EusProficiency
Models complete Basque language exercises from the official C1 proficiency examination. The questions test vocabulary and grammar.
- Made by
- Julen Etxaniz and colleagues
- Released
- March 2024
- Kind
- Reading in many languages
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Basque
- 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
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 60.6 latxa-70b-v1.1
- 56.7 GPT-4 Turbo (Jan 2024)
- 48.2 latxa-70b-v1
- 45.0 latxa-13b-v1.1
- 44.9 GPT-4
- 41.2 latxa-13b-v1
- 32.4 latxa-7b-v1.1
- 31.2 GPT-3.5 Turbo
- 28.2 latxa-7b-v1
- 27.3
Yi-34B
- 26.4
Mixtral 8x7B
- 25.9
Llama 2-13B
- 25.3 bloom-7b1
- 25.0
Mistral 7B v0.1
- 25.0 mGPT-13B
- 24.2
Llama 2-70B
- 24.1
Llama 2-7B
- 23.0 xglm-7.5B
- 1 latxa-70b-v1.1 5-shot 60.6%
- 2 GPT-4 Turbo (Jan 2024) 5-shot 56.7%
- 3 latxa-70b-v1 5-shot 48.2%
- 4 latxa-13b-v1.1 5-shot 45%
- 5 GPT-4 Jun 2023, 5-shot 44.9%
- 6 latxa-13b-v1 5-shot 41.2%
- 7 latxa-7b-v1.1 5-shot 32.4%
- 8 GPT-3.5 Turbo Jan 2024, 5-shot 31.2%
- 9 latxa-7b-v1 5-shot 28.2%
- 10
Yi-34B 5-shot 27.3%
- 11
Mixtral 8x7B 5-shot 26.4%
- 12
Llama 2-13B 5-shot 25.9%
- 13 bloom-7b1 5-shot 25.3%
- 14
Mistral 7B v0.1 5-shot 25%
- 15 mGPT-13B 5-shot 25%
- 16
Llama 2-70B 5-shot 24.2%
- 17
Llama 2-7B 5-shot 24.1%
- 18 xglm-7.5B 5-shot 23%
Source: Official EusProficiency leaderboard
- 1 GPT-4 Turbo (Jan 2024) 5-shot 56.7%
- 2 GPT-4 Jun 2023, 5-shot 44.9%
- 3 GPT-3.5 Turbo Jan 2024, 5-shot 31.2%
- 4
Yi-34B 5-shot 27.3%
- 5
Mixtral 8x7B 5-shot 26.4%
- 6
Llama 2-13B 5-shot 25.9%
- 7
Mistral 7B v0.1 5-shot 25%
- 8
Llama 2-70B 5-shot 24.2%
- 9
Llama 2-7B 5-shot 24.1%
Source: Official EusProficiency leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 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 | | 27.3% | 5-shot | Nov 2023 | raw.githubusercontent.com | Official leaderboard |
| 11 | | 26.4% | 5-shot | Dec 2023 | raw.githubusercontent.com | Official leaderboard |
| 12 | | 25.9% | 5-shot | Jul 2023 | raw.githubusercontent.com | Official leaderboard |
| 13 | bloom-7b1 | 25.3% | 5-shot | raw.githubusercontent.com | Official leaderboard | |
| 14 | | 25% | 5-shot | Sep 2023 | raw.githubusercontent.com | Official leaderboard |
| 15 | mGPT-13B | 25% | 5-shot | raw.githubusercontent.com | Official leaderboard | |
| 16 | | 24.2% | 5-shot | Jul 2023 | raw.githubusercontent.com | Official leaderboard |
| 17 | | 24.1% | 5-shot | Jul 2023 | raw.githubusercontent.com | Official leaderboard |
| 18 | xglm-7.5B | 23% | 5-shot | raw.githubusercontent.com | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 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 | | 27.3% | 5-shot | Nov 2023 | raw.githubusercontent.com | Official leaderboard |
| 5 | | 26.4% | 5-shot | Dec 2023 | raw.githubusercontent.com | Official leaderboard |
| 6 | | 25.9% | 5-shot | Jul 2023 | raw.githubusercontent.com | Official leaderboard |
| 7 | | 25% | 5-shot | Sep 2023 | raw.githubusercontent.com | Official leaderboard |
| 8 | | 24.2% | 5-shot | Jul 2023 | raw.githubusercontent.com | Official leaderboard |
| 9 | | 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.
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.
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
- 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.