Food-101
Models identify the dish in a food photograph from 101 categories.
MTEB reports accuracy on its Food101Classification task.
- Made by
- ETH Zurich
- Released
- September 2014
- 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
- One fixed set
- Run by
- Anyone
- In views
- Vision
google/siglip-so400m-patch14-384 tops the leaderboard with 95.5%
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.
- 95.5 google/siglip-so400m-patch14-384
- 95.0 google/siglip-large-patch16-384
- 94.9 QuanSun/EVA02-CLIP-bigE-14-plus
- 94.7 QuanSun/EVA02-CLIP-bigE-14
- 93.6 google/siglip-large-patch16-256
- 92.7 laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K
- 92.7 google/siglip-base-patch16-512
- 92.5 laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
- 92.4 dnotitia/DNA-VL-STEER-2B
- 92.1 google/siglip-base-patch16-384
- 92.0 openai/clip-vit-large-patch14
- 91.1 laion/CLIP-ViT-g-14-laion2B-s34B-b88K
- 91.0 laion/CLIP-ViT-H-14-laion2B-s32B-b79K
- 90.3 google/siglip-base-patch16-256
- 90.2 QuanSun/EVA02-CLIP-L-14
- 90.0 google/siglip-base-patch16-256-multilingual
- 89.9 google/siglip-base-patch16-224
- 89.6 laion/CLIP-ViT-L-14-laion2B-s32B-b82K
- 88.9 jinaai/jina-embeddings-v5-omni-small
- 88.2 Salesforce/blip2-opt-2.7b
- 88.1 facebook/dinov2-giant
- 88.1 laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K
- 87.8 facebook/dinov2-large
- 87.4 mongodb/voyage-multimodal-3
- 86.9 nomic-ai/nomic-embed-vision-v1.5
- 86.5 openai/clip-vit-base-patch16
- 85.3 royokong/e5-v
- 84.4 facebook/dinov2-base
- 84.1 Salesforce/blip2-opt-6.7b-coco
- 84.1 BAAI/bge-visualized-base
- 82.7 kakaobrain/align-base
- 82.0 Salesforce/blip-itm-large-flickr
- 81.8 Salesforce/blip-itm-large-coco
- 81.5 laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K
- 80.8 QuanSun/EVA02-CLIP-B-16
- 80.4 BAAI/bge-visualized-m3
- 79.5 jinaai/jina-clip-v1
- 79.5 openai/clip-vit-base-patch32
- 78.8 laion/CLIP-ViT-B-32-laion2B-s34B-b79K
- 78.4 Salesforce/blip-image-captioning-large
- 77.7 facebook/dinov2-small
- 76.3 Salesforce/blip-itm-base-coco
- 74.7 TIGER-Lab/VLM2Vec-Full
- 74.7 TIGER-Lab/VLM2Vec-LoRA
- 74.5 Salesforce/blip-itm-base-flickr
- 69.5 jinaai/jina-embeddings-v5-omni-nano
- 68.6 Salesforce/blip-image-captioning-base
- 54.4 nyu-visionx/moco-v3-vit-l
- 50.5 nyu-visionx/moco-v3-vit-b
- 1 google/siglip-so400m-patch14-384 MTEB Food101Classification 95.5%
- 2 google/siglip-large-patch16-384 MTEB Food101Classification 95%
- 3 QuanSun/EVA02-CLIP-bigE-14-plus MTEB Food101Classification 94.9%
- 4 QuanSun/EVA02-CLIP-bigE-14 MTEB Food101Classification 94.7%
- 5 google/siglip-large-patch16-256 MTEB Food101Classification 93.6%
- 6 laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K MTEB Food101Classification 92.7%
- 7 google/siglip-base-patch16-512 MTEB Food101Classification 92.7%
- 8 laion/CLIP-ViT-bigG-14-laion2B-39B-b160k MTEB Food101Classification 92.5%
- 9 dnotitia/DNA-VL-STEER-2B MTEB Food101Classification 92.4%
- 10 google/siglip-base-patch16-384 MTEB Food101Classification 92.1%
- 11 openai/clip-vit-large-patch14 MTEB Food101Classification 92%
- 12 laion/CLIP-ViT-g-14-laion2B-s34B-b88K MTEB Food101Classification 91.1%
- 13 laion/CLIP-ViT-H-14-laion2B-s32B-b79K MTEB Food101Classification 91%
- 14 google/siglip-base-patch16-256 MTEB Food101Classification 90.3%
- 15 QuanSun/EVA02-CLIP-L-14 MTEB Food101Classification 90.2%
- 16 google/siglip-base-patch16-256-multilingual MTEB Food101Classification 90%
- 17 google/siglip-base-patch16-224 MTEB Food101Classification 89.9%
- 18 laion/CLIP-ViT-L-14-laion2B-s32B-b82K MTEB Food101Classification 89.6%
- 19 jinaai/jina-embeddings-v5-omni-small MTEB Food101Classification 88.9%
- 20 Salesforce/blip2-opt-2.7b MTEB Food101Classification 88.2%
- 21 facebook/dinov2-giant MTEB Food101Classification 88.1%
- 22 laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K MTEB Food101Classification 88.1%
