Benchmark Almanac

Babel-ImageNet

nllb-clip-large-siglip@v1 34.3% tops its leaderboard
Not in model cards

Models classify ImageNet images using class descriptions in different languages. The benchmark measures how recognition accuracy changes with the prompt language.

Released
June 2023
Kind
General visual questions
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Language
Many languages
In and out
Images, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Based on
ImageNet-1K
12
Entries on its own leaderboard, 0 models we track

nllb-clip-large-siglip@v1 tops the leaderboard with 34.3%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The authors report no overall score, so this is the plain mean of accuracy across the 298 languages. 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. 1 nllb-clip-large-siglip@v1 34.3%
  2. 2 ViT-B-16-SigLIP-i18n-256@webli 29.5%
  3. 3 xlm-roberta-large-ViT-H-14@frozen_laion5b_s13b_b90k 28.8%
  4. 4 nllb-clip-base-siglip@v1 28%
  5. 5 nllb-clip-large@v1 27.3%
  6. 6 M-CLIP/XLM-Roberta-Large-Vit-L-14 23.7%
  7. 7 xlm-roberta-base-ViT-B-32@laion5b_s13b_b90k 23.5%
  8. 8 M-CLIP/XLM-Roberta-Large-Vit-B-16Plus 23%
  9. 9 nllb-clip-base@v1 22%
  10. 10 M-CLIP/XLM-Roberta-Large-Vit-B-32 20.9%
  11. 11 BAAI/AltCLIP-m9 20.8%
  12. 12 M-CLIP/M-BERT-Base-ViT-B 12.8%

Source: Official Babel-ImageNet leaderboard

#EntryScoreSettingDateSource
1 nllb-clip-large-siglip@v1 1.2B 34.3% Official leaderboard
2 ViT-B-16-SigLIP-i18n-256@webli 0.4B 29.5% Official leaderboard
3 xlm-roberta-large-ViT-H-14@frozen_laion5b_s13b_b90k 1.2B 28.8% Official leaderboard
4 nllb-clip-base-siglip@v1 0.5B 28% Official leaderboard
5 nllb-clip-large@v1 1.4B 27.3% Official leaderboard
6 M-CLIP/XLM-Roberta-Large-Vit-L-14 1B 23.7% Official leaderboard
7 xlm-roberta-base-ViT-B-32@laion5b_s13b_b90k 0.4B 23.5% Official leaderboard
8 M-CLIP/XLM-Roberta-Large-Vit-B-16Plus 0.8B 23% Official leaderboard
9 nllb-clip-base@v1 0.5B 22% Official leaderboard
10 M-CLIP/XLM-Roberta-Large-Vit-B-32 0.7B 20.9% Official leaderboard
11 BAAI/AltCLIP-m9 0.9B 20.8% Official leaderboard
12 M-CLIP/M-BERT-Base-ViT-B 0.3B 12.8% 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 (12 entries).
  • Pass Models scored 12 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: 12 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