LoveDA
Models label land cover in aerial images of urban and rural areas. The benchmark supports comparisons across these two settings.
- Made by
- Junjue Wang and colleagues
- Released
- October 2021
- Kind
- Detection and captioning
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Earth and environmental sciences
- In and out
- Images, Maps and geodata → Images
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Image, video and 3D generation
HRNet tops the leaderboard with 52.1%
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 HRNet W32, multi-scale training and testing 52.1%
- 2 Semantic-FPN ResNet50, multi-scale training and testing 51.8%
- 3 DeepLabV3+ ResNet50, multi-scale training and testing 51.2%
- 4 UNet ResNet50, multi-scale training and testing 51.1%
- 5 FactSeg ResNet50 48.9%
- 6 LinkNet ResNet50 48.5%
- 7 PSPNet ResNet50 48.3%
- 8 UNet++ ResNet50 48.2%
- 9 FarSeg ResNet50 48.1%
- 10 PAN ResNet50 47.1%
- 11 FCN8S VGG16 46.7%
Source: The LoveDA paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | HRNet | 52.1% | W32, multi-scale training and testing | Official leaderboard | |
| 2 | Semantic-FPN | 51.8% | ResNet50, multi-scale training and testing | Official leaderboard | |
| 3 | DeepLabV3+ | 51.2% | ResNet50, multi-scale training and testing | Official leaderboard | |
| 4 | UNet | 51.1% | ResNet50, multi-scale training and testing | Official leaderboard | |
| 5 | FactSeg | 48.9% | ResNet50 | Official leaderboard | |
| 6 | LinkNet | 48.5% | ResNet50 | Official leaderboard | |
| 7 | PSPNet | 48.3% | ResNet50 | Official leaderboard | |
| 8 | UNet++ | 48.2% | ResNet50 | Official leaderboard | |
| 9 | FarSeg | 48.1% | ResNet50 | Official leaderboard | |
| 10 | PAN | 47.1% | ResNet50 | Official leaderboard | |
| 11 | FCN8S | 46.7% | VGG16 | Official leaderboard |
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (11 entries).
- Pass Models scored 11 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 11 entries at the last read, none a model we track.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.