- 23 facebook/dinov2-large MTEB Food101Classification 87.8%
- 24 mongodb/voyage-multimodal-3 MTEB Food101Classification 87.4%
- 25 nomic-ai/nomic-embed-vision-v1.5 MTEB Food101Classification 86.9%
- 26 openai/clip-vit-base-patch16 MTEB Food101Classification 86.5%
- 27 royokong/e5-v MTEB Food101Classification 85.3%
- 28 facebook/dinov2-base MTEB Food101Classification 84.4%
- 29 Salesforce/blip2-opt-6.7b-coco MTEB Food101Classification 84.1%
- 30 BAAI/bge-visualized-base MTEB Food101Classification 84.1%
- 31 kakaobrain/align-base MTEB Food101Classification 82.7%
- 32 Salesforce/blip-itm-large-flickr MTEB Food101Classification 82%
- 33 Salesforce/blip-itm-large-coco MTEB Food101Classification 81.8%
- 34 laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K MTEB Food101Classification 81.5%
- 35 QuanSun/EVA02-CLIP-B-16 MTEB Food101Classification 80.8%
- 36 BAAI/bge-visualized-m3 MTEB Food101Classification 80.4%
- 37 jinaai/jina-clip-v1 MTEB Food101Classification 79.5%
- 38 openai/clip-vit-base-patch32 MTEB Food101Classification 79.5%
- 39 laion/CLIP-ViT-B-32-laion2B-s34B-b79K MTEB Food101Classification 78.8%
- 40 Salesforce/blip-image-captioning-large MTEB Food101Classification 78.4%
- 41 facebook/dinov2-small MTEB Food101Classification 77.7%
- 42 Salesforce/blip-itm-base-coco MTEB Food101Classification 76.3%
- 43 TIGER-Lab/VLM2Vec-Full MTEB Food101Classification 74.7%
- 44 TIGER-Lab/VLM2Vec-LoRA MTEB Food101Classification 74.7%
- 45 Salesforce/blip-itm-base-flickr MTEB Food101Classification 74.5%
- 46 jinaai/jina-embeddings-v5-omni-nano MTEB Food101Classification 69.5%
- 47 Salesforce/blip-image-captioning-base MTEB Food101Classification 68.6%
- 48 nyu-visionx/moco-v3-vit-l MTEB Food101Classification 54.4%
- 49 nyu-visionx/moco-v3-vit-b MTEB Food101Classification 50.5%
Source: MTEB’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | google/siglip-so400m-patch14-384 open weights, 0.9B | 95.5% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 2 | google/siglip-large-patch16-384 open weights, 0.7B | 95% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 3 | QuanSun/EVA02-CLIP-bigE-14-plus open weights, 5B | 94.9% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 4 | QuanSun/EVA02-CLIP-bigE-14 open weights, 4.7B | 94.7% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 5 | google/siglip-large-patch16-256 open weights, 0.7B | 93.6% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 6 | laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K open weights, 0.4B | 92.7% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 7 | google/siglip-base-patch16-512 open weights, 0.2B | 92.7% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 8 | laion/CLIP-ViT-bigG-14-laion2B-39B-b160k open weights, 2.5B | 92.5% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 9 | dnotitia/DNA-VL-STEER-2B open weights, 2.1B | 92.4% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 10 | google/siglip-base-patch16-384 open weights, 0.2B | 92.1% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 11 | openai/clip-vit-large-patch14 open weights, 0.4B | 92% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 12 | laion/CLIP-ViT-g-14-laion2B-s34B-b88K open weights, 1.4B | 91.1% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 13 | laion/CLIP-ViT-H-14-laion2B-s32B-b79K open weights, 1B | 91% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 14 | google/siglip-base-patch16-256 open weights, 0.2B | 90.3% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 15 | QuanSun/EVA02-CLIP-L-14 open weights, 0.4B | 90.2% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 16 | google/siglip-base-patch16-256-multilingual open weights, 0.4B | 90% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 17 | google/siglip-base-patch16-224 open weights, 0.2B | 89.9% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 18 | laion/CLIP-ViT-L-14-laion2B-s32B-b82K open weights, 0.4B | 89.6% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 19 | jinaai/jina-embeddings-v5-omni-small open weights, 1.6B | 88.9% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 20 | Salesforce/blip2-opt-2.7b open weights, 3.7B | 88.2% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 21 | facebook/dinov2-giant open weights, 1.1B | 88.1% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 22 | laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K open weights, 0.2B | 88.1% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 23 | facebook/dinov2-large open weights, 0.3B | 87.8% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 24 | mongodb/voyage-multimodal-3 closed weights | 87.4% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 25 | nomic-ai/nomic-embed-vision-v1.5 open weights, 0.1B | 86.9% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 26 | openai/clip-vit-base-patch16 open weights, 0.2B | 86.5% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 27 | royokong/e5-v open weights, 8.4B | 85.3% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 28 | facebook/dinov2-base open weights, 0.1B | 84.4% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 29 | Salesforce/blip2-opt-6.7b-coco open weights, 7.8B | 84.1% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 30 | BAAI/bge-visualized-base open weights, 0.2B | 84.1% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 31 | kakaobrain/align-base open weights, 0.2B | 82.7% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 32 | Salesforce/blip-itm-large-flickr open weights, 0.4B | 82% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 33 | Salesforce/blip-itm-large-coco open weights, 0.4B | 81.8% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 34 | laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K open weights, 0.2B | 81.5% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 35 | QuanSun/EVA02-CLIP-B-16 open weights, 0.1B | 80.8% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 36 | BAAI/bge-visualized-m3 open weights, 0.9B | 80.4% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 37 | jinaai/jina-clip-v1 open weights, 0.2B | 79.5% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 38 | openai/clip-vit-base-patch32 open weights, 0.2B | 79.5% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 39 | laion/CLIP-ViT-B-32-laion2B-s34B-b79K open weights, 0.2B | 78.8% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 40 | Salesforce/blip-image-captioning-large open weights, 0.4B | 78.4% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 41 | facebook/dinov2-small open weights, 0B | 77.7% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 42 | Salesforce/blip-itm-base-coco open weights, 0.2B | 76.3% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 43 | TIGER-Lab/VLM2Vec-Full open weights, 4.1B | 74.7% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 44 | TIGER-Lab/VLM2Vec-LoRA open weights, 4.2B | 74.7% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 45 | Salesforce/blip-itm-base-flickr open weights, 0.2B | 74.5% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 46 | jinaai/jina-embeddings-v5-omni-nano open weights, 1B | 69.5% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 47 | Salesforce/blip-image-captioning-base open weights, 0.2B | 68.6% | MTEB Food101Classification | huggingface.co | Official leaderboard | |
| 48 | nyu-visionx/moco-v3-vit-l open weights, 0.3B | 54.4% | MTEB Food101Classification | github.com | Official leaderboard | |
| 49 | nyu-visionx/moco-v3-vit-b open weights, 0.1B | 50.5% | MTEB Food101Classification | github.com | 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 (49 entries).
- Pass Models scored 49 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 MTEB: 49 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.