WMT25 EEA Terminology
Models translate English regulatory sentences into Icelandic. The scorer checks whether they use the official Icelandic terms from the European Economic Area agreement.
Passes test 2. The makers publish term accuracy for 34 systems on 256 sentences. A reviewer scored 50 sentences per system. The corrected release contains 299 sentences.
- Released
- June 2025
- Kind
- Translation
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Law, Languages and literature
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- Anyone
- In views
- Law and finance
- Strongest model tested
-
Gemini 2.5 Pro Jun 2025 #97 on the capability index
- Last model added
- June 2025
- Scores refreshed
- November 20th, 2026
ONLINE-G tops the leaderboard with 55.9% Gemini 2.5 Pro leads with 46.5% among models released by June 2025
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 Gemini 2.5 Pro, at 46.5%. This view shows only models we track, each at its best.
The newest model with a score here came out in June 2025, 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
- 55.9 ONLINE-G
- 53.3 Erlendur
- 46.5 ONLINE-B
- 46.5
Gemini 2.5 Pro
- 46.3 TranssionTranslate
- 38.7 hybrid
- 38.5 Claude-4
- 38.5 SalamandraTA
- 37.5 TowerPlus-9B
- 36.8 Shy
- 34.9 GPT-4.1
- 32.7 TowerPlus-72B
- 30.0
DeepSeek-V3
- 27.9 AMI
- 27.9
Llama 4 Maverick
- 26.6 NLLB
- 24.9 CommandA-MT
- 24.2 IR-MultiagentMT
- 20.1
Gemma 3 27B
- 18.9
Mistral Medium
- 16.5 GemTrans
- 13.8 IRB-MT
- 13.1 UvA-MT
- 11.6
Gemma 3 12B
- 10.9 Qwen3-235B
- 7.51 CommandA
- 3.15
Llama 3.1-8B
- 2.66
Aya Expanse 32B
- 0.73
Qwen2.5-7B
- 0.48 EuroLLM-9B
- 0.48
Command R7B
- 0.24 EuroLLM-22B
- 0.24
Mistral 7B v0.1
- 0.0
Aya Expanse 8B
- 1 ONLINE-G 55.9%
- 2 Erlendur 53.3%
- 3 ONLINE-B 46.5%
- 4
Gemini 2.5 Pro Jun 2025 46.5%
- 5 TranssionTranslate 46.3%
- 6 hybrid 38.7%
- 7 Claude-4 38.5%
- 8 SalamandraTA 38.5%
- 9 TowerPlus-9B 37.5%
- 10 Shy 36.8%
- 11 GPT-4.1 34.9%
- 12 TowerPlus-72B 32.7%
- 13
DeepSeek-V3 Mar 2025 30%
- 14 AMI 27.9%
- 15
Llama 4 Maverick 27.9%
- 16 NLLB 26.6%
- 17 CommandA-MT 24.9%
- 18 IR-MultiagentMT 24.2%
- 19
Gemma 3 27B 20.1%
- 20
Mistral Medium 18.9%
- 21 GemTrans 16.5%
- 22 IRB-MT 13.8%
- 23 UvA-MT 13.1%
- 24
Gemma 3 12B 11.6%
- 25 Qwen3-235B 10.9%
- 26 CommandA 7.51%
- 27
Llama 3.1-8B 3.15%
- 28
Aya Expanse 32B 2.66%
- 29
Qwen2.5-7B 0.73%
- 30 EuroLLM-9B 0.48%
- 31
Command R7B 0.48%
- 32 EuroLLM-22B 0.24%
- 33
Mistral 7B v0.1 0.24%
- 34
Aya Expanse 8B 0%
Source: Official WMT25 EEA Terminology leaderboard
- 1
Gemini 2.5 Pro Jun 2025 46.5%
- 2 GPT-4.1 34.9%
- 3
DeepSeek-V3 Mar 2025 30%
- 4
Llama 4 Maverick 27.9%
- 5
Gemma 3 27B 20.1%
- 6
Mistral Medium 18.9%
- 7
Gemma 3 12B 11.6%
- 8
Llama 3.1-8B 3.15%
- 9
Aya Expanse 32B 2.66%
- 10
Qwen2.5-7B 0.73%
- 11
Command R7B 0.48%
- 12
Mistral 7B v0.1 0.24%
- 13
Aya Expanse 8B 0%
Source: Official WMT25 EEA Terminology leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | ONLINE-G | 55.9% | Official leaderboard | ||
| 2 | Erlendur | 53.3% | Official leaderboard | ||
| 3 | ONLINE-B | 46.5% | Official leaderboard | ||
| 4 | | 46.5% | Jun 2025 | Official leaderboard | |
