# Video Question Answering on HourVideo v1.0 (test)

Source: [Video Question Answering on HourVideo v1.0 (test)](<https://www.sota2.com/research/sota/video-question-answering-on-hourvideo-v1-0-test>)

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

Data updated: 2026-03-05T09:48:58.055Z

Evaluation of model performance on the test split of HourVideo version 1.0 for Video Question Answering tasks, reporting accuracy across overall, navigation, perception, visual reasoning, and summarization components.

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) | HourVideo v1.0 (test) |
| Metric | Overall Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Overall Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-hourvideo-v1-0-test.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

- [Navigation Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-hourvideo-v1-0-test.md?metric=Navigation%20Accuracy>): Higher is better; unit: PERCENT.

- [Perception Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-hourvideo-v1-0-test.md?metric=Perception%20Accuracy>): Higher is better; unit: PERCENT.

- [Visual Reasoning Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-hourvideo-v1-0-test.md?metric=Visual%20Reasoning%20Accuracy>): Higher is better; unit: PERCENT.

- [Summarization Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-hourvideo-v1-0-test.md?metric=Summarization%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FocusGraph-m | 33.4 | Not recorded | 69a90e062d603e6de3e407f5 |
| GenS | 32.9 | Not recorded | 69a90e062d603e6de3e407f5 |
| FocusGraph-s | 32.3 | Not recorded | 69a90e062d603e6de3e407f5 |
| ViaRL | 32.23 | Not recorded | 69a90e062d603e6de3e407f5 |
| Uniform Sampling | 31.22 | Not recorded | 69a90e062d603e6de3e407f5 |
| Uniform Sampling | 29.86 | Not recorded | 69a90e062d603e6de3e407f5 |
| MaxInfo | 29.61 | Not recorded | 69a90e062d603e6de3e407f5 |
| ReMEmbR | 24.28 | Not recorded | 69a90e062d603e6de3e407f5 |

### FocusGraph-m

Overall Accuracy: 33.4. Result ID: 69a951706dbb7075b9533180.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

Recorded evaluation configuration: {"QA LLM":"Qwen-2.5-VL-7B","Frame Number":"8"}. This record does not assert independent reproduction.

### GenS

Overall Accuracy: 32.9. Result ID: 69a951706dbb7075b953317d.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af61e209131cea8600f.md>)

Recorded evaluation configuration: {"QA LLM":"Qwen-2.5-VL-7B","Frame Number":"8"}. This record does not assert independent reproduction.

### FocusGraph-s

Overall Accuracy: 32.3. Result ID: 69a951706dbb7075b953317f.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

Recorded evaluation configuration: {"QA LLM":"Qwen-2.5-VL-7B","Frame Number":"8"}. This record does not assert independent reproduction.

### ViaRL

Overall Accuracy: 32.23. Result ID: 69a951706dbb7075b953317e.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b91e209131cea7a0d2.md>)

Recorded evaluation configuration: {"QA LLM":"Qwen-2.5-VL-7B","Frame Number":"8"}. This record does not assert independent reproduction.

### Uniform Sampling

Overall Accuracy: 31.22. Result ID: 69a951706dbb7075b953317a.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

Recorded evaluation configuration: {"QA LLM":"Qwen-2.5-VL-7B","Frame Number":"16"}. This record does not assert independent reproduction.

### Uniform Sampling

Overall Accuracy: 29.86. Result ID: 69a951706dbb7075b9533179.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

Recorded evaluation configuration: {"QA LLM":"Qwen-2.5-VL-7B","Frame Number":"8"}. This record does not assert independent reproduction.

### MaxInfo

Overall Accuracy: 29.61. Result ID: 69a951706dbb7075b953317b.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa772d1e209131cea7196c.md>)

Recorded evaluation configuration: {"QA LLM":"Qwen-2.5-VL-7B","Frame Number":"16"}. This record does not assert independent reproduction.

### ReMEmbR

Overall Accuracy: 24.28. Result ID: 69a951706dbb7075b953317c.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e61e209131cea6490d.md>)

Recorded evaluation configuration: {"QA LLM":"Llama3.1-8B","Frame Number":"8¹"}. This record does not assert independent reproduction.

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