WMT24 Icelandic Idiomatic Expressions
Models translate English phrases into Icelandic. Context determines whether a phrase has its everyday literal meaning or its idiomatic meaning.
Passes test 4. WMT distributed the test to translation teams. The makers publish outputs for 17 systems across 198 expressions. Independent teams submitted translations alongside models including Claude and GPT-4.
- Released
- June 2024
- Kind
- Translation
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Llama 3-70B #182 on the capability index
- Last model added
- August 2024
- Scores refreshed
- November 20th, 2026
Claude-3.5 (snapshot unspecified) tops the leaderboard with 65.5% Llama 3-70B leads with 41.7%
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 Llama 3-70B, at 41.7%. This view shows only models we track, each at its best.
- 1 Claude-3.5 (snapshot unspecified) 65.5%
- 2 Unbabel-Tower70B 60.8%
- 3 GPT-4 (snapshot unspecified) 54.8%
- 4 IKUN 50.9%
- 5 IOL_Research 48.2%
- 6 IKUN-C 48.1%
- 7 TranssionMT 44.9%
- 8 AMI 44.7%
- 9 ONLINE-B 44.7%
- 10 ONLINE-A 44.2%
- 11 Dubformer 42.7%
- 12
Llama 3-70B 41.7%
- 13 ONLINE-G 41.4%
- 14
Command R+ 29.3%
- 15 Aya23 16.9%
- 16 TSU-HITs 11.2%
- 17 CycleL 10.9%
Source: The WMT24 Icelandic Idiomatic Expressions paper
- 1
Llama 3-70B 41.7%
- 2
Command R+ 29.3%
Source: The WMT24 Icelandic Idiomatic Expressions paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude-3.5 (snapshot unspecified) | 65.5% | Official leaderboard | ||
| 2 | Unbabel-Tower70B | 60.8% | Official leaderboard | ||
| 3 | GPT-4 (snapshot unspecified) | 54.8% | Official leaderboard | ||
| 4 | IKUN | 50.9% | Official leaderboard | ||
| 5 | IOL_Research | 48.2% | Official leaderboard | ||
| 6 | IKUN-C | 48.1% | Official leaderboard | ||
| 7 | TranssionMT | 44.9% | Official leaderboard | ||
| 8 | AMI | 44.7% | Official leaderboard | ||
| 9 | ONLINE-B | 44.7% | Official leaderboard | ||
| 10 | ONLINE-A | 44.2% | Official leaderboard | ||
| 11 | Dubformer | 42.7% | Official leaderboard | ||
| 12 | | 41.7% | Apr 2024 | Official leaderboard | |
| 13 | ONLINE-G | 41.4% | Official leaderboard | ||
| 14 | | 29.3% | Aug 2024 | Official leaderboard | |
| 15 | Aya23 | 16.9% | Official leaderboard | ||
| 16 | TSU-HITs | 11.2% | Official leaderboard | ||
| 17 | CycleL | 10.9% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 41.7% | Apr 2024 | Official leaderboard | |
| 2 | | 29.3% | Aug 2024 | Official 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 WMT24 Icelandic Idiomatic Expressions 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 August 2024, for Command R+. 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 benchmark’s paper (17 entries).
- Pass Models scored 2 models we track, plus 15 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in August 2024, for Command R+.
- Note Frontier models None of the top 10 has a score. The strongest tested is Llama 3-70B (#182).
- Pass Headroom The best is 41.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 2 rows for models we track and 15 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.