Global MMLU (GMMLU)
We show this table for reference; we do not rank on it.
MMLU-style knowledge evaluation across 42 high- and low-resource languages.
Benchmark score on GMMLU — November 13, 2026
We compile the GMMLU rows from provider self-reports. Claude Fable 5.2 leads the table at 96.0%, followed by Claude Opus 5.5 (94.3%) and Claude Fable 5.1 (94.0%). We do not use these results to rank models overall.
Claude Fable 5.2
Anthropic
Reported by AnthropicClaude Opus 5.5
Anthropic
Reported by AnthropicClaude Fable 5.1
Anthropic
Reported by Anthropic5 modelsMultilingualRefreshingDisplay onlyUpdated November 13, 2026
Benchmark score table (5 models)
All 5 results on this page were reported by the labs that built the models.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2AnthropicReported by Anthropic | 96.0% | Reported by Anthropic | Not reported | Closed |
| 2 | Claude Opus 5.5AnthropicReported by Anthropic | 94.3% | Reported by Anthropic | Not reported | Closed |
| 3 | Claude Fable 5.1AnthropicReported by Anthropic | 94.0% | Reported by Anthropic | Not reported | Closed |
| 4 | Claude Opus 5AnthropicReported by Anthropic | 92.5% | Reported by Anthropic | Not reported | Closed |
| 5 | Claude Sonnet 5.5AnthropicReported by Anthropic | 92.1% | Reported by Anthropic | Not reported | Closed |
- Lab-reported
- Benchmark-run
- Independent
Among the reported GMMLU rows, Claude Fable 5.2 is first at 96.0%. The third row is 2.0 points behind. The broader top-10 range is 3.9 points, so many of the published results sit in a relatively narrow band.
5 models have been evaluated on GMMLU. The benchmark falls in the Multilingual category. GMMLU is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About GMMLU
Year
2024
Tasks
Knowledge questions across 42 languages
Format
Average accuracy
Difficulty
Multilingual knowledge
Anthropic reports average accuracy from one max-effort trial without tools or a custom system prompt.
Freshness and provenance
Version
GMMLU 2024
Refresh cadence
Annual
Staleness state
Refreshing
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does GMMLU measure?
MMLU-style knowledge evaluation across 42 high- and low-resource languages.
Which model scores highest on GMMLU?
Claude Fable 5.2 by Anthropic currently leads with a score of 96.0% on GMMLU.
How many models are evaluated on GMMLU?
5 AI models have published results on GMMLU in the BenchLM catalog.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.