Benchmark Almanac

BAREC-ST-2026

Thylinao 85.3 tops its leaderboard
Not in model cards
Version 2026

Models assign Arabic sentences and documents to 19 reading levels. The blind test includes texts from 17 publishers absent from the original corpus.

NAMAA tested an EmbeddingGemma classifier on 8,077 blind sentences. The team also describes a Qwen2.5 variant in its public experiments.

Released
May 2026
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
Real work and use
Refresh
One fixed set
Run by
A host
13
Entries in its paper, 0 models we track

Thylinao tops the leaderboard with 85.3

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 Thylinao Strict 85.3
  2. 2 ZHR Open 85.2
  3. 3 Nile Nexus Strict 84.8
  4. 4 Skywalker Strict 84.2
  5. 5 Viper Strict 84.1
  6. 6 HP Strict 83.7
  7. 7 Baseline III Strict 82.5
  8. 8 NAMAA Strict 82.4
  9. 9 LSI Constrained 81.7
  10. 10 Baseline II Strict 81.1
  11. 11 soloeval Strict 80.6
  12. 12 Baseline I Strict 79.7
  13. 13 Northwestern_2 Strict 79.0

Source: The BAREC-ST-2026 paper

#EntryScoreSettingSubmitted byDateSource
1 Thylinao 85.3 Strict Thylinao Official leaderboard
2 ZHR 85.2 Open ZHR Official leaderboard
3 Nile Nexus 84.8 Strict Nile Nexus Official leaderboard
4 Skywalker 84.2 Strict Skywalker Official leaderboard
5 Viper 84.1 Strict Viper Official leaderboard
6 HP 83.7 Strict HP Official leaderboard
7 Baseline III 82.5 Strict Official leaderboard
8 NAMAA 82.4 Strict NAMAA Official leaderboard
9 LSI 81.7 Constrained LSI Official leaderboard
10 Baseline II 81.1 Strict Official leaderboard
11 soloeval 80.6 Strict soloeval Official leaderboard
12 Baseline I 79.7 Strict Official leaderboard
13 Northwestern_2 79.0 Strict Northwestern_2 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 (13 entries).
  • Pass Models scored 13 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: 13 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