# Perception on HRbench 8K

Source: [Perception on HRbench 8K](<https://www.sota2.com/research/sota/perception-on-hrbench-8k>)

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

Data updated: 2026-05-20T09:24:16.632Z

Evaluation of general perception capabilities on the HRbench 8K dataset, measured using FSP, FCP, 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 | Perception |
| Dataset (including any stated split) | HRbench 8K |
| Metric | FSP |
| 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

- [FSP](<https://www.sota2.com/research/sota/perception-on-hrbench-8k.md?metric=FSP>): Higher is better; unit: PERCENT.

- [FCP](<https://www.sota2.com/research/sota/perception-on-hrbench-8k.md?metric=FCP>): Higher is better; unit: PERCENT.

- [Overall Score](<https://www.sota2.com/research/sota/perception-on-hrbench-8k.md?metric=Overall%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FSP | Result date | Report paper |
| --- | --- | --- | --- |
| ZoomEye | 88.5 | Not recorded | 6a0d402bf984739ed6737905 |
| AutoTool | 88 | Not recorded | 6a0d402bf984739ed6737905 |
| Qwen2.5-VL-32B | 85.8 | Not recorded | 6a0d402bf984739ed6737905 |
| DeepEyes | 85.5 | Not recorded | 6a0d402bf984739ed6737905 |
| Pixel-Reasoner | 80 | Not recorded | 6a0d402bf984739ed6737905 |
| Qwen2.5-VL-7B | 74 | Not recorded | 6a0d402bf984739ed6737905 |
| InternVL3-38B | 64.8 | Not recorded | 6a0d402bf984739ed6737905 |
| GPT-4o | 60.8 | Not recorded | 6a0d402bf984739ed6737905 |
| LLaVA-OneVision | 60.5 | Not recorded | 6a0d402bf984739ed6737905 |
| InternVL3-8B | 59 | Not recorded | 6a0d402bf984739ed6737905 |

### ZoomEye

FSP: 88.5. Result ID: 6a0d7cdcfbc373592c05cceb.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af51e209131cea85f9c.md>)

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

### AutoTool

FSP: 88. Result ID: 6a0d7cdcfbc373592c05ccee.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

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

### Qwen2.5-VL-32B

FSP: 85.8. Result ID: 6a0d7cdcfbc373592c05cce7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

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

Recorded evaluation configuration: {"Size":"32B"}. This record does not assert independent reproduction.

### DeepEyes

FSP: 85.5. Result ID: 6a0d7cdcfbc373592c05cced.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

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

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

### Pixel-Reasoner

FSP: 80. Result ID: 6a0d7cdcfbc373592c05ccec.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

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

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

### Qwen2.5-VL-7B

FSP: 74. Result ID: 6a0d7cdcfbc373592c05cce6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

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

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

### InternVL3-38B

FSP: 64.8. Result ID: 6a0d7cdcfbc373592c05cce9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Size":"38B"}. This record does not assert independent reproduction.

### GPT-4o

FSP: 60.8. Result ID: 6a0d7cdcfbc373592c05cce5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

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

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

Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction.

### LLaVA-OneVision

FSP: 60.5. Result ID: 6a0d7cdcfbc373592c05ccea.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

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

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

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

### InternVL3-8B

FSP: 59. Result ID: 6a0d7cdcfbc373592c05cce8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d402bf984739ed6737905.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction.

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