# Mathematical Reasoning on MathVista (ALL, ARI, LOG, STA, VQA Scores)

Source: [Mathematical Reasoning on MathVista (ALL, ARI, LOG, STA, VQA Scores)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-mathvista-all-ari-log-sta-vqa-scores>)

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

Data updated: 2026-03-04T07:33:55.489Z

Evaluation of model performance on the MathVista dataset for Mathematical Reasoning, reporting scores across aggregated metrics including ALL, ARI, LOG, STA, and VQA.

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 | Mathematical Reasoning |
| Dataset (including any stated split) | MathVista |
| Metric | ALL Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [ALL Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-mathvista-all-ari-log-sta-vqa-scores.md?metric=ALL%20Score>): Higher is better; unit: PERCENT.

- [ARI Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-mathvista-all-ari-log-sta-vqa-scores.md?metric=ARI%20Score>): Higher is better; unit: PERCENT.

- [LOG Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-mathvista-all-ari-log-sta-vqa-scores.md?metric=LOG%20Score>): Higher is better; unit: PERCENT.

- [STA Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-mathvista-all-ari-log-sta-vqa-scores.md?metric=STA%20Score>): Higher is better; unit: PERCENT.

- [VQA Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-mathvista-all-ari-log-sta-vqa-scores.md?metric=VQA%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ALL Score | Result date | Report paper |
| --- | --- | --- | --- |
| AStar | 64.2 | Not recorded | 68fa79071e209131cea7bc7d |
| R1-VL-7B | 63.5 | Not recorded | 68fa79071e209131cea7bc7d |
| AStar | 61.7 | Not recorded | 68fa79071e209131cea7bc7d |
| Human | 60.3 | Not recorded | 68fa79071e209131cea7bc7d |
| GPT-4o | 60.1 | Not recorded | 68fa79071e209131cea7bc7d |
| URSA-8B | 59.8 | Not recorded | 68fa79071e209131cea7bc7d |
| Qwen2-VL-7B | 58.9 | Not recorded | 68fa79071e209131cea7bc7d |
| InternVL2-8B | 58.3 | Not recorded | 68fa79071e209131cea7bc7d |
| MultiMath-7B | 50 | Not recorded | 68fa79071e209131cea7bc7d |
| Math-PUMA-7B | 47.9 | Not recorded | 68fa79071e209131cea7bc7d |
| Math-LLaVA-13B | 46.6 | Not recorded | 68fa79071e209131cea7bc7d |
| LLaVA-NeXT-34B | 46.5 | Not recorded | 68fa79071e209131cea7bc7d |
| SPHINX-8x7B | 42.6 | Not recorded | 68fa79071e209131cea7bc7d |
| SPHINX-V2-13B | 36.7 | Not recorded | 68fa79071e209131cea7bc7d |
| LLaVA-1.5-13B | 27.7 | Not recorded | 68fa79071e209131cea7bc7d |
| MiniGPT4-7B | 23.1 | Not recorded | 68fa79071e209131cea7bc7d |
| Random | 17.9 | Not recorded | 68fa79071e209131cea7bc7d |

### AStar

ALL Score: 64.2. Result ID: 69a7de776dbb7075b94c5425.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Training-free":"true"}. This record does not assert independent reproduction.

### R1-VL-7B

ALL Score: 63.5. Result ID: 69a7de776dbb7075b94c5424.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a651e209131cea82e9b.md>)

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

### AStar

ALL Score: 61.7. Result ID: 69a7de776dbb7075b94c5426.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2-VL-7B","Training-free":"true"}. This record does not assert independent reproduction.

### Human

ALL Score: 60.3. Result ID: 69a7de776dbb7075b94c5417.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

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

### GPT-4o

ALL Score: 60.1. Result ID: 69a7de776dbb7075b94c5418.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

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

### URSA-8B

ALL Score: 59.8. Result ID: 69a7de776dbb7075b94c5423.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be41e209131cea8b1a7.md>)

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

### Qwen2-VL-7B

ALL Score: 58.9. Result ID: 69a7de776dbb7075b94c541f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75151e209131cea65976.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-VL>)

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

### InternVL2-8B

ALL Score: 58.3. Result ID: 69a7de776dbb7075b94c541e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

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

### MultiMath-7B

ALL Score: 50. Result ID: 69a7de776dbb7075b94c5422.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74b01e209131cea633d4.md>)

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

### Math-PUMA-7B

ALL Score: 47.9. Result ID: 69a7de776dbb7075b94c5421.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64fc2.md>)

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

### Math-LLaVA-13B

ALL Score: 46.6. Result ID: 69a7de776dbb7075b94c5420.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75201e209131cea65fb5.md>)

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

### LLaVA-NeXT-34B

ALL Score: 46.5. Result ID: 69a7de776dbb7075b94c541d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

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

### SPHINX-8x7B

ALL Score: 42.6. Result ID: 69a7de776dbb7075b94c541c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa712e1e209131cea4fc54.md>)

[Implementation](<https://github.com/Alpha-VLLM/LLaMA2-Accessory>)

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

### SPHINX-V2-13B

ALL Score: 36.7. Result ID: 69a7de776dbb7075b94c541b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa712e1e209131cea4fc54.md>)

[Implementation](<https://github.com/Alpha-VLLM/LLaMA2-Accessory>)

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

### LLaVA-1.5-13B

ALL Score: 27.7. Result ID: 69a7de776dbb7075b94c541a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

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

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

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

### MiniGPT4-7B

ALL Score: 23.1. Result ID: 69a7de776dbb7075b94c5419.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70bd1e209131cea4cf90.md>)

[Implementation](<https://minigpt-4.github.io/>)

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

### Random

ALL Score: 17.9. Result ID: 69a7de776dbb7075b94c5416.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc7d.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.