Unverified50% confidenceBenchmarkExact time
Publicly available reasoning models, with appropriate prompting, can solve all 6 problems of the 2025 IMO.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/23/2026
First Seen
Valid until: 12/22/2026
Sources
Related Entities
Related Claims
UnverifiedIn the second year after 2024, models from multiple institutions were able to solve all IMO problems except the last one.73% similarUnverifiedIn the 2024 IMO test, AlphaProof solved multiple problems including the most difficult Problem 6.67% similarUnverified到2026年，评判AI编程工具的核心指标将变为四个系统级能力：能不能分工、能不能隔离、能不能审计、能不能自己跑到交付66% similarUnverifiedAround 2018, statistical language model-based code completion began to emerge, capable of predicting the next token based on context.66% similarUnverifiedContext engineering is a concept that emerged in 2025, focusing on how to systematically manage the complete context fed to a model.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/943013API
curl https://kongchang.com/api/v1/knowledge/claims/943013MCP
get_claim(id=943013)