multilingual-support changedbuild-with-claude/multilingual-support
Nearest release: v2.1.321, published under an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+17added
Lines−15removed
From line
5
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits15to this page, all time
The whole hunk
from line 5, old and new numbered
/
from line 5
55featureMetadata:
66 status: stable
77 supportedModels:
8 - claude-fable-5-2
9 - claude-mythos-5-2
810 - claude-fable-5-1
911 - claude-mythos-5-1
1012 - claude-fable-5
from line 43
4143
4244The following table shows zero-shot scores for Claude models on [Global-MMLU](https://arxiv.org/abs/2412.03304), which extends the [MMLU (Massive Multitask Language Understanding)](https://en.wikipedia.org/wiki/MMLU) test set to 42 languages. Each score is a percentage of the same model’s English score:
4345
44| Language | Claude Fable 5.1 | Claude Opus 5.5 | Claude Sonnet 5.5 | Claude Haiku 5.5 |
46| Language | Claude Fable 5.2 | Claude Opus 5.5 | Claude Sonnet 5.5 | Claude Haiku 5.5 |
4547| -------------------- | ---------------- | --------------- | ----------------- | ---------------- |
4648| English | 100% | 100% | 100% | 100% |
47| Spanish | 99.4% | 99.3% | 99.0% | 98.1% |
48| Portuguese (Brazil) | 99.0% | 99.2% | 98.7% | 98.1% |
49| Italian | 99.0% | 99.2% | 98.4% | 97.7% |
50| French | 99.0% | 99.3% | 98.7% | 97.7% |
51| Indonesian | 98.9% | 99.1% | 98.6% | 97.1% |
52| German | 99.1% | 99.1% | 98.5% | 97.4% |
53| Arabic | 98.7% | 99.3% | 98.3% | 96.6% |
54| Chinese (Simplified) | 98.8% | 99.3% | 98.5% | 97.7% |
55| Korean | 98.8% | 99.1% | 98.3% | 97.0% |
56| Japanese | 98.7% | 99.2% | 98.4% | 97.4% |
57| Hindi | 98.9% | 99.2% | 98.5% | 96.6% |
58| Bengali | 98.3% | 98.6% | 97.2% | 95.4% |
59| Swahili | 97.7% | 98.3% | 96.9% | 94.0% |
60| Yoruba | 95.1% | 96.3% | 93.6% | 87.0% |
49| Spanish | 99.8% | 99.3% | 99.0% | 98.1% |
50| Portuguese (Brazil) | 99.4% | 99.2% | 98.7% | 98.1% |
51| Italian | 99.5% | 99.2% | 98.4% | 97.7% |
52| French | 99.6% | 99.3% | 98.7% | 97.7% |
53| Indonesian | 99.4% | 99.1% | 98.6% | 97.1% |
54| German | 99.5% | 99.1% | 98.5% | 97.4% |
55| Arabic | 99.6% | 99.3% | 98.3% | 96.6% |
56| Chinese (Simplified) | 99.6% | 99.3% | 98.5% | 97.7% |
57| Korean | 99.6% | 99.1% | 98.3% | 97.0% |
58| Japanese | 99.5% | 99.2% | 98.4% | 97.4% |
59| Hindi | 99.4% | 99.2% | 98.5% | 96.6% |
60| Bengali | 99.2% | 98.6% | 97.2% | 95.4% |
61| Swahili | 99.2% | 98.3% | 96.9% | 94.0% |
62| Yoruba | 98.5% | 96.3% | 93.6% | 87.0% |
6163
6264All scores use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) at the `max` [effort level](https://platform.claude.com/docs/en/build-with-claude/effort). Scores exclude questions that safety classifiers blocked or that went unanswered. For each score in the table, at most 1.7 percent of the questions are excluded.
6365
No line in this hunk matches that.