PRiSM: An Agentic Multimodal Benchmark for Scientific Reasoning via Python-Grounded Evaluation

Shima Imani(University of California, Riverside), Babak Damavandi(Meta (Israel)), Adel Ahmadyan, Kirmani Ahmed, Seungwhan Moon, Lu Zhang
arXiv (Cornell University)
December 5, 2025
Cited by 0


Related Papers