New math benchmark reveals AI models confidently solve problems that have no solution
A consortium of 64 mathematicians built SOOHAK, a new AI benchmark with 439 handwritten tasks, including 99 that are deliberately unsolvable. Google's Gemini 3 Pro leads on research-level problems at 30 percent. But no model cracks 50 percent on spotting broken tasks. More compute makes models…
No discussion yet. Be the first to share your thoughts!