WMT24++
Progress Over Time
Interactive timeline showing model performance evolution on WMT24++
WMT24++ Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | 120B | — | — | |||
| 2 | 32B | 262K | $0.06 / $0.24 | |||
| 3 |  Alibaba Cloud / Qwen Team | — | 1.0M | $1.25 / $3.75 | ||
| 4 | Alibaba Cloud / Qwen Team | — | 1.0M | $0.32 / $1.28 | ||
| 5 | Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 6 | 550B | — | — | |||
| 7 |  Cohere | 218B | — | — | ||
| 8 | Alibaba Cloud / Qwen Team | 397B | — | — | ||
| 9 | Alibaba Cloud / Qwen Team | 122B | — | — | ||
| 10 | Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 11 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 12 | Alibaba Cloud / Qwen Team | 9B | — | — | ||
| 13 | Alibaba Cloud / Qwen Team | 4B | — | — | ||
| 14 |  Google | 27B | — | — | ||
| 15 | Google | 12B | — | — | ||
| 16 | Google | 8B | — | — | ||
| 16 | 2B | — | — | |||
| 18 | Google | 4B | — | — | ||
| 19 | Alibaba Cloud / Qwen Team | 2B | — | — | ||
| 20 | 2B | — | — | |||
| 20 | Google | 8B | — | — | ||
| 22 | Google | 1B | — | — | ||
| 23 | Alibaba Cloud / Qwen Team | 800M | — | — |
What is WMT24++?
WMT24++ is a comprehensive multilingual machine translation benchmark that expands the WMT24 dataset to cover 55 languages and dialects. It includes human-written references and post-edits across four domains (literary, news, social, and speech) to evaluate machine translation systems and large language models across diverse linguistic contexts.
WMT24++ is a text benchmark evaluating models on language tasks. LLM Stats tracks 23 models on this benchmark, scored on a 0–1 scale. The current average is 0.6, with the leader at 0.9.
Compare leaders on the best AI for language leaderboards.
Current leaders
Nemotron 3 Super (120B A12B) from NVIDIA currently leads the WMT24++ leaderboard with a score of 0.867 across 23 evaluated AI models.
Source paper
- Title
- WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects
- Authors
- Daniel Deutsch, Eleftheria Briakou, Isaac Caswell, Mara Finkelstein, and 13 others
- Published
- arXiv
- 2502.12404
Abstract
As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages and dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. The dataset covers four domains: literary, news, social, and speech. We benchmark a variety of MT providers and LLMs on the collected dataset using automatic metrics and find that LLMs are the best-performing MT systems in all 55 languages. These results should be confirmed using a human-based evaluation, which we leave for future work.
FAQ
Common questions about the WMT24++ benchmark and leaderboard.