# Video Question Answering on Video-MME (test)

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

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

Data updated: 2026-02-26T05:30:34.669Z

Evaluation of Video Question Answering performance on the test split of the Video-MME dataset, reporting primary metrics like Accuracy and F1 Mean, alongside statistical variance metrics (standard deviations).

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) | Video-MME (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| 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

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

- [F1 Mean](<https://www.sota2.com/research/sota/video-question-answering-on-video-mme-test.md?metric=F1%20Mean>): Higher is better; unit: PERCENT.

- [Recall Std Dev](<https://www.sota2.com/research/sota/video-question-answering-on-video-mme-test.md?metric=Recall%20Std%20Dev>): Lower is better; unit: SCALAR.

- [F1 Std Dev](<https://www.sota2.com/research/sota/video-question-answering-on-video-mme-test.md?metric=F1%20Std%20Dev>): Lower is better; unit: SCALAR.

- [JS Std Dev](<https://www.sota2.com/research/sota/video-question-answering-on-video-mme-test.md?metric=JS%20Std%20Dev>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| BOLD | 40.19 | Not recorded | 68fa79041e209131cea7bb81 |
| Weighted\_BOLD | 40.04 | Not recorded | 68fa79041e209131cea7bb81 |
| BOLD | 34.7 | Not recorded | 68fa79041e209131cea7bb81 |
| Weighted\_BOLD | 34.63 | Not recorded | 68fa79041e209131cea7bb81 |
| BOLD | 32.73 | Not recorded | 68fa79041e209131cea7bb81 |
| Weighted\_BOLD | 32.2 | Not recorded | 68fa79041e209131cea7bb81 |

### BOLD

Accuracy: 40.19. Result ID: 6995b7bb3badfaffe6b897c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Implementation](<https://github.com/ologin/BOLD>)

Recorded evaluation configuration: {"Model":"SeViLA","k":0.5}. This record does not assert independent reproduction.

### Weighted\_BOLD

Accuracy: 40.04. Result ID: 6995b7bb3badfaffe6b897c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Implementation](<https://github.com/ologin/BOLD>)

Recorded evaluation configuration: {"Model":"SeViLA","k":0.5}. This record does not assert independent reproduction.

### BOLD

Accuracy: 34.7. Result ID: 6995b7bb3badfaffe6b897c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Implementation](<https://github.com/ologin/BOLD>)

Recorded evaluation configuration: {"Model":"Video-LLaVA","k":0.5}. This record does not assert independent reproduction.

### Weighted\_BOLD

Accuracy: 34.63. Result ID: 6995b7bb3badfaffe6b897c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Implementation](<https://github.com/ologin/BOLD>)

Recorded evaluation configuration: {"Model":"Video-LLaVA","k":0.5}. This record does not assert independent reproduction.

### BOLD

Accuracy: 32.73. Result ID: 6995b7bb3badfaffe6b897c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Implementation](<https://github.com/ologin/BOLD>)

Recorded evaluation configuration: {"Model":"Video-LLaMA","k":0.5}. This record does not assert independent reproduction.

### Weighted\_BOLD

Accuracy: 32.2. Result ID: 6995b7bb3badfaffe6b897c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb81.md>)

[Implementation](<https://github.com/ologin/BOLD>)

Recorded evaluation configuration: {"Model":"Video-LLaMA","k":0.5}. This record does not assert independent reproduction.

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