Benchmark Almanac

Multilingual Understanding

Qwen2.5-72B 89.6% leads since September 2024
Dropped

Models answer five multilingual comprehension sets, BELEBELE, XCOPA, XWinograd, XStoryCloze, and PAWS-X. Qwen reports the average accuracy.

This is a Qwen composite score, not a standalone benchmark.

Released
February 2024
Kind
Reasoning in many languages
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Strongest model tested
Qwen2.5-72B #165 on the capability index
Last in a launch post
September 2024, dropped after it saturated
Last model added
September 2024
3
Models scored in lab cards
3
Launch posts list it, from 1 lab

Qwen2.5-72B leads with 89.6% among models released by September 2024

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.

The newest model with a score here came out in September 2024, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 89.6 Qwen2.5-72B
  2. 80.7 Qwen2-72B
  3. 78.2 Qwen1.5-72B
  1. 1 Qwen2.5-72B 89.6%
  2. 2 Qwen2-72B 80.7%
  3. 3 Qwen1.5-72B 78.2%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Qwen2.5-72B 89.6% Sep 2024 Lab model card
2 Qwen2-72B 80.7% Jun 2024 Lab model card
3 Qwen1.5-72B 78.2% Feb 2024 Lab model card

3 models have held number one in labs’ own numbers since its release in February 2024

Lab claims count from the day the card came out, independent runs from the model’s release.

Qwen
Lab claims Passed 85% in Sep 2024, by Qwen2.5-72B
Qwen2.5-72B 89.6%

Source: Labs’ model cards

Qwen’s own number for Qwen2.5-72B passed 85% in September 2024

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Qwen2.5-72B Qwen2-72B Qwen1.5-72B 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Qwen2.5-72B Qwen2-72B

Source: Labs’ model cards

Labs dropped it from launch posts once the best score passed 85%

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.

Qwen
DateLaunch postScoreAs the post writes it
Sep 19, 2024 Qwen2.5-72B 89.6 Multi-Understanding
Jun 7, 2024 Qwen2-72B 80.7 Multi-Understanding
Feb 5, 2024 Qwen1.5-72B 78.2 Multilingual Understanding (BELEBELE, XWinograd, XCOPA, PAWS-X, XStoryCloze)

More in Multilingual

All 120 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%