# Multi-turn Visual Question Answering on MT-VQA v2 (val)

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

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

Data updated: 2026-03-24T16:03:39.874Z

Evaluation of model performance on the validation split of 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 (val) |
| 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-val.md?metric=Acc1>): Higher is better; unit: PERCENT.

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

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

- [Avg Acc](<https://www.sota2.com/research/sota/multi-turn-visual-question-answering-on-mt-vqa-v2-val.md?metric=Avg%20Acc>): 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 |
| Base | 76.72 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 74.62 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 73.91 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 73.83 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 72.7 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 72.65 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 71.97 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 71.86 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 70.88 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 70.65 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| MetaCompress | 70.27 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| PruMerge | 70.18 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| PruMerge | 69.03 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 68.46 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 68.12 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 67.88 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 67.26 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Sample | 67.11 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| Random | 66.36 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 57.09 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 57.07 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 55.36 | Not recorded | 69c21aa60636e5bf4afc4a72 |
| FastV | 45.98 | Not recorded | 69c21aa60636e5bf4afc4a72 |

### Base

Acc1: 81.02. Result ID: 69c2b5c847f34ce924ac0182.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-13b","Reduction Rate":"0%"}. This record does not assert independent reproduction.

### Base

Acc1: 80.2. Result ID: 69c2b5c847f34ce924ac017d.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-7b","Reduction Rate":"0%"}. This record does not assert independent reproduction.

### Base

Acc1: 78.8. Result ID: 69c2b5c847f34ce924ac0187.

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

Recorded evaluation configuration: {"Model":"XComposer-2.5-7b","Reduction Rate":"0%"}. This record does not assert independent reproduction.

### Base

Acc1: 78.35. Result ID: 69c2b5c847f34ce924ac0177.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-13b","Reduction Rate":"0%"}. This record does not assert independent reproduction.

### Base

Acc1: 76.72. Result ID: 69c2b5c847f34ce924ac0171.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-7b","Reduction Rate":"0%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 74.62. Result ID: 69c2b5c847f34ce924ac0186.

[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":"90%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 73.91. Result ID: 69c2b5c847f34ce924ac018b.

[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":"90%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 73.83. Result ID: 69c2b5c847f34ce924ac0181.

[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":"90%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 72.7. Result ID: 69c2b5c847f34ce924ac017c.

[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":"90%"}. This record does not assert independent reproduction.

### FastV

Acc1: 72.65. Result ID: 69c2b5c847f34ce924ac018a.

[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":"90%"}. This record does not assert independent reproduction.

### Sample

Acc1: 71.97. Result ID: 69c2b5c847f34ce924ac0184.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-13b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### Random

Acc1: 71.86. Result ID: 69c2b5c847f34ce924ac0183.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-13b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### Sample

Acc1: 70.88. Result ID: 69c2b5c847f34ce924ac017f.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-7b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### Random

Acc1: 70.65. Result ID: 69c2b5c847f34ce924ac017e.

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

Recorded evaluation configuration: {"Model":"LLaVA-NeXT-7b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### MetaCompress

Acc1: 70.27. Result ID: 69c2b5c847f34ce924ac0176.

[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":"90%"}. This record does not assert independent reproduction.

### PruMerge

Acc1: 70.18. Result ID: 69c2b5c847f34ce924ac017b.

[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":"90%"}. This record does not assert independent reproduction.

### PruMerge

Acc1: 69.03. Result ID: 69c2b5c847f34ce924ac0175.

[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":"90%"}. This record does not assert independent reproduction.

### Sample

Acc1: 68.46. Result ID: 69c2b5c847f34ce924ac0189.

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

Recorded evaluation configuration: {"Model":"XComposer-2.5-7b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### Sample

Acc1: 68.12. Result ID: 69c2b5c847f34ce924ac0179.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-13b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### Random

Acc1: 67.88. Result ID: 69c2b5c847f34ce924ac0188.

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

Recorded evaluation configuration: {"Model":"XComposer-2.5-7b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### Random

Acc1: 67.26. Result ID: 69c2b5c847f34ce924ac0178.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-13b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### Sample

Acc1: 67.11. Result ID: 69c2b5c847f34ce924ac0173.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-7b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### Random

Acc1: 66.36. Result ID: 69c2b5c847f34ce924ac0172.

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

Recorded evaluation configuration: {"Model":"LLaVA-1.5-7b","Reduction Rate":"90%"}. This record does not assert independent reproduction.

### FastV

Acc1: 57.09. Result ID: 69c2b5c847f34ce924ac0180.

[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":"90%"}. This record does not assert independent reproduction.

### FastV

Acc1: 57.07. Result ID: 69c2b5c847f34ce924ac0185.

[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":"90%"}. This record does not assert independent reproduction.

### FastV

Acc1: 55.36. Result ID: 69c2b5c847f34ce924ac017a.

[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":"90%"}. This record does not assert independent reproduction.

### FastV

Acc1: 45.98. Result ID: 69c2b5c847f34ce924ac0174.

[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":"90%"}. This record does not assert independent reproduction.

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