Unverified50% confidenceBenchmarkExact time
In 2024, a model introduced by Google DeepMind answered 4 out of 6 problems correctly on the IMO exam.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGoogle DeepMind在2023年发表的论文中提出了一个从新兴AGI到超人AGI的五级分类框架75% similarUnverifiedGoogle DeepMind applied reinforcement learning to chip floorplanning in 2019 and published the findings in Nature in 2021, demonstrating that AI can surpass human experts on specific EDA sub-tasks.73% similarVerifiedIn 2024, Google DeepMind's AlphaProof and AlphaGeometry 2 achieved a silver medal level on IMO-level problems for the first time.72% similarVerifiedThe emergent ability phenomenon was systematically documented by the Google DeepMind research team in 2022.71% similarUnverifiedGoogle DeepMind在2023年提出了能力弹性（Capability Elicitation）框架，强调模型的真实行为边界只有在特定触发条件下才会暴露70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/943011API
curl https://kongchang.com/api/v1/knowledge/claims/943011MCP
get_claim(id=943011)