# High-Resolution Perception on V\*-Bench v1.0 (test)

Source: [High-Resolution Perception on V\*-Bench v1.0 (test)](<https://www.sota2.com/research/sota/high-resolution-perception-on-v-bench-v1-0-test>)

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

Data updated: 2026-03-30T07:39:39.404Z

Evaluation of model performance on the test split of V\*-Bench v1.0, focusing on High-Resolution Perception capabilities, measured by Attribute, Spatial, and Overall scores.

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 | High-Resolution Perception |
| Dataset (including any stated split) | V\*-Bench v1.0 (test) |
| Metric | Overall Score |
| 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

- [Overall Score](<https://www.sota2.com/research/sota/high-resolution-perception-on-v-bench-v1-0-test.md?metric=Overall%20Score>): Higher is better; unit: PERCENT.

- [Attribute Score](<https://www.sota2.com/research/sota/high-resolution-perception-on-v-bench-v1-0-test.md?metric=Attribute%20Score>): Higher is better; unit: PERCENT.

- [Spatial Score](<https://www.sota2.com/research/sota/high-resolution-perception-on-v-bench-v1-0-test.md?metric=Spatial%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall Score | Result date | Report paper |
| --- | --- | --- | --- |
| VRE | 83.8 | Not recorded | 69ca03710636e5bf4afc92b1 |
| Thyme | 82.2 | Not recorded | 69ca03710636e5bf4afc92b1 |
| DeepEyesV2 | 81.8 | Not recorded | 69ca03710636e5bf4afc92b1 |
| Qwen2.5-VL | 81.2 | Not recorded | 69ca03710636e5bf4afc92b1 |
| DyFo | 81.2 | Not recorded | 69ca03710636e5bf4afc92b1 |
| Semantic-back | 79.6 | Not recorded | 69ca03710636e5bf4afc92b1 |
| GPT-4o | 79.5 | Not recorded | 69ca03710636e5bf4afc92b1 |
| Qwen2.5-VL | 76.4 | Not recorded | 69ca03710636e5bf4afc92b1 |
| LLaVA-OneVision | 75.4 | Not recorded | 69ca03710636e5bf4afc92b1 |
| SEAL | 75.4 | Not recorded | 69ca03710636e5bf4afc92b1 |

### VRE

Overall Score: 83.8. Result ID: 69ca284047f34ce924b27abe.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

Recorded evaluation configuration: {"Tool Use":"No","Param Size":"7B"}. This record does not assert independent reproduction.

### Thyme

Overall Score: 82.2. Result ID: 69ca284047f34ce924b27abc.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

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

Recorded evaluation configuration: {"Tool Use":"Yes","Param Size":"7B"}. This record does not assert independent reproduction.

### DeepEyesV2

Overall Score: 81.8. Result ID: 69ca284047f34ce924b27abb.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691171652828b7cc6937d492.md>)

[Implementation](<https://github.com/Visual-Agent/DeepEyes>)

Recorded evaluation configuration: {"Tool Use":"Yes","Param Size":"7B"}. This record does not assert independent reproduction.

### Qwen2.5-VL

Overall Score: 81.2. Result ID: 69ca284047f34ce924b27ab8.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

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

Recorded evaluation configuration: {"Tool Use":"No","Param Size":"32B"}. This record does not assert independent reproduction.

### DyFo

Overall Score: 81.2. Result ID: 69ca284047f34ce924b27aba.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78191e209131cea76c8b.md>)

Recorded evaluation configuration: {"Tool Use":"Yes","Param Size":"7B"}. This record does not assert independent reproduction.

### Semantic-back

Overall Score: 79.6. Result ID: 69ca284047f34ce924b27abd.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79dc1e209131cea7fcc2.md>)

Recorded evaluation configuration: {"Tool Use":"No","Param Size":"7B"}. This record does not assert independent reproduction.

### GPT-4o

Overall Score: 79.5. Result ID: 69ca284047f34ce924b27ab5.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Tool Use":"No","Param Size":"-"}. This record does not assert independent reproduction.

### Qwen2.5-VL

Overall Score: 76.4. Result ID: 69ca284047f34ce924b27ab7.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

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

Recorded evaluation configuration: {"Tool Use":"No","Param Size":"7B"}. This record does not assert independent reproduction.

### LLaVA-OneVision

Overall Score: 75.4. Result ID: 69ca284047f34ce924b27ab6.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

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

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

Recorded evaluation configuration: {"Tool Use":"No","Param Size":"7B"}. This record does not assert independent reproduction.

### SEAL

Overall Score: 75.4. Result ID: 69ca284047f34ce924b27ab9.

[Reporting paper](<https://www.sota2.com/research/paper/69ca03710636e5bf4afc92b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ac1e209131cea52781.md>)

Recorded evaluation configuration: {"Tool Use":"Yes","Param Size":"7B"}. This record does not assert independent reproduction.

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