# Visual Logical Reasoning on LogicVista (BoN@8)

Source: [Visual Logical Reasoning on LogicVista (BoN@8)](<https://www.sota2.com/research/sota/visual-logical-reasoning-on-logicvista-bon-at-8>)

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

Data updated: 2026-03-18T08:24:21.461Z

Evaluation of model performance on the LogicVista dataset for Visual Logical Reasoning, specifically reporting BoN@8 accuracy and the Delta\_8 score.

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 Logical Reasoning |
| Dataset (including any stated split) | LogicVista |
| 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-logical-reasoning-on-logicvista-bon-at-8.md?metric=BoN%408%20Accuracy>): Higher is better; unit: PERCENT.

- [Delta\_8 Score](<https://www.sota2.com/research/sota/visual-logical-reasoning-on-logicvista-bon-at-8.md?metric=Delta_8%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BoN@8 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Claude-3.5-Sonnet | 60.4 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-38B + EVPV-PRM | 58.74 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-38B + VisualPRM | 53.7 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| GPT-4o | 52.8 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| Gemini-2.0-Flash | 52.3 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-26B + EVPV-PRM | 51.72 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-26B + VisualPRM | 51 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-38B | 47.9 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-8B + EVPV-PRM | 45.33 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-8B + VisualPRM | 43.8 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-26B | 39.64 | Not recorded | 69ba31af0636e5bf4afc0a3c |
| InternVL2.5-8B | 36.38 | Not recorded | 69ba31af0636e5bf4afc0a3c |

### Claude-3.5-Sonnet

BoN@8 Accuracy: 60.4. Result ID: 69ba613447f34ce924a43901.

[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: 58.74. Result ID: 69ba613447f34ce924a4390a.

[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.

### InternVL2.5-38B + VisualPRM

BoN@8 Accuracy: 53.7. Result ID: 69ba613447f34ce924a43909.

[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.

### GPT-4o

BoN@8 Accuracy: 52.8. Result ID: 69ba613447f34ce924a438ff.

[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.

### Gemini-2.0-Flash

BoN@8 Accuracy: 52.3. Result ID: 69ba613447f34ce924a43900.

[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 + EVPV-PRM

BoN@8 Accuracy: 51.72. Result ID: 69ba613447f34ce924a43907.

[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.

### InternVL2.5-26B + VisualPRM

BoN@8 Accuracy: 51. Result ID: 69ba613447f34ce924a43906.

[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.

### InternVL2.5-38B

BoN@8 Accuracy: 47.9. Result ID: 69ba613447f34ce924a43908.

[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.

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

BoN@8 Accuracy: 45.33. Result ID: 69ba613447f34ce924a43904.

[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 + VisualPRM

BoN@8 Accuracy: 43.8. Result ID: 69ba613447f34ce924a43903.

[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: 39.64. Result ID: 69ba613447f34ce924a43905.

[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

BoN@8 Accuracy: 36.38. Result ID: 69ba613447f34ce924a43902.

[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.
