Benchmark Almanac

EDIS

dnotitia/DNA-VL-STEER-2B 0.34 tops its leaderboard
Not in model cards

Models retrieve news images and their associated text using queries that refer to specific people, places, or events.

MTEB reports nDCG at 10 on its EDIST2ITRetrieval task.

Made by
Siqi Liu and colleagues
Released
May 2023
Kind
General visual questions
Level
School
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Vision
43
Entries on MTEB’s leaderboard, 0 models we track

dnotitia/DNA-VL-STEER-2B tops the leaderboard with 0.34

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.

43 entries. Scroll sideways for the rest.

  1. 0.34 dnotitia/DNA-VL-STEER-2B
  2. 0.31 laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
  3. 0.31 mongodb/voyage-multimodal-3
  4. 0.30 laion/CLIP-ViT-g-14-laion2B-s34B-b88K
  5. 0.28 laion/CLIP-ViT-H-14-laion2B-s32B-b79K
  6. 0.26 laion/CLIP-ViT-L-14-laion2B-s32B-b82K
  7. 0.26 openai/clip-vit-large-patch14
  8. 0.25 openai/clip-vit-base-patch16
  9. 0.24 openai/clip-vit-base-patch32
  10. 0.24 laion/CLIP-ViT-B-32-laion2B-s34B-b79K
  11. 0.24 BAAI/bge-visualized-base
  12. 0.23 laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K
  13. 0.23 royokong/e5-v
  14. 0.22 jinaai/jina-clip-v1
  15. 0.22 BAAI/bge-visualized-m3
  16. 0.21 laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K
  17. 0.21 Salesforce/blip-itm-large-coco
  18. 0.21 nomic-ai/nomic-embed-vision-v1.5
  19. 0.20 laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K
  20. 0.19 Salesforce/blip-itm-large-flickr
  21. 0.18 Salesforce/blip-itm-base-coco
  22. 0.18 QuanSun/EVA02-CLIP-bigE-14-plus
  23. 0.17 QuanSun/EVA02-CLIP-L-14
  24. 0.16 TIGER-Lab/VLM2Vec-LoRA
  25. 0.16 TIGER-Lab/VLM2Vec-Full
  26. 0.16 Salesforce/blip-itm-base-flickr
  27. 0.15 QuanSun/EVA02-CLIP-bigE-14
  28. 0.15 QuanSun/EVA02-CLIP-B-16
  29. 0.15 google/siglip-large-patch16-256
  30. 0.14 google/siglip-large-patch16-384
  31. 0.14 jinaai/jina-embeddings-v5-omni-nano
  32. 0.13 jinaai/jina-embeddings-v5-omni-small
  33. 0.13 Salesforce/blip2-opt-2.7b
  34. 0.13 google/siglip-base-patch16-256
  35. 0.12 google/siglip-base-patch16-384
  36. 0.12 google/siglip-so400m-patch14-384
  37. 0.12 google/siglip-base-patch16-512
  38. 0.12 google/siglip-base-patch16-224
  39. 0.11 google/siglip-base-patch16-256-multilingual
  40. 0.10 kakaobrain/align-base
  41. 0.09 Salesforce/blip2-opt-6.7b-coco
  42. 0.00 Salesforce/blip-image-captioning-base
  43. 0.00 Salesforce/blip-image-captioning-large
  1. 1 dnotitia/DNA-VL-STEER-2B 0.34
  2. 2 laion/CLIP-ViT-bigG-14-laion2B-39B-b160k 0.31
  3. 3 mongodb/voyage-multimodal-3 0.31
  4. 4 laion/CLIP-ViT-g-14-laion2B-s34B-b88K 0.30
  5. 5 laion/CLIP-ViT-H-14-laion2B-s32B-b79K 0.28
  6. 6 laion/CLIP-ViT-L-14-laion2B-s32B-b82K 0.26
  7. 7 openai/clip-vit-large-patch14 0.26
  8. 8 openai/clip-vit-base-patch16 0.25
  9. 9 openai/clip-vit-base-patch32 0.24
  10. 10 laion/CLIP-ViT-B-32-laion2B-s34B-b79K 0.24
  11. 11 BAAI/bge-visualized-base 0.24
  12. 12 laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K 0.23
  13. 13 royokong/e5-v 0.23
  14. 14 jinaai/jina-clip-v1 0.22
  15. 15 BAAI/bge-visualized-m3 0.22
  16. 16 laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K 0.21
  17. 17 Salesforce/blip-itm-large-coco 0.21
  18. 18 nomic-ai/nomic-embed-vision-v1.5 0.21
  19. 19 laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K 0.20
  20. 20 Salesforce/blip-itm-large-flickr 0.19
  21. 21 Salesforce/blip-itm-base-coco 0.18
  22. 22 QuanSun/EVA02-CLIP-bigE-14-plus 0.18
  23. 23 QuanSun/EVA02-CLIP-L-14 0.17
  24. 24 TIGER-Lab/VLM2Vec-LoRA 0.16
  25. 25 TIGER-Lab/VLM2Vec-Full 0.16
  26. 26 Salesforce/blip-itm-base-flickr 0.16
  27. 27 QuanSun/EVA02-CLIP-bigE-14 0.15
  28. 28 QuanSun/EVA02-CLIP-B-16 0.15
  29. 29 google/siglip-large-patch16-256 0.15
  30. 30 google/siglip-large-patch16-384 0.14
  31. 31 jinaai/jina-embeddings-v5-omni-nano 0.14
  32. 32 jinaai/jina-embeddings-v5-omni-small 0.13
  33. 33 Salesforce/blip2-opt-2.7b 0.13
  34. 34 google/siglip-base-patch16-256 0.13
  35. 35 google/siglip-base-patch16-384 0.12
  36. 36 google/siglip-so400m-patch14-384 0.12
  37. 37 google/siglip-base-patch16-512 0.12
  38. 38 google/siglip-base-patch16-224 0.12
  39. 39 google/siglip-base-patch16-256-multilingual 0.11
  40. 40 kakaobrain/align-base 0.10
  41. 41 Salesforce/blip2-opt-6.7b-coco 0.09
  42. 42 Salesforce/blip-image-captioning-base 0.00
  43. 43 Salesforce/blip-image-captioning-large 0.00

