XTREME-R
Multilingual models are fine-tuned on English data and tested on 10 tasks in 50 typologically diverse languages, including harder language-agnostic retrieval tasks. It extends XTREME and adds MultiCheckList, a multilingual diagnostic suite.
It shares the XTREME repository and leaderboard site. Like XTREME, it targets fine-tuned encoders, not prompted chat models.
- Made by
- Google Research and DeepMind with collaborators
- Released
- April 2021
- Kind
- Reading in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
In the authors’ words
Machine learning has brought striking advances in multilingual natural language processing capabilities over the past year. For example, the latest techniques have improved the state-of-the-art performance on the XTREME multilingual benchmark by more than 13 points. While a sizeable gap to human-level performance remains, improvements have been easier to achieve in some tasks than in others. This paper analyzes the current state of cross-lingual transfer learning and summarizes some lessons learned. In order to catalyze meaningful progress, we extend XTREME to XTREME-R, which consists of an improved set of ten natural language understanding tasks, including challenging language-agnostic retrieval tasks, and covers 50 typologically diverse languages. In addition, we provide a massively multilingual diagnostic suite (MultiCheckList) and fine-grained multi-dataset evaluation capabilities through an interactive public leaderboard to gain a better understanding of such models. The leaderboard and code for XTREME-R will be made available at https://sites.research.google/xtreme and https://github.com/google-research/xtreme respectively.
XLM-R Large tops the leaderboard with 65.3
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. 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.
- 1 XLM-R Large English supervised, zero-shot transfer 65.3
- 2 mT5-XXL English supervised, zero-shot transfer 64.6
- 3 mBERT English supervised, zero-shot transfer 54.1
Source: Official XTREME-R leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | XLM-R Large | 65.3 | English supervised, zero-shot transfer | Official leaderboard | |
| 2 | mT5-XXL | 64.6 | English supervised, zero-shot transfer | Official leaderboard | |
| 3 | mBERT | 54.1 | English supervised, zero-shot transfer | Official leaderboard |
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
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.
Nemotron 3 Ultra 550B-A55B Base 90.1% - 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%