Benchmark Almanac

DFKI English-Russian Linguistic Test Suite at WMT25

Algharb 93.1% tops its leaderboard GPT-4.1 89.5% leads the models we track
Not in model cards

Models translate English passages into idiomatic Russian. Rules match known translations. A linguist judges unresolved cases across 55 phenomena. The authors report item-weighted and category-weighted accuracy.

Passes test 4. WMT distributed 5,553 source items and compared system rankings. The authors report 465 scored items for ten systems, including Claude, DeepSeek, Gemini and GPT.

Released
June 2025
Kind
Translation
Level
University
Scored
Graded by people
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English, Russian
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-4.1 #138 on the capability index
Last model added
April 2025
Scores refreshed
November 21st, 2026
10
Entries in its paper, 1 model we track

Algharb tops the leaderboard with 93.1% GPT-4.1 leads with 89.5%

Best score per entry from the benchmark's paper, read on November 21st, 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 GPT-4.1, at 89.5%. This view shows only models we track, each at its best.

  1. 1 Algharb 93.1%
  2. 2 Wenyiil 93.1%
  3. 3 Yandex 93.1%
  4. 4 Gemini 91.8%
  5. 5 Shy-hunyuan-MT 89.7%
  6. 6 Claude-4 89.5%
  7. 7 GPT-4.1 89.5%
  8. 8 DeepSeek-V3 (snapshot unspecified) 89.2%
  9. 9 CommandA 86.5%
  10. 10 UvA-MT 83.7%

Source: The DFKI English-Russian Linguistic Test Suite at WMT25 paper

Source: The DFKI English-Russian Linguistic Test Suite at WMT25 paper

#EntryScoreSettingDateSource
1 Algharb 93.1% Official leaderboard
2 Wenyiil 93.1% Official leaderboard
3 Yandex 93.1% Official leaderboard
4 Gemini 91.8% Official leaderboard
5 Shy-hunyuan-MT 89.7% Official leaderboard
6 Claude-4 89.5% Official leaderboard
7 GPT-4.1 89.5% Apr 2025 Official leaderboard
8 DeepSeek-V3 (snapshot unspecified) 89.2% Official leaderboard
9 CommandA 86.5% Official leaderboard
10 UvA-MT 83.7% Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4.1 89.5% Apr 2025 Official leaderboard

GPT-4.1 on the official leaderboard passed 85% in April 2025

Models released before it came out already scored that high. 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% 2025 Near the ceiling (85%) GPT-4.1 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-4.1

Source: Official DFKI English-Russian Linguistic Test Suite at WMT25 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

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (10 entries).
  • Pass Models scored 1 model we track, plus 9 other entries on its leaderboard.
  • Note Newest score The newest came 19 months ago, in April 2025, for GPT-4.1. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-4.1 (#138).
  • Note Headroom Saturated. The best is 89.5%, past 85% since April 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on aclanthology.org: 1 row for models we track and 9 other entries at the last read.
  • Pass Last read November 21st, 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