Benchmark Almanac

SuperLim 2.0

gpt-sw3-6.7b 0.82 tops its leaderboard
Not in model cards
Version 2.0

Models complete 15 Swedish language tasks across 14 datasets. Tasks include recognizing arguments, choosing synonyms, and summarizing newspaper articles.

The National Library of Sweden lists 18 systems, including eight pretrained encoders and four GPT-SW3 sizes. Some entries cover only part of the suite.

Released
September 2022
Kind
Reading in many languages
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Swedish
In and out
Text → Text
Interaction
Single turn
Items from
Another benchmark
Run by
Anyone
Based on
SuperLim 1.0
18
Entries on its own leaderboard, 0 models we track

gpt-sw3-6.7b tops the leaderboard with 0.82

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.

  1. 1 gpt-sw3-6.7b 0.82
  2. 2 gpt-sw3-1.3b 0.70
  3. 3 gpt-sw3-356m 0.50
  4. 4 KBLab/megatron-bert-large-swedish-cased-165k 0.44
  5. 5 AI-Nordics/bert-large-swedish-cased 0.41
  6. 6 xlm-roberta-large 0.41
  7. 7 KB/bert-base-swedish-cased 0.40
  8. 8 KBLab/megatron-bert-base-swedish-cased-600k 0.39
  9. 9 gpt-sw3-126m 0.37
  10. 10 NbAiLab/nb-bert-base 0.37
  11. 11 KBLab/bert-base-swedish-cased-new 0.33
  12. 12 xlm-roberta-base 0.31
  13. 13 SVM 0.17
  14. 14 sv_core_news_lg 0.15
  15. 15 Decision Tree 0.07
  16. 16 Random -0.00
  17. 17 Random Forest -0.11
  18. 18 MaxFreq/Avg -0.22

Source: Official SuperLim 2.0 leaderboard

#EntryScoreSettingDateSource
1 gpt-sw3-6.7b 6.7B 0.82 Official leaderboard
2 gpt-sw3-1.3b 1.3B 0.70 Official leaderboard
3 gpt-sw3-356m 0.4B 0.50 Official leaderboard
4 KBLab/megatron-bert-large-swedish-cased-165k 0.4B 0.44 Official leaderboard
5 AI-Nordics/bert-large-swedish-cased 0.3B 0.41 Official leaderboard
6 xlm-roberta-large 0.6B 0.41 Official leaderboard
7 KB/bert-base-swedish-cased 0.1B 0.40 Official leaderboard
8 KBLab/megatron-bert-base-swedish-cased-600k 0.1B 0.39 Official leaderboard
9 gpt-sw3-126m 0.1B 0.37 Official leaderboard
10 NbAiLab/nb-bert-base 0.2B 0.37 Official leaderboard
11 KBLab/bert-base-swedish-cased-new 0.1B 0.33 Official leaderboard
12 xlm-roberta-base 0.3B 0.31 Official leaderboard
13 SVM 0.17 Official leaderboard
14 sv_core_news_lg 0.15 Official leaderboard
15 Decision Tree 0.07 Official leaderboard
16 Random -0.00 Official leaderboard
17 Random Forest -0.11 Official leaderboard
18 MaxFreq/Avg -0.22 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.

Versions

More in Multilingual

All 545 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 Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on lab.kb.se: 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.

How we check