# Visual Question Answering on RSVQA-HRBEN (test)

Source: [Visual Question Answering on RSVQA-HRBEN (test)](<https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-hrben-test>)

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

Data updated: 2026-02-27T10:21:37.796Z

Evaluation of Visual Question Answering performance on the test split of the RSVQA-HRBEN dataset, reporting scores for Presence, Comparison, and Average accuracy.

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 Question Answering |
| Dataset (including any stated split) | RSVQA-HRBEN (test) |
| Metric | Presence Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Presence Accuracy](<https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-hrben-test.md?metric=Presence%20Accuracy>): Higher is better; unit: PERCENT.

- [Comparison Accuracy](<https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-hrben-test.md?metric=Comparison%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-hrben-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Presence Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| InternVL2-8B | 67.35 | Not recorded | 68fa77e01e209131cea75bfc |
| Qwen-VL | 66.44 | Not recorded | 68fa77e01e209131cea75bfc |
| EarthGPT | 62.77 | Not recorded | 68fa77e01e209131cea75bfc |
| EarthDial | 58.89 | Not recorded | 68fa77e01e209131cea75bfc |
| GeoChat | 58.45 | Not recorded | 68fa77e01e209131cea75bfc |
| MiniGPTv2 | 40.79 | Not recorded | 68fa77e01e209131cea75bfc |

### InternVL2-8B

Presence Accuracy: 67.35. Result ID: 69a1701535dfcabb00e7063d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"Evaluation Mode":"Zero-Shot"}. This record does not assert independent reproduction.

### Qwen-VL

Presence Accuracy: 66.44. Result ID: 69a1701535dfcabb00e7063c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d41e209131cea4d774.md>)

[Implementation](<https://github.com/QwenLM/Qwen-VL>)

Recorded evaluation configuration: {"Evaluation Mode":"Zero-Shot"}. This record does not assert independent reproduction.

### EarthGPT

Presence Accuracy: 62.77. Result ID: 69a1701535dfcabb00e7063f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727b1e209131cea56a6b.md>)

Recorded evaluation configuration: {"Evaluation Mode":"Zero-Shot"}. This record does not assert independent reproduction.

### EarthDial

Presence Accuracy: 58.89. Result ID: 69a1701535dfcabb00e70640.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

Recorded evaluation configuration: {"Evaluation Mode":"Zero-Shot"}. This record does not assert independent reproduction.

### GeoChat

Presence Accuracy: 58.45. Result ID: 69a1701535dfcabb00e7063e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa714c1e209131cea50865.md>)

Recorded evaluation configuration: {"Evaluation Mode":"Zero-Shot"}. This record does not assert independent reproduction.

### MiniGPTv2

Presence Accuracy: 40.79. Result ID: 69a1701535dfcabb00e7063b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

Recorded evaluation configuration: {"Evaluation Mode":"Zero-Shot"}. This record does not assert independent reproduction.

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