# Object Detection on DOTA v2 (val)

Source: [Object Detection on DOTA v2 (val)](<https://www.sota2.com/research/sota/object-detection-on-dota-v2-val>)

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

Data updated: 2026-03-11T09:03:29.705Z

Evaluation of Object Detection performance on the validation split of the DOTA v2 dataset, reporting mIoU and mAP@50.

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 | Object Detection |
| Dataset (including any stated split) | DOTA v2 (val) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [mIoU](<https://www.sota2.com/research/sota/object-detection-on-dota-v2-val.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [mAP@50](<https://www.sota2.com/research/sota/object-detection-on-dota-v2-val.md?metric=mAP%4050>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| GeoSolver | 0.5347 | Not recorded | 69b0f72e2d603e6de3e45fb4 |
| GLM-4.1V-Thinking | 0.4045 | Not recorded | 69b0f72e2d603e6de3e45fb4 |
| Gemini-2.0-flash | 0.143 | Not recorded | 69b0f72e2d603e6de3e45fb4 |
| ChatGPT-5 | 0.0866 | Not recorded | 69b0f72e2d603e6de3e45fb4 |
| SkySenseGPT | 0.0456 | Not recorded | 69b0f72e2d603e6de3e45fb4 |
| Claude-sonnet-4 | 0.0389 | Not recorded | 69b0f72e2d603e6de3e45fb4 |
| EarthDial | 0.0352 | Not recorded | 69b0f72e2d603e6de3e45fb4 |
| VHM | 0.0237 | Not recorded | 69b0f72e2d603e6de3e45fb4 |

### GeoSolver

mIoU: 0.5347. Result ID: 69b12fdb6dbb7075b95bc620.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

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

### GLM-4.1V-Thinking

mIoU: 0.4045. Result ID: 69b12fdb6dbb7075b95bc61c.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aaf1e209131cea849ba.md>)

Recorded evaluation configuration: {"Model Category":"Open-source Reasoning Vision-Language Models"}. This record does not assert independent reproduction.

### Gemini-2.0-flash

mIoU: 0.143. Result ID: 69b12fdb6dbb7075b95bc61a.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: {"Model Category":"Closed-source Commercial Vision-Language Models"}. This record does not assert independent reproduction.

### ChatGPT-5

mIoU: 0.0866. Result ID: 69b12fdb6dbb7075b95bc61b.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

Recorded evaluation configuration: {"Model Category":"Closed-source Commercial Vision-Language Models"}. This record does not assert independent reproduction.

### SkySenseGPT

mIoU: 0.0456. Result ID: 69b12fdb6dbb7075b95bc61e.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73fe1e209131cea5f150.md>)

Recorded evaluation configuration: {"Model Category":"Open-source Remote Sensing Vision-Language Models"}. This record does not assert independent reproduction.

### Claude-sonnet-4

mIoU: 0.0389. Result ID: 69b12fdb6dbb7075b95bc619.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

Recorded evaluation configuration: {"Model Category":"Closed-source Commercial Vision-Language Models"}. This record does not assert independent reproduction.

### EarthDial

mIoU: 0.0352. Result ID: 69b12fdb6dbb7075b95bc61f.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

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

Recorded evaluation configuration: {"Model Category":"Open-source Remote Sensing Vision-Language Models"}. This record does not assert independent reproduction.

### VHM

mIoU: 0.0237. Result ID: 69b12fdb6dbb7075b95bc61d.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72e2d603e6de3e45fb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76541e209131cea6c716.md>)

Recorded evaluation configuration: {"Model Category":"Open-source Remote Sensing Vision-Language Models"}. This record does not assert independent reproduction.

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