Source: MTEB’s leaderboard

#EntryScoreSettingDateLinkSource
1 dnotitia/DNA-VL-STEER-2B open weights, 2.1B 0.34 huggingface.co Official leaderboard
2 laion/CLIP-ViT-bigG-14-laion2B-39B-b160k open weights, 2.5B 0.31 huggingface.co Official leaderboard
3 mongodb/voyage-multimodal-3 closed weights 0.31 huggingface.co Official leaderboard
4 laion/CLIP-ViT-g-14-laion2B-s34B-b88K open weights, 1.4B 0.30 huggingface.co Official leaderboard
5 laion/CLIP-ViT-H-14-laion2B-s32B-b79K open weights, 1B 0.28 huggingface.co Official leaderboard
6 laion/CLIP-ViT-L-14-laion2B-s32B-b82K open weights, 0.4B 0.26 huggingface.co Official leaderboard
7 openai/clip-vit-large-patch14 open weights, 0.4B 0.26 huggingface.co Official leaderboard
8 openai/clip-vit-base-patch16 open weights, 0.2B 0.25 huggingface.co Official leaderboard
9 openai/clip-vit-base-patch32 open weights, 0.2B 0.24 huggingface.co Official leaderboard
10 laion/CLIP-ViT-B-32-laion2B-s34B-b79K open weights, 0.2B 0.24 huggingface.co Official leaderboard
11 BAAI/bge-visualized-base open weights, 0.2B 0.24 huggingface.co Official leaderboard
12 laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K open weights, 0.4B 0.23 huggingface.co Official leaderboard
13 royokong/e5-v open weights, 8.4B 0.23 huggingface.co Official leaderboard
14 jinaai/jina-clip-v1 open weights, 0.2B 0.22 huggingface.co Official leaderboard
15 BAAI/bge-visualized-m3 open weights, 0.9B 0.22 huggingface.co Official leaderboard
16 laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K open weights, 0.2B 0.21 huggingface.co Official leaderboard
17 Salesforce/blip-itm-large-coco open weights, 0.4B 0.21 huggingface.co Official leaderboard
18 nomic-ai/nomic-embed-vision-v1.5 open weights, 0.1B 0.21 huggingface.co Official leaderboard
19 laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K open weights, 0.2B 0.20 huggingface.co Official leaderboard
20 Salesforce/blip-itm-large-flickr open weights, 0.4B 0.19 huggingface.co Official leaderboard
21 Salesforce/blip-itm-base-coco open weights, 0.2B 0.18 huggingface.co Official leaderboard
22 QuanSun/EVA02-CLIP-bigE-14-plus open weights, 5B 0.18 huggingface.co Official leaderboard
23 QuanSun/EVA02-CLIP-L-14 open weights, 0.4B 0.17 huggingface.co Official leaderboard
24 TIGER-Lab/VLM2Vec-LoRA open weights, 4.2B 0.16 huggingface.co Official leaderboard
25 TIGER-Lab/VLM2Vec-Full open weights, 4.1B 0.16 huggingface.co Official leaderboard
26 Salesforce/blip-itm-base-flickr open weights, 0.2B 0.16 huggingface.co Official leaderboard
27 QuanSun/EVA02-CLIP-bigE-14 open weights, 4.7B 0.15 huggingface.co Official leaderboard
28 QuanSun/EVA02-CLIP-B-16 open weights, 0.1B 0.15 huggingface.co Official leaderboard
29 google/siglip-large-patch16-256 open weights, 0.7B 0.15 huggingface.co Official leaderboard
30 google/siglip-large-patch16-384 open weights, 0.7B 0.14 huggingface.co Official leaderboard
31 jinaai/jina-embeddings-v5-omni-nano open weights, 1B 0.14 huggingface.co Official leaderboard
32 jinaai/jina-embeddings-v5-omni-small open weights, 1.6B 0.13 huggingface.co Official leaderboard
33 Salesforce/blip2-opt-2.7b open weights, 3.7B 0.13 huggingface.co Official leaderboard
34 google/siglip-base-patch16-256 open weights, 0.2B 0.13 huggingface.co Official leaderboard
35 google/siglip-base-patch16-384 open weights, 0.2B 0.12 huggingface.co Official leaderboard
36 google/siglip-so400m-patch14-384 open weights, 0.9B 0.12 huggingface.co Official leaderboard
37 google/siglip-base-patch16-512 open weights, 0.2B 0.12 huggingface.co Official leaderboard
38 google/siglip-base-patch16-224 open weights, 0.2B 0.12 huggingface.co Official leaderboard
39 google/siglip-base-patch16-256-multilingual open weights, 0.4B 0.11 huggingface.co Official leaderboard
40 kakaobrain/align-base open weights, 0.2B 0.10 huggingface.co Official leaderboard
41 Salesforce/blip2-opt-6.7b-coco open weights, 7.8B 0.09 huggingface.co Official leaderboard
42 Salesforce/blip-image-captioning-base open weights, 0.2B 0.00 huggingface.co Official leaderboard
43 Salesforce/blip-image-captioning-large open weights, 0.4B 0.00 huggingface.co 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

All 636 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 (43 entries).
  • Pass Models scored 43 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on MTEB: 43 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.

How we check