RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence Paper • 2512.02622 • Published 26 days ago • 9 • 2
Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning Paper • 2506.10521 • Published Jun 12 • 73 • 4