Updated daily at 05:00 UTC
Benchmark
Global-MMLU-Lite
Measures: A human-translated MMLU subset with 200 culturally sensitive and 200 culturally agnostic questions per language (15 languages at launch, 23 in v3.0); multiple-choice accuracy averaged over languages.
- Maintainer
- Cohere Labs
- Introduced
- 2024
- Status
- Active
- Saturation
- Saturated
- Typical provenance
- Mixed
- In scoring set
- No
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results