# General perception on MMVP

Source: [General perception on MMVP](<https://www.sota2.com/research/sota/general-perception-on-mmvp>)

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

Data updated: 2026-07-08T07:13:02.681Z

Evaluation of model performance on the MMVP dataset focusing on general perception capabilities.

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 | General perception |
| Dataset (including any stated split) | MMVP |
| Metric | General Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [General Score](<https://www.sota2.com/research/sota/general-perception-on-mmvp.md?metric=General%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | General Score | Result date | Report paper |
| --- | --- | --- | --- |
| SegAnswer | 72.3 | Not recorded | 6a4dd9b84da6617fe9198c9d |
| DeepEyes | 71.3 | Not recorded | 6a4dd9b84da6617fe9198c9d |
| Pixel Reasoner | 71.1 | Not recorded | 6a4dd9b84da6617fe9198c9d |
| Qwen2.5-VL-7B | 70.7 | Not recorded | 6a4dd9b84da6617fe9198c9d |
| LLaVA-OneVision-9B | 67.8 | Not recorded | 6a4dd9b84da6617fe9198c9d |

### SegAnswer

General Score: 72.3. Result ID: 6a4df86f60b88bb339d6dcb2.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b84da6617fe9198c9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4dd9b84da6617fe9198c9d.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction.

### DeepEyes

General Score: 71.3. Result ID: 6a4df86f60b88bb339d6dcb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b84da6617fe9198c9d.md>)

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

Recorded evaluation configuration: {"Evaluation protocol":"Re-evaluated using its official model and evaluation code"}. This record does not assert independent reproduction.

### Pixel Reasoner

General Score: 71.1. Result ID: 6a4df86f60b88bb339d6dcb0.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b84da6617fe9198c9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a774.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Re-evaluated using its official model and evaluation code"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

General Score: 70.7. Result ID: 6a4df86f60b88bb339d6dcaf.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b84da6617fe9198c9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Re-evaluated using its official model and evaluation code"}. This record does not assert independent reproduction.

### LLaVA-OneVision-9B

General Score: 67.8. Result ID: 6a4df86f60b88bb339d6dcae.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b84da6617fe9198c9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e58.md>)

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

Recorded evaluation configuration: {"Evaluation protocol":"Re-evaluated using its official model and evaluation code"}. This record does not assert independent reproduction.

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