Preprint

MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

Omid Ghahroodi, Arshia Hemmat, Marzia Nouri, Seyed M. H. Hosseini, Doratossadat Dastgheib, Mohammad Vali Sanian, Alireza Sahebi, Reihaneh Zohrabi, Mohammad Hossein Rohban, Ehsaneddin Asgari, Mahdieh Soleymani Baghshah

Figure from MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

The first large-scale Persian multimodal benchmark: roughly 7.5k Persian and 3k English questions with difficulty metadata and recorded student success rates.

A longer write-up of this work is on its way. Until then the paper and the code are the best place to look.