Beta version: *Information might not be fully accurate. Please report any discrepancies.
Knowledge & Communication
Evaluates breadth and depth of world knowledge, language understanding across multiple languages, and ability to communicate effectively. Covers MMLU, HellaSwag, WMT translations, and real-world task performance.
Top Models
Domain Info
- Benchmarks
- 6
- Models Evaluated
- 74
- Categories
- Knowledge, Multilingual, Real-world