Benchmark Almanac

TurBLiMP

EuroLLM 93.8% tops its leaderboard Gemma 3 12B 93.6% leads the models we track
Not in model cards

Models compare Turkish sentence pairs that differ in grammaticality. The core tests cover 16 grammatical phenomena.

Made by
Ezgi Başar and colleagues
Released
June 2025
Kind
Reasoning in many languages
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Turkish
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Last model added
March 2025
Scores refreshed
November 20th, 2026
13
Entries in its paper, 2 models we track

EuroLLM tops the leaderboard with 93.8% Gemma 3 12B leads with 93.6%

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. The best model we track is Gemma 3 12B, at 93.6%. This view shows only models we track, each at its best.

  1. 1 EuroLLM 93.8%
  2. 2 Goldfish 1000MB 93.7%
  3. 3 CosmosGPT 93.6%
  4. 4 Gemma 3 12B 93.6%
  5. 5 Gemma 3 4B 91.7%
  6. 6 Gemma 2 91.5%
  7. 7 Aya Expanse 90.6%
  8. 8 Llama 3.1 90%
  9. 9 BERTurk 89.1%
  10. 10 Qwen 2.5 87%
  11. 11 Goldfish 100MB 85.1%
  12. 12 Goldfish 10MB 64.5%
  13. 13 Goldfish 5MB 63.3%

Source: The TurBLiMP paper

Source: The TurBLiMP paper

#EntryScoreSettingDateSource
1 EuroLLM 93.8% Official leaderboard
2 Goldfish 1000MB 93.7% Official leaderboard
3 CosmosGPT 93.6% Official leaderboard
4 Gemma 3 12B 93.6% Mar 2025 Official leaderboard
5 Gemma 3 4B 91.7% Mar 2025 Official leaderboard
6 Gemma 2 91.5% Official leaderboard
7 Aya Expanse 90.6% Official leaderboard
8 Llama 3.1 90% Official leaderboard
9 BERTurk 89.1% Official leaderboard
10 Qwen 2.5 87% Official leaderboard
11 Goldfish 100MB 85.1% Official leaderboard
12 Goldfish 10MB 64.5% Official leaderboard
13 Goldfish 5MB 63.3% Official leaderboard
#ModelScoreSettingDateSource
1 Gemma 3 12B 93.6% Mar 2025 Official leaderboard
2 Gemma 3 4B 91.7% Mar 2025 Official leaderboard

Gemma 3 12B on the official leaderboard passed 85% in March 2025

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Gemma 3 12B 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Gemma 3 12B

Source: Official TurBLiMP 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

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 benchmark’s paper (13 entries).
  • Pass Models scored 2 models we track, plus 11 other entries on its leaderboard.
  • Note Newest score The newest came 20 months ago, in March 2025, for Gemma 3 12B. That’s expected for a saturated test.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Saturated. The best is 93.6%, past 85% since March 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 2 rows for models we track and 11 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