Benchmark Almanac

BAREC Shared Task 2025

!MSA 87.5 tops its leaderboard
Not in model cards
Version 2025

Models assign Arabic sentences and documents to 19 reading levels. The hardest sentence determines the reference level for a document.

Pixels ran the PIXEL vision transformer on the blind test. AMAR tested GPT-4.1 on development sentences. The blind set contained 3,420 sentences.

Released
May 2025
Kind
Reading in many languages
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
Public, plus a private test set
Measures
Capability
Language
Arabic
In and out
Text → Text
Interaction
Single turn
Items from
Another benchmark
Run by
A host
16
Entries in its paper, 0 models we track

!MSA tops the leaderboard with 87.5

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 !MSA Strict sentence 87.5
  2. 2 AMAR Strict sentence 86.4
  3. 3 mucAI Strict sentence, trained on development data 85.7
  4. 4 STBW Strict sentence 85.6
  5. 5 ZAI Strict sentence 85.5
  6. 6 Syntaxa Strict sentence 84.3
  7. 7 MorphoArabia Strict sentence 84.2
  8. 8 MARSAD Strict sentence 84.1
  9. 9 Noor Strict sentence 83.1
  10. 10 Phantom Strict sentence 82.7
  11. 11 Qais Strict sentence 82.5
  12. 12 LIS Strict sentence 82.4
  13. 13 SATLab Strict sentence 82.3
  14. 14 PalNLP Strict sentence, trained on development data 81.1
  15. 15 ANLPers Strict sentence 73.0
  16. 16 Pixel Strict sentence 66.2

Source: The BAREC Shared Task 2025 paper

#EntryScoreSettingSubmitted byDateSource
1 !MSA 87.5 Strict sentence !MSA Official leaderboard
2 AMAR 86.4 Strict sentence AMAR Official leaderboard
3 mucAI 85.7 Strict sentence, trained on development data mucAI Official leaderboard
4 STBW 85.6 Strict sentence STBW Official leaderboard
5 ZAI 85.5 Strict sentence ZAI Official leaderboard
6 Syntaxa 84.3 Strict sentence Syntaxa Official leaderboard
7 MorphoArabia 84.2 Strict sentence MorphoArabia Official leaderboard
8 MARSAD 84.1 Strict sentence MARSAD Official leaderboard
9 Noor 83.1 Strict sentence Noor Official leaderboard
10 Phantom 82.7 Strict sentence Phantom Official leaderboard
11 Qais 82.5 Strict sentence Qais Official leaderboard
12 LIS 82.4 Strict sentence LIS Official leaderboard
13 SATLab 82.3 Strict sentence SATLab Official leaderboard
14 PalNLP 81.1 Strict sentence, trained on development data PalNLP Official leaderboard
15 ANLPers 73.0 Strict sentence ANLPers Official leaderboard
16 Pixel 66.2 Strict sentence Pixel 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 Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (16 entries).
  • Pass Models scored 16 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 aclanthology.org: 16 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