Benchmark Almanac

Swedish Benchmarks V1.0

Gemma 4 31B IT 81.0 leads since April 2026
Not in model cards
Version 1.0

Models answer Swedish language and document questions. The overall score gives task performance a 75% weight and response time a 25% weight by default.

Markovic’s April leaderboard ranks 15 models on ten tests.

Made by
Drasko Markovic
Released
April 2026
Kind
Reading in many languages
Level
School
Scored
Checked automatically
Answers
Short answer
Measures
Capability
Language
Swedish
In and out
Text, Documents → Text
Interaction
Single turn
Items from
Another benchmark
Run by
A host
Strongest model tested
Qwen3.6 27B #88 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
15
Entries on its own leaderboard, 12 models we track

Gemma 4 31B IT leads with 81.0 among models released by April 2026 Gemma 4 31B IT leads with 81.0 among models released by April 2026

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. This view shows only models we track, each at its best.

The newest model with a score here came out in April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemma 4 31B IT 81.0
  2. 2 Qwen3.6 27B 77.4
  3. 3 Qwen 3.6 35B-A3B 76.1
  4. 4 Gemma 4 26B A4B 75.3
  5. 5 qwen3.5-122b-a10b-halo 74.6
  6. 6 gpt-oss-120b 71.0
  7. 7 Nemotron 3 Super 70.4
  8. 8 gpt-oss-20b 65.2
  9. 9 nvidia_nemotron-3-nano 63.3
  10. 10 Gemma 3 27B 61.7
  11. 11 Llama 3.3 70B 61.2
  12. 12 MiniMax-M2.7 60.3
  13. 13 glm-4.7-flash 58.9
  14. 14 mistralai_ministral-3-14b-reasoning 45.5
  15. 15 Mistral Small 4 34.1

Source: Official Swedish Benchmarks V1.0 leaderboard

#EntryScoreSettingDateSource
1 Gemma 4 31B IT 81.0 Apr 2026 Official leaderboard
2 Qwen3.6 27B 77.4 Apr 2026 Official leaderboard
3 Qwen 3.6 35B-A3B 76.1 Apr 2026 Official leaderboard
4 Gemma 4 26B A4B 75.3 Apr 2026 Official leaderboard
5 qwen3.5-122b-a10b-halo 74.6 Official leaderboard
6 gpt-oss-120b 71.0 Aug 2025 Official leaderboard
7 Nemotron 3 Super 70.4 Mar 2026 Official leaderboard
8 gpt-oss-20b 65.2 Aug 2025 Official leaderboard
9 nvidia_nemotron-3-nano 63.3 Official leaderboard
10 Gemma 3 27B 61.7 Mar 2025 Official leaderboard
11 Llama 3.3 70B 61.2 Dec 2024 Official leaderboard
12 MiniMax-M2.7 60.3 Mar 2026 Official leaderboard
13 glm-4.7-flash 58.9 Jan 2026 Official leaderboard
14 mistralai_ministral-3-14b-reasoning 45.5 Official leaderboard
15 Mistral Small 4 34.1 Mar 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Gemma 4 31B IT 81.0 Apr 2026 Official leaderboard
2 Qwen3.6 27B 77.4 Apr 2026 Official leaderboard
3 Qwen 3.6 35B-A3B 76.1 Apr 2026 Official leaderboard
4 Gemma 4 26B A4B 75.3 Apr 2026 Official leaderboard
5 gpt-oss-120b 71.0 Aug 2025 Official leaderboard
6 Nemotron 3 Super 70.4 Mar 2026 Official leaderboard
7 gpt-oss-20b 65.2 Aug 2025 Official leaderboard
8 Gemma 3 27B 61.7 Mar 2025 Official leaderboard
9 Llama 3.3 70B 61.2 Dec 2024 Official leaderboard
10 MiniMax-M2.7 60.3 Mar 2026 Official leaderboard
11 glm-4.7-flash 58.9 Jan 2026 Official leaderboard
12 Mistral Small 4 34.1 Mar 2026 Official leaderboard

Rankings by part

We read 10 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as New Synonym Benchmark, SweDiagnostics and SweFAQ. Gemma 4 31B IT leads 4 of them, and 5 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

New Synonym Benchmark

12 models we track have a score here.

  1. 1 Gemma 4 31B IT 98.7
  2. 2 Gemma 4 26B A4B ↑2 95.1
  3. 3 Gemma 3 27B ↑5 90.5
  4. 4 Qwen 3.6 35B-A3B ↓1 89.0
  5. 5 Qwen3.6 27B ↓3 88.2
  6. 6 Llama 3.3 70B ↑3 86.3
  7. 7 Nemotron 3 Super ↓1 85.8
  8. 8 gpt-oss-20b ↓1 75.3
  9. 9 gpt-oss-120b ↓4 74.9
  10. 10 MiniMax-M2.7 63.5

2 models have held number one on the official leaderboard since its release in April 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI Google DeepMind
Own leaderboard Replaced by 1.1, Apr 2026

Source: Official Swedish Benchmarks V1.0 leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
40.0 60.0 80.0 2025 2026 40.0 60.0 80.0 2025 2026

Source: Official Swedish Benchmarks V1.0 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

7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (15 entries).
  • Pass Models scored 12 models we track, plus 3 other entries on its leaderboard.
  • Note Newest score The newest came 7 months ago, in April 2026, for Qwen3.6 27B. That’s expected for a test replaced by Swedish Benchmarks V1.1.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Qwen3.6 27B (#88).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on markovic.com: 12 rows for models we track and 3 other entries at the last read.
  • 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