ADAM: A Diverse Archive of Mankind for Evaluating and Enhancing LLMs in Biographical Reasoning Paper • 2509.22991 • Published Sep 26 • 1 • 2
MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment Paper • 2508.17290 • Published Aug 24 • 8 • 3