WMT26
North Small Translate 1.0 83.6 In use Systems translate the WMT26 general task test set in 24 directions, mostly out of English, across several domains with added instructions. The shared task ranks systems by human contrastive ESA judgments.
The blind test set came out on 2026-06-18 and references on 2026-07-27. Cohere scores it with a GPT-5.6-Sol judge on a 0 to 100 scale, which differs from the shared task's human ranking.
- 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 83.6
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.
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | North Small Translate 1.0 | 83.6 | Sep 2026 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 10 Sep 2026 | North Small Translate 1.0 | 83.6 | WMT26 All Languages benchmark score (GPT-5.6-Sol as judge, 0 to 100) |
One system card reports it
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 | 83.6 | WMT26 All languages, GEMBA-ESA style GPT-5.6 Sol judge without references, adequacy and fluency averaged (Tables 1 and 4). Europe 82.0, ME + Asia 86.1, Latin script 82.4, Other scripts 85.4. Agentic 84.4. Per language in Table 6 | 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%