| 5 | TranssionTranslate | 46.3% | Official leaderboard | ||
| 6 | hybrid | 38.7% | Official leaderboard | ||
| 7 | Claude-4 | 38.5% | Official leaderboard | ||
| 8 | SalamandraTA | 38.5% | Official leaderboard | ||
| 9 | TowerPlus-9B | 37.5% | Official leaderboard | ||
| 10 | Shy | 36.8% | Official leaderboard | ||
| 11 | GPT-4.1 | 34.9% | Apr 2025 | Official leaderboard | |
| 12 | TowerPlus-72B | 32.7% | Official leaderboard | ||
| 13 | | 30% | Mar 2025 | Official leaderboard | |
| 14 | AMI | 27.9% | Official leaderboard | ||
| 15 | | 27.9% | Apr 2025 | Official leaderboard | |
| 16 | NLLB | 26.6% | Official leaderboard | ||
| 17 | CommandA-MT | 24.9% | Official leaderboard | ||
| 18 | IR-MultiagentMT | 24.2% | Official leaderboard | ||
| 19 | | 20.1% | Mar 2025 | Official leaderboard | |
| 20 | | 18.9% | Dec 2023 | Official leaderboard | |
| 21 | GemTrans | 16.5% | Official leaderboard | ||
| 22 | IRB-MT | 13.8% | Official leaderboard | ||
| 23 | UvA-MT | 13.1% | Official leaderboard | ||
| 24 | | 11.6% | Mar 2025 | Official leaderboard | |
| 25 | Qwen3-235B | 10.9% | Official leaderboard | ||
| 26 | CommandA | 7.51% | Official leaderboard | ||
| 27 | | 3.15% | Jul 2024 | Official leaderboard | |
| 28 | | 2.66% | Oct 2024 | Official leaderboard | |
| 29 | | 0.73% | Sep 2024 | Official leaderboard | |
| 30 | EuroLLM-9B | 0.48% | Official leaderboard | ||
| 31 | | 0.48% | Dec 2024 | Official leaderboard | |
| 32 | EuroLLM-22B | 0.24% | Official leaderboard | ||
| 33 | | 0.24% | Sep 2023 | Official leaderboard | |
| 34 | | 0% | Oct 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 46.5% | Jun 2025 | Official leaderboard | |
| 2 | GPT-4.1 | 34.9% | Apr 2025 | Official leaderboard | |
| 3 | | 30% | Mar 2025 | Official leaderboard | |
| 4 | | 27.9% | Apr 2025 | Official leaderboard | |
| 5 | | 20.1% | Mar 2025 | Official leaderboard | |
| 6 | | 18.9% | Dec 2023 | Official leaderboard | |
| 7 | | 11.6% | Mar 2025 | Official leaderboard | |
| 8 | | 3.15% | Jul 2024 | Official leaderboard | |
| 9 | | 2.66% | Oct 2024 | Official leaderboard | |
| 10 | | 0.73% | Sep 2024 | Official leaderboard | |
| 11 | | 0.48% | Dec 2024 | Official leaderboard | |
| 12 | | 0.24% | Sep 2023 | Official leaderboard | |
| 13 | | 0% | Oct 2024 | Official leaderboard |
2 models have held number one on the official leaderboard since its release in June 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official WMT25 EEA Terminology 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 WMT25 EEA Terminology 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 17 months ago, in June 2025, for Gemini 2.5 Pro. 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 (34 entries).
- Pass Models scored 13 models we track, plus 21 other entries on its leaderboard.
- Warning Newest score The newest came 17 months ago, in June 2025, for Gemini 2.5 Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Pro (#97).
- Pass Headroom The best is 46.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 13 rows for models we track and 21 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.