# Visual Mathematical Reasoning on MathVision (BoN@8)

Source: [Visual Mathematical Reasoning on MathVision (BoN@8)](<https://www.sota2.com/research/sota/visual-mathematical-reasoning-on-mathvision-bon-at-8>)

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

Data updated: 2026-03-18T08:24:21.412Z

Evaluation of model performance on the MathVision dataset for Visual Mathematical Reasoning, specifically measured using BoN@8 accuracy and derived metrics.

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 Mathematical Reasoning |
| Dataset (including any stated split) | MathVision |
| Metric | BoN@8 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [BoN@8 Accuracy](<https://www.sota2.com/research/sota/visual-mathematical-reasoning-on-mathvision-bon-at-8.md?metric=BoN%408%20Accuracy>): Higher is better; unit: PERCENT.

- [Delta (BoN@8 - Pass@1)](<https://www.sota2.com/research/sota/visual-mathematical-reasoning-on-mathvision-bon-at-8.md?metric=Delta%20(BoN%408%20-%20Pass%401)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BoN@8 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Gemini-2.0-Flash | 43.6 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-38B + EVPV-PRM | 37.59 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| Claude-3.5-Sonnet | 35.6 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-38B + VisualPRM | 35.2 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-38B | 32.2 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| GPT-4o | 31.2 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-26B + VisualPRM | 29.6 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-26B + EVPV-PRM | 28.11 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-8B + VisualPRM | 25.7 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-26B | 23.4 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-8B + EVPV-PRM | 22.07 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-8B | 17 | Not recorded | 69ba31af0636e5bf4afc0a3c |

### Gemini-2.0-Flash

BoN@8 Accuracy: 43.6. Result ID: 69ba613447f34ce924a438dc.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-38B + EVPV-PRM

BoN@8 Accuracy: 37.59. Result ID: 69ba613447f34ce924a438e6.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-38B","Process Reward Model (PRM)":"EVPV-PRM","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### Claude-3.5-Sonnet

BoN@8 Accuracy: 35.6. Result ID: 69ba613447f34ce924a438dd.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-38B + VisualPRM

BoN@8 Accuracy: 35.2. Result ID: 69ba613447f34ce924a438e5.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-38B","Process Reward Model (PRM)":"VisualPRM","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-38B

BoN@8 Accuracy: 32.2. Result ID: 69ba613447f34ce924a438e4.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-38B","Process Reward Model (PRM)":"None","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### GPT-4o

BoN@8 Accuracy: 31.2. Result ID: 69ba613447f34ce924a438db.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-26B + VisualPRM

BoN@8 Accuracy: 29.6. Result ID: 69ba613447f34ce924a438e2.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-26B","Process Reward Model (PRM)":"VisualPRM","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-26B + EVPV-PRM

BoN@8 Accuracy: 28.11. Result ID: 69ba613447f34ce924a438e3.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-26B","Process Reward Model (PRM)":"EVPV-PRM","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-8B + VisualPRM

BoN@8 Accuracy: 25.7. Result ID: 69ba613447f34ce924a438df.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-8B","Process Reward Model (PRM)":"VisualPRM","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-26B

BoN@8 Accuracy: 23.4. Result ID: 69ba613447f34ce924a438e1.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-26B","Process Reward Model (PRM)":"None","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-8B + EVPV-PRM

BoN@8 Accuracy: 22.07. Result ID: 69ba613447f34ce924a438e0.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-8B","Process Reward Model (PRM)":"EVPV-PRM","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

### InternVL2.5-8B

BoN@8 Accuracy: 17. Result ID: 69ba613447f34ce924a438de.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31af0636e5bf4afc0a3c.md>)

Recorded evaluation configuration: {"Policy Model":"InternVL2.5-8B","Process Reward Model (PRM)":"None","Reranking Strategy":"Best-of-8"}. This record does not assert independent reproduction.

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