DaLAJ
Models judge the linguistic acceptability of Swedish sentences.
MTEB scores the task using accuracy.
- Made by
- Elena Volodina and colleagues
- Released
- May 2021
- Kind
- Reading in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Swedish
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
electra-small-nordic tops the leaderboard with 55.8%
Best score per entry from the benchmark's own 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.
- 55.8 electra-small-nordic
- 55.6 electra-small-swedish-cased-discriminator
- 51.8 bert-base-swedish-cased
- 51.2 xlm-roberta-base
- 50.9 nb-bert-large
- 50.4 dfm-encoder-large-v1
- 50.3 nb-bert-base
- 50.3 DanskBERT
- 50.2 multilingual-e5-small
- 50.1 paraphrase-multilingual-MiniLM-L12-v2
- 50.1 sentence-bert-swedish-cased
- 50.0 dfm-sentence-encoder-large-1
- 50.0 multilingual-e5-large
- 49.9 all-MiniLM-L6-v2
- 49.9 multilingual-e5-base
- 49.9 e5-small
- 49.8 e5-large
- 49.6 e5-base
- 1 electra-small-nordic 55.8%
- 2 electra-small-swedish-cased-discriminator 55.6%
- 3 bert-base-swedish-cased 51.8%
- 4 xlm-roberta-base 51.2%
- 5 nb-bert-large 50.9%
- 6 dfm-encoder-large-v1 50.4%
- 7 nb-bert-base 50.3%
- 8 DanskBERT 50.3%
- 9 multilingual-e5-small 50.2%
- 10 paraphrase-multilingual-MiniLM-L12-v2 50.1%
- 11 sentence-bert-swedish-cased 50.1%
- 12 dfm-sentence-encoder-large-1 50%
- 13 multilingual-e5-large 50%
- 14 all-MiniLM-L6-v2 49.9%
- 15 multilingual-e5-base 49.9%
- 16 e5-small 49.9%
- 17 e5-large 49.8%
- 18 e5-base 49.6%
Source: Official DaLAJ leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | electra-small-nordic | 55.8% | huggingface.co | Official leaderboard | ||
| 2 | electra-small-swedish-cased-discriminator | 55.6% | huggingface.co | Official leaderboard | ||
| 3 | bert-base-swedish-cased | 51.8% | huggingface.co | Official leaderboard | ||
| 4 | xlm-roberta-base | 51.2% | huggingface.co | Official leaderboard | ||
| 5 | nb-bert-large | 50.9% | huggingface.co | Official leaderboard | ||
| 6 | dfm-encoder-large-v1 | 50.4% | huggingface.co | Official leaderboard | ||
| 7 | nb-bert-base | 50.3% | huggingface.co | Official leaderboard | ||
| 8 | DanskBERT | 50.3% | huggingface.co | Official leaderboard | ||
| 9 | multilingual-e5-small | 50.2% | huggingface.co | Official leaderboard | ||
| 10 | paraphrase-multilingual-MiniLM-L12-v2 | 50.1% | huggingface.co | Official leaderboard | ||
| 11 | sentence-bert-swedish-cased | 50.1% | huggingface.co | Official leaderboard | ||
| 12 | dfm-sentence-encoder-large-1 | 50% | huggingface.co | Official leaderboard | ||
| 13 | multilingual-e5-large | 50% | huggingface.co | Official leaderboard | ||
| 14 | all-MiniLM-L6-v2 | 49.9% | huggingface.co | Official leaderboard | ||
| 15 | multilingual-e5-base | 49.9% | huggingface.co | Official leaderboard | ||
| 16 | e5-small | 49.9% | huggingface.co | Official leaderboard | ||
| 17 | e5-large | 49.8% | huggingface.co | Official leaderboard | ||
| 18 | e5-base | 49.6% | 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 Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
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 (18 entries).
- Pass Models scored 18 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 datawrapper.dwcdn.net: 18 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.