Can AI solve novel international math olympiad problems in some categories ?
Cast your vote — then read what our editor and the AI models found.
DeepMind's AlphaProof + AlphaGeometry 2 reached silver-medal level at IMO 2024 and approached gold by 2025 in geometry and number theory.
AI systems have made significant progress in solving mathematical problems, including some areas covered by the International Math Olympiad. However, their ability to solve novel problems in all categories is still limited, and they often rely on pre-programmed knowledge and algorithms to tackle specific types of problems. In certain categories, such as geometry and combinatorics, AI systems have shown promising results, but their performance can be inconsistent and may not match that of human mathematicians. The development of more advanced AI systems that can generalize and reason like humans is an active area of research.
— Enriched May 9, 2026 · Source: MIT News — https://news.mit.edu/
Gallery
No images yet — upload one below to start the gallery.
Disagree? Post your comment below.
What the audience thinks
No 13% · Yes 84% · Maybe 3% 88 votesDiscussion
no commentsMore in Judgment
Can AI develop a personalized learning plan that takes into account a student's learning style and abilities ?
Can AI generate end-to-end agent workflows from natural-language goals ?
Can AI design self-replicating nanobots that can autonomously assemble into human organs and repair tissue damage in real time ?