Benchmark Almanac

EusProficiency

latxa-70b-v1.1 60.6% tops its leaderboard GPT-4 Turbo (Jan 2024) 56.7% leads the models we track
Not in model cards

Models complete Basque language exercises from the official C1 proficiency examination. The questions test vocabulary and grammar.

Released
March 2024
Kind
Reading in many languages
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Basque
In and out
Text → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-4 Jun 2023 #186 on the capability index
Last model added
January 2024
Scores refreshed
November 20th, 2026
18
Entries on its own leaderboard, 9 models we track

latxa-70b-v1.1 tops the leaderboard with 60.6% GPT-4 Turbo (Jan 2024) leads with 56.7% among models released by January 2024

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. The best model we track is GPT-4 Turbo (Jan 2024), at 56.7%. This view shows only models we track, each at its best.

The newest model with a score here came out in January 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 latxa-70b-v1.1 5-shot 60.6%
  2. 2 GPT-4 Turbo (Jan 2024) 5-shot 56.7%
  3. 3 latxa-70b-v1 5-shot 48.2%
  4. 4 latxa-13b-v1.1 5-shot 45%
  5. 5 GPT-4 Jun 2023, 5-shot 44.9%
  6. 6 latxa-13b-v1 5-shot 41.2%
  7. 7 latxa-7b-v1.1 5-shot 32.4%
  8. 8 GPT-3.5 Turbo Jan 2024, 5-shot 31.2%
  9. 9 latxa-7b-v1 5-shot 28.2%
  10. 10 Yi-34B 5-shot 27.3%
  11. 11 Mixtral 8x7B 5-shot 26.4%
  12. 12 Llama 2-13B 5-shot 25.9%
  13. 13 bloom-7b1 5-shot 25.3%
  14. 14 Mistral 7B v0.1 5-shot 25%
  15. 15 mGPT-13B 5-shot 25%
  16. 16 Llama 2-70B 5-shot 24.2%
  17. 17 Llama 2-7B 5-shot 24.1%
  18. 18 xglm-7.5B 5-shot 23%

Source: Official EusProficiency leaderboard

#EntryScoreSettingDateLinkSource
1 latxa-70b-v1.1 60.6% 5-shot raw.githubusercontent.com Official leaderboard
2 GPT-4 Turbo (Jan 2024) 56.7% 5-shot Jan 2024 raw.githubusercontent.com Official leaderboard
3 latxa-70b-v1 48.2% 5-shot raw.githubusercontent.com Official leaderboard
4 latxa-13b-v1.1 45% 5-shot raw.githubusercontent.com Official leaderboard
5 GPT-4 Jun 2023 44.9% 5-shot Jun 2023 raw.githubusercontent.com Official leaderboard
6 latxa-13b-v1 41.2% 5-shot raw.githubusercontent.com Official leaderboard
7 latxa-7b-v1.1 32.4% 5-shot raw.githubusercontent.com Official leaderboard
8 GPT-3.5 Turbo Jan 2024 31.2% 5-shot Jan 2024 raw.githubusercontent.com Official leaderboard
9 latxa-7b-v1 28.2% 5-shot raw.githubusercontent.com Official leaderboard
10 Yi-34B 27.3% 5-shot Nov 2023 raw.githubusercontent.com Official leaderboard
11 Mixtral 8x7B 26.4% 5-shot Dec 2023 raw.githubusercontent.com Official leaderboard
12 Llama 2-13B 25.9% 5-shot Jul 2023 raw.githubusercontent.com Official leaderboard
13 bloom-7b1 25.3% 5-shot raw.githubusercontent.com Official leaderboard
14 Mistral 7B v0.1 25% 5-shot Sep 2023 raw.githubusercontent.com Official leaderboard
15 mGPT-13B 25% 5-shot raw.githubusercontent.com Official leaderboard
16 Llama 2-70B 24.2% 5-shot Jul 2023 raw.githubusercontent.com Official leaderboard
17 Llama 2-7B 24.1% 5-shot Jul 2023 raw.githubusercontent.com Official leaderboard
18 xglm-7.5B 23% 5-shot raw.githubusercontent.com Official leaderboard
#ModelScoreSettingDateLinkSource
1 GPT-4 Turbo (Jan 2024) 56.7% 5-shot Jan 2024 raw.githubusercontent.com Official leaderboard
2 GPT-4 Jun 2023 44.9% 5-shot Jun 2023 raw.githubusercontent.com Official leaderboard
3 GPT-3.5 Turbo Jan 2024 31.2% 5-shot Jan 2024 raw.githubusercontent.com Official leaderboard
4 Yi-34B 27.3% 5-shot Nov 2023 raw.githubusercontent.com Official leaderboard
5 Mixtral 8x7B 26.4% 5-shot Dec 2023 raw.githubusercontent.com Official leaderboard
6 Llama 2-13B 25.9% 5-shot Jul 2023 raw.githubusercontent.com Official leaderboard
7 Mistral 7B v0.1 25% 5-shot Sep 2023 raw.githubusercontent.com Official leaderboard
8 Llama 2-70B 24.2% 5-shot Jul 2023 raw.githubusercontent.com Official leaderboard
9 Llama 2-7B 24.1% 5-shot Jul 2023 raw.githubusercontent.com Official leaderboard

Number one over time

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

OpenAI
Own leaderboard Not tested since Mar 2024

Source: Official EusProficiency 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 Best so far
0% 20% 40% 60% 80% 100% 2023 2024 Near the ceiling (85%) GPT-4 Turbo (Jan 2024) GPT-4 0% 20% 40% 60% 80% 100% 2023 2024 Near the ceiling (85%) GPT-4 Turbo (Jan 2024) GPT-4

Source: Official EusProficiency 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in January 2024, for GPT-3.5 Turbo. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (18 entries).
  • Pass Models scored 9 models we track, plus 9 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in January 2024, for GPT-3.5 Turbo.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4 (#186).
  • Pass Headroom The best is 56.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 9 rows for models we track and 9 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