Natural Adversarial Objects
Models identify objects in unmodified photographs that caused errors in earlier detectors. Human annotations identify the objects.
The collection contains 9,943 annotated objects in 7,934 photographs.
- Made by
- Felix Lau and colleagues with Scale AI
- Released
- November 2021
- Kind
- Detection and captioning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
Mask RCNN R50 tops the leaderboard with 15.2%
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 Mask RCNN R50 15.2%
- 2 EfficientDet-D4 15%
- 3 EfficientDet-D7 13.6%
- 4 Faster RCNN 13.5%
- 5 EfficientDet-D2 12.8%
- 6 RetinaNet-R50 11.1%
- 7 YOLOv3 10%
Source: The Natural Adversarial Objects paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Mask RCNN R50 0B | 15.2% | Official leaderboard | ||
| 2 | EfficientDet-D4 0B | 15% | Official leaderboard | ||
| 3 | EfficientDet-D7 0.1B | 13.6% | Official leaderboard | ||
| 4 | Faster RCNN 0B | 13.5% | Official leaderboard | ||
| 5 | EfficientDet-D2 0B | 12.8% | Official leaderboard | ||
| 6 | RetinaNet-R50 0B | 11.1% | Official leaderboard | ||
| 7 | YOLOv3 0.1B | 10% | 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 (7 entries).
- Pass Models scored 7 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 labs.scale.com: 7 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.