Benchmark Almanac

Domain Dynamics English-Hindi Translation

Online-A 36.2 tops its leaderboard Llama 3-70B 26.2 leads the models we track
Not in model cards

Models translate 2,094 English sentences into Hindi across six domains. The authors report BLEU and COMET on the full set and by domain.

The authors compare 16 systems, including GPT-4 and Claude 3.5. A linguist rated translations of three sentences per domain, for 18 source sentences.

Released
August 2024
Kind
Translation
Level
University
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English, Hindi
In and out
Text → Text
Interaction
Single turn
Items from
Another benchmark
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
16
Entries in its paper, 3 models we track

Online-A tops the leaderboard with 36.2 Llama 3-70B leads with 26.2 among models released by August 2024

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 26.2. This view shows only models we track, each at its best.

The newest model with a score here came out in August 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Online-A 36.2
  2. 2 ZMT 36.2
  3. 3 TransmissionMT 35.9
  4. 4 Online-B 35.9
  5. 5 Online-G 32.8
  6. 6 Claude3.5 31.6
  7. 7 Unbabel-Tower-70B 31.3
  8. 8 NVIDIA-NeMo 29.8
  9. 9 IOL-Research 26.8
  10. 10 Llama 3-70B 26.2
  11. 11 GPT-4 Jun 2023 26.0
  12. 12 Aya23 23.5
  13. 13 Command R+ 23.3
  14. 14 IKUN-C 16.7
  15. 15 IKUN 16.4
  16. 16 CycleL 0.78

Source: The Domain Dynamics English-Hindi Translation paper

Source: The Domain Dynamics English-Hindi Translation paper

#EntryScoreSettingDateSource
1 Online-A 36.2 Official leaderboard
2 ZMT 36.2 Official leaderboard
3 TransmissionMT 35.9 Official leaderboard
4 Online-B 35.9 Official leaderboard
5 Online-G 32.8 Official leaderboard
6 Claude3.5 31.6 Official leaderboard
7 Unbabel-Tower-70B 31.3 Official leaderboard
8 NVIDIA-NeMo 29.8 Official leaderboard
9 IOL-Research 26.8 Official leaderboard
10 Llama 3-70B 26.2 Apr 2024 Official leaderboard
11 GPT-4 Jun 2023 26.0 Jun 2023 Official leaderboard
12 Aya23 23.5 Official leaderboard
13 Command R+ 23.3 Aug 2024 Official leaderboard
14 IKUN-C 16.7 Official leaderboard
15 IKUN 16.4 Official leaderboard
16 CycleL 0.78 Official leaderboard
#ModelScoreSettingDateSource
1 Llama 3-70B 26.2 Apr 2024 Official leaderboard
2 GPT-4 Jun 2023 26.0 Jun 2023 Official leaderboard
3 Command R+ 23.3 Aug 2024 Official leaderboard

Rankings by part

We read 6 parts from the benchmark’s paper, each ranking models on one part of the test, such as Education, General and Judicial. Llama 3-70B leads 3 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Education

3 models we track have a score here.

  1. 1 Llama 3-70B 45.7
  2. 2 GPT-4 Jun 2023 40.9
  3. 3 Command R+ 35.3

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Meta
Benchmark paper Not tested since Aug 2024

Source: The Domain Dynamics English-Hindi Translation paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper
23.0 24.0 25.0 26.0 27.0 2023 2024 23.0 24.0 25.0 26.0 27.0 2023 2024

Source: Official Domain Dynamics English-Hindi Translation 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

8 of 9 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 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (16 entries).
  • Pass Models scored 3 models we track, plus 13 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).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 3 rows for models we track and 13 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