# Visual Question Answering on RSVQA-LRBEN

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

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

Data updated: 2026-02-27T11:28:59.355Z

Evaluation of model performance on the RSVQA-LRBEN dataset for Visual Question Answering, reporting scores across specific categories such as Presence, Comparison, and Rural/Urban.

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-LRBEN |
| Metric | Presence |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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](<https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-lrben.md?metric=Presence>): Higher is better; unit: PERCENT.

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

- [Rural/Urban Score](<https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-lrben.md?metric=Rural%2FUrban%20Score>): Higher is better; unit: PERCENT.

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

- [Friedman Ranking Score](<https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-lrben.md?metric=Friedman%20Ranking%20Score>): Higher is better; unit: SCALAR.

- [Rank](<https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-lrben.md?metric=Rank>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Presence | Result date | Report paper |
| --- | --- | --- | --- |
| GeoChat | 91.09 | Not recorded | 6955ff5753fdd5c36173dd04 |
| MF-RSVLM | 90.21 | Not recorded | 6955ff5753fdd5c36173dd04 |
| SkyEyeGPT | 88.63 | Not recorded | 6955ff5753fdd5c36173dd04 |
| RSVQA | 87.47 | Not recorded | 6955ff5753fdd5c36173dd04 |
| InternVL2 | 58.54 | Not recorded | 6955ff5753fdd5c36173dd04 |
| LLaVA-1.5 | 55.46 | Not recorded | 6955ff5753fdd5c36173dd04 |
| MiniGPT-v2 | 55.16 | Not recorded | 6955ff5753fdd5c36173dd04 |
| Qwen-VL | 38.57 | Not recorded | 6955ff5753fdd5c36173dd04 |
| Qwen-VL-Chat | 38.57 | Not recorded | 6955ff5753fdd5c36173dd04 |

### GeoChat

Presence: 91.09. Result ID: 69a17fee35dfcabb00e77313.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MF-RSVLM

Presence: 90.21. Result ID: 69a17fee35dfcabb00e77318.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SkyEyeGPT

Presence: 88.63. Result ID: 69a17fee35dfcabb00e77317.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d61e209131cea53400.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RSVQA

Presence: 87.47. Result ID: 69a17fee35dfcabb00e77316.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67911e209131cea1710a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### InternVL2

Presence: 58.54. Result ID: 69a17fee35dfcabb00e77312.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LLaVA-1.5

Presence: 55.46. Result ID: 69a17fee35dfcabb00e77314.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MiniGPT-v2

Presence: 55.16. Result ID: 69a17fee35dfcabb00e77310.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7e5.md>)

[Implementation](<https://minigpt-v2.github.io/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen-VL

Presence: 38.57. Result ID: 69a17fee35dfcabb00e77311.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen-VL-Chat

Presence: 38.57. Result ID: 69a17fee35dfcabb00e77315.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff5753fdd5c36173dd04.md>)

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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