EuroSAT
Models classify land use and land cover in Sentinel-2 satellite images.
MTEB reports accuracy on its EuroSAT task.
- Made by
- Patrick Helber and colleagues
- Released
- August 2017
- Kind
- General visual questions
- Level
- University
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Subject
- Earth and environmental sciences
- Language
- English
- In and out
- Images, Maps and geodata → Text
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
QuanSun/EVA02-CLIP-bigE-14-plus tops the leaderboard with 93.9% EmbeddingGemma 2 leads with 83.6%
Best score per entry from MTEB’s 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. The best model we track is EmbeddingGemma 2, at 83.6%. This view shows only models we track, each at its best.
- 93.9 QuanSun/EVA02-CLIP-bigE-14-plus
- 93.4 QuanSun/EVA02-CLIP-bigE-14
- 92.4 laion/CLIP-ViT-H-14-laion2B-s32B-b79K
- 92.2 laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
- 91.8 laion/CLIP-ViT-g-14-laion2B-s34B-b88K
- 91.3 laion/CLIP-ViT-L-14-laion2B-s32B-b82K
- 90.3 BidirLM/BidirLM-Omni-2.5B-Embedding
- 89.6 google/siglip-large-patch16-384
- 89.5 nyu-visionx/moco-v3-vit-l
- 89.3 google/siglip-large-patch16-256
- 89.1 laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K
- 89.0 google/siglip-so400m-patch14-384
- 88.9 laion/CLIP-ViT-B-32-laion2B-s34B-b79K
- 88.8 laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K
- 88.7 nyu-visionx/moco-v3-vit-b
- 88.5 LanguageBind/LanguageBind_Omni
- 88.5 jinaai/jina-embeddings-v5-omni-small
- 88.2 encord-team/ebind-full
- 87.8 google/siglip-base-patch16-224
- 87.6 google/siglip-base-patch16-256
- 87.5 royokong/e5-v
- 87.4 google/siglip-base-patch16-256-multilingual
- 87.0 google/siglip-base-patch16-384
- 86.4 google/siglip-base-patch16-512
- 84.5 facebook/dinov2-giant
- 83.9 QuanSun/EVA02-CLIP-L-14
- 83.6
EmbeddingGemma 2
- 83.3 BAAI/bge-visualized-base
- 83.3 jinaai/jina-clip-v1
- 81.9 facebook/dinov2-small
- 81.7 facebook/dinov2-base
- 80.9 Salesforce/blip-itm-large-coco
- 80.9 Salesforce/blip-itm-base-coco
- 80.5 openai/clip-vit-large-patch14
- 80.2 facebook/dinov2-large
- 79.3 mongodb/voyage-multimodal-3
- 79.0 Salesforce/blip-itm-large-flickr
- 78.8 Salesforce/blip-itm-base-flickr
- 78.8 Salesforce/blip2-opt-2.7b
- 77.8 BAAI/bge-visualized-m3
- 77.6 laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K
- 77.1 QuanSun/EVA02-CLIP-B-16
- 76.9 Salesforce/blip2-opt-6.7b-coco
- 75.8 TIGER-Lab/VLM2Vec-Full
- 75.7 TIGER-Lab/VLM2Vec-LoRA
- 75.2 jinaai/jina-embeddings-v5-omni-nano
- 74.2 openai/clip-vit-base-patch16
- 73.9 dnotitia/DNA-VL-STEER-2B
- 71.9 LCO-Embedding/LCO-Embedding-Omni-7B
- 71.1 LCO-Embedding/LCO-Embedding-Omni-3B
- 70.2 Tevatron/OmniEmbed-v0.1
- 69.7 Haon-Chen/e5-omni-7B
- 67.2 openai/clip-vit-base-patch32
- 65.3 kakaobrain/align-base
- 60.6 Salesforce/blip-image-captioning-large
- 55.8 Haon-Chen/e5-omni-3B
- 53.3 Salesforce/blip-image-captioning-base
- 49.0 nomic-ai/nomic-embed-vision-v1.5
- 1 QuanSun/EVA02-CLIP-bigE-14-plus MTEB RGB classification 93.9%
- 2 QuanSun/EVA02-CLIP-bigE-14 MTEB RGB classification 93.4%
- 3 laion/CLIP-ViT-H-14-laion2B-s32B-b79K MTEB RGB classification 92.4%
- 4 laion/CLIP-ViT-bigG-14-laion2B-39B-b160k MTEB RGB classification 92.2%
- 5 laion/CLIP-ViT-g-14-laion2B-s34B-b88K MTEB RGB classification 91.8%
- 6 laion/CLIP-ViT-L-14-laion2B-s32B-b82K MTEB RGB classification 91.3%
- 7 BidirLM/BidirLM-Omni-2.5B-Embedding MTEB RGB classification 90.3%
- 8 google/siglip-large-patch16-384 MTEB RGB classification 89.6%
- 9 nyu-visionx/moco-v3-vit-l MTEB RGB classification 89.5%
- 10 google/siglip-large-patch16-256 MTEB RGB classification 89.3%
- 11 laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K MTEB RGB classification 89.1%
- 12 google/siglip-so400m-patch14-384 MTEB RGB classification 89%
- 13 laion/CLIP-ViT-B-32-laion2B-s34B-b79K MTEB RGB classification 88.9%
- 14 laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K MTEB RGB classification 88.8%
- 15 nyu-visionx/moco-v3-vit-b MTEB RGB classification 88.7%
- 16 LanguageBind/LanguageBind_Omni MTEB RGB classification 88.5%
- 17 jinaai/jina-embeddings-v5-omni-small MTEB RGB classification 88.5%
- 18 encord-team/ebind-full MTEB RGB classification 88.2%
- 19 google/siglip-base-patch16-224 MTEB RGB classification 87.8%
- 20 google/siglip-base-patch16-256 MTEB RGB classification 87.6%
- 21 royokong/e5-v MTEB RGB classification 87.5%
- 22 google/siglip-base-patch16-256-multilingual MTEB RGB classification 87.4%
- 23 google/siglip-base-patch16-384 MTEB RGB classification 87%
- 24 google/siglip-base-patch16-512 MTEB RGB classification 86.4%
- 25 facebook/dinov2-giant MTEB RGB classification 84.5%
- 26 QuanSun/EVA02-CLIP-L-14 MTEB RGB classification 83.9%
- 27
