# Visual Question Answering (Perception + Reasoning) on MathVista, MMStar, and MMVet

Source: [Visual Question Answering (Perception + Reasoning) on MathVista, MMStar, and MMVet](<https://www.sota2.com/research/sota/visual-question-answering-perception-plus-reasoning-on-mathvista-mmstar-and-mmvet>)

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

Data updated: 2026-02-26T05:51:39.710Z

Aggregate evaluation of model performance across MathVista, MMStar, and MMVet datasets, focusing on visual question answering that requires both perceptual understanding and complex reasoning.

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 | Visual Question Answering (Perception + Reasoning) |
| Dataset (including any stated split) | MathVista, MMStar, MMVet |
| Metric | MathVista Score |
| 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

- [MathVista Score](<https://www.sota2.com/research/sota/visual-question-answering-perception-plus-reasoning-on-mathvista-mmstar-and-mmvet.md?metric=MathVista%20Score>): Higher is better; unit: PERCENT.

- [MMStar Score](<https://www.sota2.com/research/sota/visual-question-answering-perception-plus-reasoning-on-mathvista-mmstar-and-mmvet.md?metric=MMStar%20Score>): Higher is better; unit: PERCENT.

- [MMVet Score](<https://www.sota2.com/research/sota/visual-question-answering-perception-plus-reasoning-on-mathvista-mmstar-and-mmvet.md?metric=MMVet%20Score>): Higher is better; unit: PERCENT.

- [Aggregate Score](<https://www.sota2.com/research/sota/visual-question-answering-perception-plus-reasoning-on-mathvista-mmstar-and-mmvet.md?metric=Aggregate%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MathVista Score | Result date | Report paper |
| --- | --- | --- | --- |
| LATTE | 46.9 | Not recorded | 68fa7b451e209131cea876c2 |
| Vanilla IT | 42.4 | Not recorded | 68fa7b451e209131cea876c2 |
| LATTE | 38.9 | Not recorded | 68fa7b451e209131cea876c2 |
| LATTE | 36.6 | Not recorded | 68fa7b451e209131cea876c2 |
| Vanilla IT | 36.2 | Not recorded | 68fa7b451e209131cea876c2 |
| LATTE | 34.9 | Not recorded | 68fa7b451e209131cea876c2 |
| Vanilla IT | 33.1 | Not recorded | 68fa7b451e209131cea876c2 |
| Vanilla IT | 31.1 | Not recorded | 68fa7b451e209131cea876c2 |

### LATTE

MathVista Score: 46.9. Result ID: 698b83e17a967eddb76f3b46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Implementation](<https://github.com/SalesforceAIResearch/LATTE>)

Recorded evaluation configuration: {"Language / Vision":"Qwen2-7B/SigLIP","Starting checkpoint":"LLaVA-OV Stage 1.5"}. This record does not assert independent reproduction.

### Vanilla IT

MathVista Score: 42.4. Result ID: 698b83e17a967eddb76f3b45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

Recorded evaluation configuration: {"Language / Vision":"Qwen2-7B/SigLIP","Starting checkpoint":"LLaVA-OV Stage 1.5"}. This record does not assert independent reproduction.

### LATTE

MathVista Score: 38.9. Result ID: 698b83e17a967eddb76f3b44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Implementation](<https://github.com/SalesforceAIResearch/LATTE>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/SigLIP","Starting checkpoint":"Mantis Instruct-tuned"}. This record does not assert independent reproduction.

### LATTE

MathVista Score: 36.6. Result ID: 698b83e17a967eddb76f3b40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Implementation](<https://github.com/SalesforceAIResearch/LATTE>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/CLIP","Starting checkpoint":"Mantis Pretrained"}. This record does not assert independent reproduction.

### Vanilla IT

MathVista Score: 36.2. Result ID: 698b83e17a967eddb76f3b43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/SigLIP","Starting checkpoint":"Mantis Instruct-tuned"}. This record does not assert independent reproduction.

### LATTE

MathVista Score: 34.9. Result ID: 698b83e17a967eddb76f3b42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Implementation](<https://github.com/SalesforceAIResearch/LATTE>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/CLIP","Starting checkpoint":"Mantis Pretrained (Configuration 2)"}. This record does not assert independent reproduction.

### Vanilla IT

MathVista Score: 33.1. Result ID: 698b83e17a967eddb76f3b3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/CLIP","Starting checkpoint":"Mantis Pretrained"}. This record does not assert independent reproduction.

### Vanilla IT

MathVista Score: 31.1. Result ID: 698b83e17a967eddb76f3b41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/CLIP","Starting checkpoint":"Mantis Pretrained (Configuration 2)"}. This record does not assert independent reproduction.

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