AI cracks second FrontierMath benchmark problem on absolute Galois groups, signaling a shift for computational research

Share

Anthropic’s Claude Fable 5 and OpenAI’s GPT-5.5 Pro independently solved the same number theory problem involving the absolute Galois group of the 2-adic numbers. Epoch AI’s FrontierMath benchmark recorded its second verified solution on June 24, 2026, with Claude Fable 5 reaching the solution first on June 9, followed by GPT-5.5 Pro fifteen days later. This type of problem, classified as a solid result in number theory, would typically require one to three months of work for human experts. The mathematical community notes, however, that the complete verification of the AI-generated proofs is still ongoing as of July 6, 2026.

Source: Read the original article

Telemac
Telemachttp://cryptoinfo.ch
Passionné de nouvelles technologies, j’explore l’univers de la blockchain et des cryptomonnaies pour partager l’actualité et les innovations du secteur.

Lire la Suite

Articles