EmbeddingGemma 2 MTEB RGB classification 83.6%
- 28 BAAI/bge-visualized-base MTEB RGB classification 83.3%
- 29 jinaai/jina-clip-v1 MTEB RGB classification 83.3%
- 30 facebook/dinov2-small MTEB RGB classification 81.9%
- 31 facebook/dinov2-base MTEB RGB classification 81.7%
- 32 Salesforce/blip-itm-large-coco MTEB RGB classification 80.9%
- 33 Salesforce/blip-itm-base-coco MTEB RGB classification 80.9%
- 34 openai/clip-vit-large-patch14 MTEB RGB classification 80.5%
- 35 facebook/dinov2-large MTEB RGB classification 80.2%
- 36 mongodb/voyage-multimodal-3 MTEB RGB classification 79.3%
- 37 Salesforce/blip-itm-large-flickr MTEB RGB classification 79%
- 38 Salesforce/blip-itm-base-flickr MTEB RGB classification 78.8%
- 39 Salesforce/blip2-opt-2.7b MTEB RGB classification 78.8%
- 40 BAAI/bge-visualized-m3 MTEB RGB classification 77.8%
- 41 laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K MTEB RGB classification 77.6%
- 42 QuanSun/EVA02-CLIP-B-16 MTEB RGB classification 77.1%
- 43 Salesforce/blip2-opt-6.7b-coco MTEB RGB classification 76.9%
- 44 TIGER-Lab/VLM2Vec-Full MTEB RGB classification 75.8%
- 45 TIGER-Lab/VLM2Vec-LoRA MTEB RGB classification 75.7%
- 46 jinaai/jina-embeddings-v5-omni-nano MTEB RGB classification 75.2%
- 47 openai/clip-vit-base-patch16 MTEB RGB classification 74.2%
- 48 dnotitia/DNA-VL-STEER-2B MTEB RGB classification 73.9%
- 49 LCO-Embedding/LCO-Embedding-Omni-7B MTEB RGB classification 71.9%
- 50 LCO-Embedding/LCO-Embedding-Omni-3B MTEB RGB classification 71.1%
- 51 Tevatron/OmniEmbed-v0.1 MTEB RGB classification 70.2%
- 52 Haon-Chen/e5-omni-7B MTEB RGB classification 69.7%
- 53 openai/clip-vit-base-patch32 MTEB RGB classification 67.2%
- 54 kakaobrain/align-base MTEB RGB classification 65.3%
- 55 Salesforce/blip-image-captioning-large MTEB RGB classification 60.6%
- 56 Haon-Chen/e5-omni-3B MTEB RGB classification 55.8%
- 57 Salesforce/blip-image-captioning-base MTEB RGB classification 53.3%
- 58 nomic-ai/nomic-embed-vision-v1.5 MTEB RGB classification 49%
Source: MTEB’s leaderboard
Source: MTEB’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | QuanSun/EVA02-CLIP-bigE-14-plus open weights, 5B | 93.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 2 | QuanSun/EVA02-CLIP-bigE-14 open weights, 4.7B | 93.4% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 3 | laion/CLIP-ViT-H-14-laion2B-s32B-b79K open weights, 1B | 92.4% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 4 | laion/CLIP-ViT-bigG-14-laion2B-39B-b160k open weights, 2.5B | 92.2% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 5 | laion/CLIP-ViT-g-14-laion2B-s34B-b88K open weights, 1.4B | 91.8% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 6 | laion/CLIP-ViT-L-14-laion2B-s32B-b82K open weights, 0.4B | 91.3% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 7 | BidirLM/BidirLM-Omni-2.5B-Embedding open weights, 2.4B | 90.3% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 8 | google/siglip-large-patch16-384 open weights, 0.7B | 89.6% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 9 | nyu-visionx/moco-v3-vit-l open weights, 0.3B | 89.5% | MTEB RGB classification | github.com | Official leaderboard | |
| 10 | google/siglip-large-patch16-256 open weights, 0.7B | 89.3% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 11 | laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K open weights, 0.2B | 89.1% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 12 | google/siglip-so400m-patch14-384 open weights, 0.9B | 89% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 13 | laion/CLIP-ViT-B-32-laion2B-s34B-b79K open weights, 0.2B | 88.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 14 | laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K open weights, 0.2B | 88.8% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 15 | nyu-visionx/moco-v3-vit-b open weights, 0.1B | 88.7% | MTEB RGB classification | github.com | Official leaderboard | |
| 16 | LanguageBind/LanguageBind_Omni open weights, 1.2B | 88.5% | MTEB RGB classification | github.com | Official leaderboard | |
| 17 | jinaai/jina-embeddings-v5-omni-small open weights, 1.6B | 88.5% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 18 | encord-team/ebind-full open weights, 1.8B | 88.2% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 19 | google/siglip-base-patch16-224 open weights, 0.2B | 87.8% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 20 | google/siglip-base-patch16-256 open weights, 0.2B | 87.6% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 21 | royokong/e5-v open weights, 8.4B | 87.5% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 22 | google/siglip-base-patch16-256-multilingual open weights, 0.4B | 87.4% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 23 | google/siglip-base-patch16-384 open weights, 0.2B | 87% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 24 | google/siglip-base-patch16-512 open weights, 0.2B | 86.4% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 25 | facebook/dinov2-giant open weights, 1.1B | 84.5% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 26 | QuanSun/EVA02-CLIP-L-14 open weights, 0.4B | 83.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 27 | | 83.6% | MTEB RGB classification | Oct 2026 | huggingface.co | Official leaderboard |
