Benchmark Almanac

CAPR-ja

Aya Expanse 32B 93% leads since July 2026
Not in model cards

Models read a Japanese scenario and choose the best matching proverb from four options. The authors score exact choices.

The makers rank 14 models on 100 scenarios. Every test target proverb also appears as a distractor in the training choices.

Released
July 2026
Kind
Reasoning in many languages
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Japanese
In and out
Text → Text
Interaction
Single turn
Items from
Generated
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Qwen3-32B #135 on the capability index
Last model added
August 2025
Scores refreshed
November 20th, 2026
14
Entries on its own leaderboard, 12 models we track

Aya Expanse 32B leads with 93% among models released by August 2025 Aya Expanse 32B leads with 93% among models released by August 2025

Best score per entry from the benchmark's own leaderboard, read on November 20th, 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. This view shows only models we track, each at its best.

The newest model with a score here came out in August 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Aya Expanse 32B zero_shot 93%
  2. 2 Qwen3-14B zero_shot 91%
  3. 3 Qwen3-32B zero_shot 89%
  4. 4 Gemma 3 27B zero_shot 86%
  5. 5 Gemma 3 12B zero_shot 85%
  6. 6 aya:35b zero_shot 80%
  7. 7 Qwen3-8B zero_shot 77%
  8. 8 Qwen3-4B zero_shot 77%
  9. 9 Aya Expanse 8B zero_shot 76%
  10. 10 aya:8b zero_shot 62%
  11. 11 Gemma 3 4B zero_shot 55%
  12. 12 Qwen3-1.7B zero_shot 38%
  13. 13 Gemma 3 1B zero_shot 28%
  14. 14 Gemma 3 270M zero_shot 22%

Source: Official CAPR-ja leaderboard

#EntryScoreSettingDateSource
1 Aya Expanse 32B 93% zero_shot Oct 2024 Official leaderboard
2 Qwen3-14B 91% zero_shot Apr 2025 Official leaderboard
3 Qwen3-32B 89% zero_shot Apr 2025 Official leaderboard
4 Gemma 3 27B 86% zero_shot Mar 2025 Official leaderboard
5 Gemma 3 12B 85% zero_shot Mar 2025 Official leaderboard
6 aya:35b 80% zero_shot Official leaderboard
7 Qwen3-8B 77% zero_shot Apr 2025 Official leaderboard
8 Qwen3-4B 77% zero_shot Apr 2025 Official leaderboard
9 Aya Expanse 8B 76% zero_shot Oct 2024 Official leaderboard
10 aya:8b 62% zero_shot Official leaderboard
11 Gemma 3 4B 55% zero_shot Mar 2025 Official leaderboard
12 Qwen3-1.7B 38% zero_shot Apr 2025 Official leaderboard
13 Gemma 3 1B 28% zero_shot Mar 2025 Official leaderboard
14 Gemma 3 270M 22% zero_shot Aug 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Aya Expanse 32B 93% zero_shot Oct 2024 Official leaderboard
2 Qwen3-14B 91% zero_shot Apr 2025 Official leaderboard
3 Qwen3-32B 89% zero_shot Apr 2025 Official leaderboard
4 Gemma 3 27B 86% zero_shot Mar 2025 Official leaderboard
5 Gemma 3 12B 85% zero_shot Mar 2025 Official leaderboard
6 Qwen3-8B 77% zero_shot Apr 2025 Official leaderboard
7 Qwen3-4B 77% zero_shot Apr 2025 Official leaderboard
8 Aya Expanse 8B 76% zero_shot Oct 2024 Official leaderboard
9 Gemma 3 4B 55% zero_shot Mar 2025 Official leaderboard
10 Qwen3-1.7B 38% zero_shot Apr 2025 Official leaderboard
11 Gemma 3 1B 28% zero_shot Mar 2025 Official leaderboard
12 Gemma 3 270M 22% zero_shot Aug 2025 Official leaderboard

Number one over time

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

Cohere
Own leaderboard Passed 85% in Jul 2026, by Aya Expanse 32B

Source: Official CAPR-ja leaderboard

Aya Expanse 32B on the official leaderboard passed 85% in October 2024

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Aya Expanse 32B 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Aya Expanse 32B

Source: Official CAPR-ja 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.

Versions

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 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (14 entries).
  • Pass Models scored 12 models we track, plus 2 other entries on its leaderboard.
  • Note Newest score The newest came 15 months ago, in August 2025, for Gemma 3 270M. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Qwen3-32B (#135).
  • Note Headroom Saturated. The best is 93%, past 85% since October 2024.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 12 rows for models we track and 2 other entries at the last read.
  • Pass Last read November 20th, 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