ADE20K
Models label the pixels in a scene by object or region. Meta measures overlap between predicted and reference segments.
- Released
- August 2016
- Kind
- Detection and captioning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Image, video and 3D generation
HRNetV2 tops the leaderboard with 62.3%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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 HRNetV2 Multi-scale testing 62.3%
- 2 UperNet101 Multi-scale testing 61.8%
- 3 ResNet101dilated + PPM_deepsup Multi-scale testing 61.7%
- 4 ResNet50dilated + PPM_deepsup Multi-scale testing 61.1%
- 5 UperNet50 Multi-scale testing 60.9%
- 6 ResNet18dilated + PPM_deepsup Multi-scale testing 59%
- 7 MobileNetV2dilated + PPM_deepsup Multi-scale testing 57.3%
- 8 ResNet18dilated + C1_deepsup Multi-scale testing 56.4%
- 9 MobileNetV2dilated + C1_deepsup Multi-scale testing 55.3%
Source: Official ADE20K leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | HRNetV2 | 62.3% | Multi-scale testing | Official leaderboard | |
| 2 | UperNet101 | 61.8% | Multi-scale testing | Official leaderboard | |
| 3 | ResNet101dilated + PPM_deepsup | 61.7% | Multi-scale testing | Official leaderboard | |
| 4 | ResNet50dilated + PPM_deepsup | 61.1% | Multi-scale testing | Official leaderboard | |
| 5 | UperNet50 | 60.9% | Multi-scale testing | Official leaderboard | |
| 6 | ResNet18dilated + PPM_deepsup | 59% | Multi-scale testing | Official leaderboard | |
| 7 | MobileNetV2dilated + PPM_deepsup | 57.3% | Multi-scale testing | Official leaderboard | |
| 8 | ResNet18dilated + C1_deepsup | 56.4% | Multi-scale testing | Official leaderboard | |
| 9 | MobileNetV2dilated + C1_deepsup | 55.3% | Multi-scale testing | 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 official leaderboard (9 entries).
- Pass Models scored 9 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 github.com: 9 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.