| 28 | BAAI/bge-visualized-base open weights, 0.2B | 83.3% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 29 | jinaai/jina-clip-v1 open weights, 0.2B | 83.3% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 30 | facebook/dinov2-small open weights, 0B | 81.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 31 | facebook/dinov2-base open weights, 0.1B | 81.7% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 32 | Salesforce/blip-itm-large-coco open weights, 0.4B | 80.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 33 | Salesforce/blip-itm-base-coco open weights, 0.2B | 80.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 34 | openai/clip-vit-large-patch14 open weights, 0.4B | 80.5% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 35 | facebook/dinov2-large open weights, 0.3B | 80.2% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 36 | mongodb/voyage-multimodal-3 closed weights | 79.3% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 37 | Salesforce/blip-itm-large-flickr open weights, 0.4B | 79% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 38 | Salesforce/blip-itm-base-flickr open weights, 0.2B | 78.8% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 39 | Salesforce/blip2-opt-2.7b open weights, 3.7B | 78.8% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 40 | BAAI/bge-visualized-m3 open weights, 0.9B | 77.8% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 41 | laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K open weights, 0.4B | 77.6% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 42 | QuanSun/EVA02-CLIP-B-16 open weights, 0.1B | 77.1% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 43 | Salesforce/blip2-opt-6.7b-coco open weights, 7.8B | 76.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 44 | TIGER-Lab/VLM2Vec-Full open weights, 4.1B | 75.8% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 45 | TIGER-Lab/VLM2Vec-LoRA open weights, 4.2B | 75.7% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 46 | jinaai/jina-embeddings-v5-omni-nano open weights, 1B | 75.2% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 47 | openai/clip-vit-base-patch16 open weights, 0.2B | 74.2% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 48 | dnotitia/DNA-VL-STEER-2B open weights, 2.1B | 73.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 49 | LCO-Embedding/LCO-Embedding-Omni-7B open weights, 8.9B | 71.9% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 50 | LCO-Embedding/LCO-Embedding-Omni-3B open weights, 4.7B | 71.1% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 51 | Tevatron/OmniEmbed-v0.1 open weights, 8.9B | 70.2% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 52 | Haon-Chen/e5-omni-7B open weights, 8.9B | 69.7% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 53 | openai/clip-vit-base-patch32 open weights, 0.2B | 67.2% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 54 | kakaobrain/align-base open weights, 0.2B | 65.3% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 55 | Salesforce/blip-image-captioning-large open weights, 0.4B | 60.6% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 56 | Haon-Chen/e5-omni-3B open weights, 4.7B | 55.8% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 57 | Salesforce/blip-image-captioning-base open weights, 0.2B | 53.3% | MTEB RGB classification | huggingface.co | Official leaderboard | |
| 58 | nomic-ai/nomic-embed-vision-v1.5 open weights, 0.1B | 49% | MTEB RGB classification | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 83.6% | MTEB RGB classification | Oct 2026 | huggingface.co | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: MTEB’s 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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (58 entries).
- Pass Models scored 1 model we track, plus 57 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for EmbeddingGemma 2.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 83.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on MTEB: 1 row for models we track and 57 other entries at the last read.
- 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.