Google Landmarks Dataset v2
Models recognize landmarks or retrieve photographs of the same landmark. The benchmark uses images from around the world.
- Made by
- Released
- April 2020
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- A version of another benchmark
- In views
- Vision
DELG global+SP tops the leaderboard with 41.5%
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of recognition micro-average precision and retrieval mAP@100. 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 DELG global+SP Trained on GLDv1-train 41.5%
- 2 DELF-ASMK*+SP Trained on GLDv1-train 38.5%
- 3 DELF-R-ASMK*+SP Trained on GLDv1-train 36.4%
- 4 DELF-R-ASMK* Trained on GLDv1-train 32.9%
- 5 ResNet101+ArcFace Trained on GLDv2-train-clean 27.1%
- 6 DELG global-only Trained on GLDv1-train 26.9%
- 7 DELF-ASMK* Trained on GLDv1-train 15.8%
Source: The Google Landmarks Dataset v2 paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | DELG global+SP | 41.5% | Trained on GLDv1-train | Official leaderboard | |
| 2 | DELF-ASMK*+SP | 38.5% | Trained on GLDv1-train | Official leaderboard | |
| 3 | DELF-R-ASMK*+SP | 36.4% | Trained on GLDv1-train | Official leaderboard | |
| 4 | DELF-R-ASMK* | 32.9% | Trained on GLDv1-train | Official leaderboard | |
| 5 | ResNet101+ArcFace | 27.1% | Trained on GLDv2-train-clean | Official leaderboard | |
| 6 | DELG global-only | 26.9% | Trained on GLDv1-train | Official leaderboard | |
| 7 | DELF-ASMK* | 15.8% | Trained on GLDv1-train | 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 arxiv.org: 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.