# Multi-turn Video Question Answering on MT-Video-MME

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

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

Data updated: 2026-03-24T16:03:39.715Z

Evaluation of Multi-turn Video Question Answering performance on the MT-Video-MME dataset, reporting accuracy metrics (Acc1, Acc2, Acc3, Avg).

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 | Multi-turn Video Question Answering |
| Dataset (including any stated split) | MT-Video-MME |
| Metric | Accuracy 1 (Acc1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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 1 (Acc1)](<https://www.sota2.com/research/sota/multi-turn-video-question-answering-on-mt-video-mme.md?metric=Accuracy%201%20(Acc1)>): Higher is better; unit: PERCENT.

- [Accuracy 2 (Acc2)](<https://www.sota2.com/research/sota/multi-turn-video-question-answering-on-mt-video-mme.md?metric=Accuracy%202%20(Acc2)>): Higher is better; unit: PERCENT.

- [Accuracy 3 (Acc3)](<https://www.sota2.com/research/sota/multi-turn-video-question-answering-on-mt-video-mme.md?metric=Accuracy%203%20(Acc3)>): Higher is better; unit: PERCENT.

- [Average Accuracy (Avg)](<https://www.sota2.com/research/sota/multi-turn-video-question-answering-on-mt-video-mme.md?metric=Average%20Accuracy%20(Avg)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy 1 (Acc1) | Result date | Report paper |
| --- | --- | --- | --- |
| Base | 44.3 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 28.5 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 26.8 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 26.2 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 25.5 | Not recorded | 69c21aa60636e5bf4afc4a72 |

### Base

Accuracy 1 (Acc1): 44.3. Result ID: 69c2b5c847f34ce924ac011b.

[Reporting paper](<https://www.sota2.com/research/paper/69c21aa60636e5bf4afc4a72.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MetaCompress

Accuracy 1 (Acc1): 28.5. Result ID: 69c2b5c847f34ce924ac011f.

[Reporting paper](<https://www.sota2.com/research/paper/69c21aa60636e5bf4afc4a72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21aa60636e5bf4afc4a72.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Random

Accuracy 1 (Acc1): 26.8. Result ID: 69c2b5c847f34ce924ac011c.

[Reporting paper](<https://www.sota2.com/research/paper/69c21aa60636e5bf4afc4a72.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FastV

Accuracy 1 (Acc1): 26.2. Result ID: 69c2b5c847f34ce924ac011e.

[Reporting paper](<https://www.sota2.com/research/paper/69c21aa60636e5bf4afc4a72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Sample

Accuracy 1 (Acc1): 25.5. Result ID: 69c2b5c847f34ce924ac011d.

[Reporting paper](<https://www.sota2.com/research/paper/69c21aa60636e5bf4afc4a72.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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