Verified65% confidenceBenchmarkExact time
DeepMind's AlphaProof and AlphaGeometry, introduced in 2024, together solved 4 out of 6 problems in an IMO test, approaching the gold medal threshold.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
9/9/2026
First Seen
Valid until: 12/8/2026
Sources
Related Entities
Related Claims
Partially VerifiedDeepMind's AlphaProof and AlphaGeometry have demonstrated strong capabilities on International Mathematical Olympiad (IMO)-level problems, but are essentially specialized systems.79% similarVerifiedDeepMind's AlphaProof and AlphaGeometry systems adopt a step-by-step verification approach.75% similarUnverifiedDeepSeek Math V2 is the first open-source model to reach International Mathematical Olympiad (IMO) gold-medal level, solving five out of six IMO problems.73% similarVerifiedDeepMind's AlphaProof combined large language models with Lean 4 in 2024 and used reinforcement learning to self-play in a formal environment to generate and verify proof steps.72% similarUnverifiedDeepMind's Demis Hassabis publicly stated after AlphaGo defeated Lee Sedol in 2016 that AI would achieve breakthroughs on scientific problems such as protein folding, a judgment that was validated four years later by AlphaFold2.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/885689API
curl https://kongchang.com/api/v1/knowledge/claims/885689MCP
get_claim(id=885689)