Benchmark Almanac

MKQA

RoBERTa (MKQA fine-tuned) 36.8% tops its leaderboard
Not in model cards

Models answer 10,000 open-domain questions translated into 26 languages. Exact match and token F1 measure agreement with human answers, including unanswerable questions.

Questions originate in Natural Questions, but the makers collected passage-independent answers. Each language can have several accepted answer forms.

Made by
Apple
Released
July 2020
Kind
Knowledge in many languages
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Many languages
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Many languages

In the authors’ words

Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets. We introduce Multilingual Knowledge Questions and Answers (MKQA), an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). Answers are based on a heavily curated, language-independent data representation, making results comparable across languages and independent of language-specific passages. With 26 languages, this dataset supplies the widest range of languages to-date for evaluating question answering. We benchmark a variety of state-of-the-art methods and baselines for generative and extractive question answering, trained on Natural Questions, in zero shot and translation settings. Results indicate this dataset is challenging even in English, but especially in low-resource languages

Abstract of MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering (arXiv:2007.15207, CC0)
3
Entries in its paper, 0 models we track

RoBERTa (MKQA fine-tuned) tops the leaderboard with 36.8%

Best score per entry from the benchmark's paper, read on November 18th, 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.

  1. 1 RoBERTa (MKQA fine-tuned) query translation: Test; answer translation: Test 36.8%
  2. 2 mT5 (MKQA fine-tuned) query translation: -; answer translation: - 35%
  3. 3 Xlm-R (MKQA fine-tuned) query translation: -; answer translation: - 34.1%

Source: The MKQA paper

#EntryScoreSettingDateSource
1 RoBERTa (MKQA fine-tuned) 36.8% query translation: Test; answer translation: Test, DPR Official leaderboard
2 mT5 (MKQA fine-tuned) 35% query translation: -; answer translation: -, Query-only Official leaderboard
3 Xlm-R (MKQA fine-tuned) 34.1% query translation: -; answer translation: -, Elasticsearch* Official 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

All 7 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
  • Pass Independent runs Scores from the benchmark’s paper (3 entries).
  • Note Models scored 3 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 3 entries at the last read, none a model we track.
  • Pass Last read November 18th, 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