CulturalRiddles: A Multicultural Benchmark of Riddles Paper • 2610.29968 • Published 19 days ago • 34
Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation Paper • 2504.07072 • Published Apr 9, 2025 • 9
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge Paper • 2411.19799 • Published Nov 29, 2024 • 16