# Multi-turn Visual Question Answering on MT-VQA v2

Source: [Multi-turn Visual Question Answering on MT-VQA v2](<https://www.sota2.com/research/sota/multi-turn-visual-question-answering-on-mt-vqa-v2>)

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

Data updated: 2026-03-24T16:03:39.752Z

Evaluation of model performance on the MT-VQA v2 dataset for multi-turn visual question answering, 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 Visual Question Answering |
| Dataset (including any stated split) | MT-VQA v2 |
| Metric | Acc1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 27 of 27 |
| 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

- [Acc1](<https://www.sota2.com/research/sota/multi-turn-visual-question-answering-on-mt-vqa-v2.md?metric=Acc1>): Higher is better; unit: PERCENT.

- [Acc2](<https://www.sota2.com/research/sota/multi-turn-visual-question-answering-on-mt-vqa-v2.md?metric=Acc2>): Higher is better; unit: PERCENT.

- [Acc3](<https://www.sota2.com/research/sota/multi-turn-visual-question-answering-on-mt-vqa-v2.md?metric=Acc3>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/multi-turn-visual-question-answering-on-mt-vqa-v2.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc1 | Result date | Report paper |
| --- | --- | --- | --- |
| Base | 81.02 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Base | 80.2 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Base | 78.8 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Base | 78.35 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 78.24 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 78.14 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 77.93 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 77.75 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 77.51 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 77.3 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Base | 76.72 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 76.6 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 76.18 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 75.96 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 75.78 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 75.67 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 75.07 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 74.63 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 74.03 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 73.85 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 73.81 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| PruMerge | 73.8 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 73.63 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 72.96 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| PruMerge | 72.79 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 72.72 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 69.3 | Not recorded | 69c21aa60636e5bf4afc4a72 |

### Base

Acc1: 81.02. Result ID: 69c2b5c847f34ce924ac0131.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Base

Acc1: 80.2. Result ID: 69c2b5c847f34ce924ac012c.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Base

Acc1: 78.8. Result ID: 69c2b5c847f34ce924ac0136.

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

Recorded evaluation configuration: {"Model":"XComposer-2.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Base

Acc1: 78.35. Result ID: 69c2b5c847f34ce924ac0126.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 78.24. Result ID: 69c2b5c847f34ce924ac013a.

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

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

Recorded evaluation configuration: {"Model":"XComposer-2.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 78.14. Result ID: 69c2b5c847f34ce924ac0135.

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

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### FastV

Acc1: 77.93. Result ID: 69c2b5c847f34ce924ac0139.

[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: {"Model":"XComposer-2.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 77.75. Result ID: 69c2b5c847f34ce924ac0130.

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

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Sample

Acc1: 77.51. Result ID: 69c2b5c847f34ce924ac0133.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Random

Acc1: 77.3. Result ID: 69c2b5c847f34ce924ac0132.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Base

Acc1: 76.72. Result ID: 69c2b5c847f34ce924ac0120.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Sample

Acc1: 76.6. Result ID: 69c2b5c847f34ce924ac012e.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Random

Acc1: 76.18. Result ID: 69c2b5c847f34ce924ac012d.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### FastV

Acc1: 75.96. Result ID: 69c2b5c847f34ce924ac012f.

[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: {"Model":"LLaVA-NeXT-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### FastV

Acc1: 75.78. Result ID: 69c2b5c847f34ce924ac0134.

[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: {"Model":"LLaVA-NeXT-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 75.67. Result ID: 69c2b5c847f34ce924ac0125.

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

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Sample

Acc1: 75.07. Result ID: 69c2b5c847f34ce924ac0138.

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

Recorded evaluation configuration: {"Model":"XComposer-2.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Random

Acc1: 74.63. Result ID: 69c2b5c847f34ce924ac0137.

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

Recorded evaluation configuration: {"Model":"XComposer-2.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 74.03. Result ID: 69c2b5c847f34ce924ac012b.

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

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### FastV

Acc1: 73.85. Result ID: 69c2b5c847f34ce924ac0129.

[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: {"Model":"LLaVA-1.5-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Sample

Acc1: 73.81. Result ID: 69c2b5c847f34ce924ac0128.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### PruMerge

Acc1: 73.8. Result ID: 69c2b5c847f34ce924ac012a.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa732e1e209131cea5af59.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Random

Acc1: 73.63. Result ID: 69c2b5c847f34ce924ac0127.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-13b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Sample

Acc1: 72.96. Result ID: 69c2b5c847f34ce924ac0122.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### PruMerge

Acc1: 72.79. Result ID: 69c2b5c847f34ce924ac0124.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa732e1e209131cea5af59.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### Random

Acc1: 72.72. Result ID: 69c2b5c847f34ce924ac0121.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

### FastV

Acc1: 69.3. Result ID: 69c2b5c847f34ce924ac0123.

[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: {"Model":"LLaVA-1.5-7b","Reduction Rate":"70%"}. This record does not assert independent reproduction.

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