 | Not recorded | 68fa77931e209131cea7410b |
| VideoAgent | 58.2 | Not recorded | 68fa77931e209131cea7410b |
| LLoVi | 53.1 | Not recorded | 68fa77931e209131cea7410b |

### video-grounded entailment tree reasoning

Temporal Reasoning Score: 60.8. Result ID: 699544103badfaffe630c8b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea7410b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77931e209131cea7410b.md>)

Recorded evaluation configuration: {"Model Reasoner":"VideoLLAVA (7B)"}. This record does not assert independent reproduction.

### VideoTree

Temporal Reasoning Score: 60.2. Result ID: 699544103badfaffe630c8b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea7410b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea73736.md>)

[Implementation](<https://videotree2024.github.io/>)

Recorded evaluation configuration: {"Model Reasoner":"GPT-4 (1.8T)"}. This record does not assert independent reproduction.

### VideoAgent

Temporal Reasoning Score: 58.2. Result ID: 699544103badfaffe630c8b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea7410b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72971e209131cea5761e.md>)

[Implementation](<https://wxh1996.github.io/VideoAgent-Website/>)

Recorded evaluation configuration: {"Model Reasoner":"GPT-4 (1.8T)"}. This record does not assert independent reproduction.

### LLoVi

Temporal Reasoning Score: 53.1. Result ID: 699544103badfaffe630c8b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77931e209131cea7410b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6629c.md>)

[Implementation](<https://github.com/CeeZh/LLoVi>)

Recorded evaluation configuration: {"Model Reasoner":"GPT-4 (1.8T)"}. This record does not assert independent reproduction.

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