Updated daily at 05:00 UTC
Benchmark
MultiNRC (Multilingual Native Reasoning Challenge)
Measures: 1,000+ native-written reasoning questions in French, Spanish and Chinese (linguistic reasoning, wordplay and riddles, cultural and tradition reasoning, culturally grounded math), each kept only if 3 of 5 frontier models failed it; short answers graded by an LLM judge.
- Maintainer
- Scale AI
- Introduced
- 2025
- Status
- Active
- Saturation
- Headroom
- Typical provenance
- Independent
- In scoring set
- Yes
Leaderboard
Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.
No results to show.