DIOR-RSVG
Models draw a box around the object named in a description of an aerial image. The released test split contains 7,500 descriptions.
The VLEO-Bench authors tested GPT-4V and Qwen-VL-Chat on object localization. The LGFormer authors also reported accuracy at five box overlap thresholds.
- Released
- October 2022
- Kind
- Detection and captioning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- In and out
- Text, Images, Maps and geodata → Text
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- DIOR
- In views
- Vision
MGVLF tops the leaderboard with 76.8%
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 MGVLF ResNet-50 + BERT 76.8%
- 2 VLTVG ResNet-101 + BERT 75.8%
- 3 LBYL-Net DarkNet-53 + BERT 73.8%
- 4 ReSC DarkNet-53 + BERT 72.7%
- 5 TransVG ResNet-50 + BERT 72.4%
- 6 FAOA DarkNet-53 + LSTM 70.9%
- 7 FAOA-no Spatial DarkNet-53 + BERT 63.6%
- 8 ZSGNet ResNet-50 + BiLSTM 51.7%
Source: The DIOR-RSVG paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | MGVLF | 76.8% | ResNet-50 + BERT | Official leaderboard | |
| 2 | VLTVG | 75.8% | ResNet-101 + BERT | Official leaderboard | |
| 3 | LBYL-Net | 73.8% | DarkNet-53 + BERT | Official leaderboard | |
| 4 | ReSC | 72.7% | DarkNet-53 + BERT | Official leaderboard | |
| 5 | TransVG | 72.4% | ResNet-50 + BERT | Official leaderboard | |
| 6 | FAOA | 70.9% | DarkNet-53 + LSTM | Official leaderboard | |
| 7 | FAOA-no Spatial | 63.6% | DarkNet-53 + BERT | Official leaderboard | |
| 8 | ZSGNet | 51.7% | ResNet-50 + BiLSTM | 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 (8 entries).
- Pass Models scored 8 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: 8 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.