Benchmark Almanac

WMT24 Icelandic Idiomatic Expressions

Claude-3.5 (snapshot unspecified) 65.5% tops its leaderboard Llama 3-70B 41.7% leads the models we track
Not in model cards

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
Language
English, Icelandic
In and out
Text → Text
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
17
Entries in its paper, 2 models we track

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. 1 Claude-3.5 (snapshot unspecified) 65.5%
  2. 2 Unbabel-Tower70B 60.8%
  3. 3 GPT-4 (snapshot unspecified) 54.8%
  4. 4 IKUN 50.9%
  5. 5 IOL_Research 48.2%
  6. 6 IKUN-C 48.1%
  7. 7 TranssionMT 44.9%
  8. 8 AMI 44.7%
  9. 9 ONLINE-B 44.7%
  10. 10 ONLINE-A 44.2%
  11. 11 Dubformer 42.7%
  12. 12 Llama 3-70B 41.7%
  13. 13 ONLINE-G 41.4%
  14. 14 Command R+ 29.3%
  15. 15 Aya23 16.9%
  16. 16 TSU-HITs 11.2%
  17. 17 CycleL 10.9%

Source: The WMT24 Icelandic Idiomatic Expressions paper

Source: The WMT24 Icelandic Idiomatic Expressions paper

#EntryScoreSettingDateSource
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 Llama 3-70B 41.7% Apr 2024 Official leaderboard
13 ONLINE-G 41.4% Official leaderboard
14 Command R+ 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
#ModelScoreSettingDateSource
1 Llama 3-70B 41.7% Apr 2024 Official leaderboard
2 Command R+ 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.

In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Llama 3-70B 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Llama 3-70B

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

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 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.

How we check