# Multimodal Math Reasoning on MathVista (avg@8 accuracy)

Source: [Multimodal Math Reasoning on MathVista (avg@8 accuracy)](<https://www.sota2.com/research/sota/multimodal-math-reasoning-on-mathvista-avg-at-8-accuracy>)

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

Data updated: 2026-04-15T09:05:14.843Z

Evaluation of model performance on the MathVista dataset for Multimodal Math Reasoning, specifically reporting the average accuracy across 8 samples (avg@8).

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 | Multimodal Math Reasoning |
| Dataset (including any stated split) | MathVista |
| Metric | Avg@8 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Avg@8 Accuracy](<https://www.sota2.com/research/sota/multimodal-math-reasoning-on-mathvista-avg-at-8-accuracy.md?metric=Avg%408%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg@8 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PAPO\_G | 69.53 | Not recorded | 68fa7a761e209131cea8363f |
| PAPO\_D | 67.53 | Not recorded | 68fa7a761e209131cea8363f |
| GRPO | 65.48 | Not recorded | 68fa7a761e209131cea8363f |
| PAPO\_D | 62.53 | Not recorded | 68fa7a761e209131cea8363f |
| DAPO | 61.91 | Not recorded | 68fa7a761e209131cea8363f |
| PAPO\_G | 61.38 | Not recorded | 68fa7a761e209131cea8363f |
| DAPO | 60.89 | Not recorded | 68fa7a761e209131cea8363f |
| GRPO | 59.34 | Not recorded | 68fa7a761e209131cea8363f |
| PAPO\_G | 56.08 | Not recorded | 68fa7a761e209131cea8363f |
| GRPO | 53.58 | Not recorded | 68fa7a761e209131cea8363f |

### PAPO\_G

Avg@8 Accuracy: 69.53. Result ID: 69df54ba47f34ce924c8442c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Model Size":"7B","Training Algorithm":"PAPO\_G","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### PAPO\_D

Avg@8 Accuracy: 67.53. Result ID: 69df54ba47f34ce924c84430.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Model Size":"7B","Training Algorithm":"PAPO\_D","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### GRPO

Avg@8 Accuracy: 65.48. Result ID: 69df54ba47f34ce924c8442b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Model Size":"7B","Training Algorithm":"GRPO","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### PAPO\_D

Avg@8 Accuracy: 62.53. Result ID: 69df54ba47f34ce924c8442e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Model Size":"3B","Training Algorithm":"PAPO\_D","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### DAPO

Avg@8 Accuracy: 61.91. Result ID: 69df54ba47f34ce924c8442f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78a81e209131cea79ac6.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Model Size":"7B","Training Algorithm":"DAPO","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### PAPO\_G

Avg@8 Accuracy: 61.38. Result ID: 69df54ba47f34ce924c8442a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Model Size":"3B","Training Algorithm":"PAPO\_G","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### DAPO

Avg@8 Accuracy: 60.89. Result ID: 69df54ba47f34ce924c8442d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78a81e209131cea79ac6.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Model Size":"3B","Training Algorithm":"DAPO","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### GRPO

Avg@8 Accuracy: 59.34. Result ID: 69df54ba47f34ce924c84429.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Model Size":"3B","Training Algorithm":"GRPO","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### PAPO\_G

Avg@8 Accuracy: 56.08. Result ID: 69df54ba47f34ce924c84432.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-VL (thinking)","Model Size":"2B","Training Algorithm":"PAPO\_G","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

### GRPO

Avg@8 Accuracy: 53.58. Result ID: 69df54ba47f34ce924c84431.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Backbone":"Qwen3-VL (thinking)","Model Size":"2B","Training Algorithm":"GRPO","Inference Temperature":"1.0"}. This record does not assert independent reproduction.

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