# Visual Reasoning with Tool Use on V\*

Source: [Visual Reasoning with Tool Use on V\*](<https://www.sota2.com/research/sota/visual-reasoning-with-tool-use-on-v>)

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

Data updated: 2026-03-04T12:26:42.960Z

Evaluation of model performance on the V\* dataset for Visual Reasoning capabilities that specifically require Tool Use, measured by Accuracy and Faithfulness.

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 Reasoning with Tool Use |
| Dataset (including any stated split) | V\* |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/visual-reasoning-with-tool-use-on-v.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Faithfulness](<https://www.sota2.com/research/sota/visual-reasoning-with-tool-use-on-v.md?metric=Faithfulness>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DeepEyes-7B | 84.8 | Not recorded | 692689e9d6b0dd33429306bb |
| CodeV-7B-RL | 84.8 | Not recorded | 692689e9d6b0dd33429306bb |
| Thyme-RL-7B | 82.7 | Not recorded | 692689e9d6b0dd33429306bb |
| Pixel-Reasoner-7B | 79.6 | Not recorded | 692689e9d6b0dd33429306bb |

### DeepEyes-7B

Accuracy: 84.8. Result ID: 69a824ed6dbb7075b94e46ed.

[Reporting paper](<https://www.sota2.com/research/paper/692689e9d6b0dd33429306bb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a75e.md>)

Recorded evaluation configuration: {"Backbone":"7B"}. This record does not assert independent reproduction.

### CodeV-7B-RL

Accuracy: 84.8. Result ID: 69a824ed6dbb7075b94e46f0.

[Reporting paper](<https://www.sota2.com/research/paper/692689e9d6b0dd33429306bb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689e9d6b0dd33429306bb.md>)

[Implementation](<https://github.com/renlyh/CodeV>)

Recorded evaluation configuration: {"Backbone":"7B","Training":"RL"}. This record does not assert independent reproduction.

### Thyme-RL-7B

Accuracy: 82.7. Result ID: 69a824ed6dbb7075b94e46ef.

[Reporting paper](<https://www.sota2.com/research/paper/692689e9d6b0dd33429306bb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa21e209131cea84434.md>)

Recorded evaluation configuration: {"Backbone":"7B","Training":"RL"}. This record does not assert independent reproduction.

### Pixel-Reasoner-7B

Accuracy: 79.6. Result ID: 69a824ed6dbb7075b94e46ee.

[Reporting paper](<https://www.sota2.com/research/paper/692689e9d6b0dd33429306bb.md>)

Recorded evaluation configuration: {"Backbone":"7B"}. This record does not assert independent reproduction.

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