WMT25
North Small Translate 1.0 48.9 Only in system cards Systems translate the WMT25 general task test sets in 16 directions, mostly out of English. New pairs include English to Bhojpuri, Korean and Maasai. Humans evaluate the systems.
Blind sets came out on 2025-06-19. A multilingual subtask added the WMT24++ test set.
- Level
- University Undergraduates and entry-level professionals
- Scored
- Graded by people Human experts grade or compare the outputs.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
North Small Translate 1.0 leads with 48.9
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 North Small Translate 1.0 48.9
- 2 Command A Translate -6.30
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | North Small Translate 1.0 | 48.9 | Sep 2026 | Model card | |
| 2 | Command A Translate | -6.30 | Sep 2025 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
3 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 12 Sep 2026 | North Small Translate 1.0 technical report | 48.9 | Long context, one 9,900-word WMT25 General MT document into 9 languages, reference-based xCOMET-XL (Table 1 and Section 3.3). Agentic 47.8 | Capabilities |
| 26 Sep 2025 | Command A Translate technical report | -6.3 | WMT25 test set MetricX-XL Avg, paragraph-level, higher is better (Table 3). Long-context literary domain xComet-XL 51.9, 56.9 for the paragraph-level row (Table 5) | Capabilities |
| 5 Sep 2025 |  Hunyuan-MT-7B technical report | WMT2025 General Machine Translation shared task, the Hunyuan-MT models rank first in 30 of 31 language pairs, no score printed (Abstract) | Capabilities |
Versions
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.
Inkling 88.7% - 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%