AI Solved 27 Math Problems, Averaging 47 Years Open
OwariDa · x · 2026-07-26
A researcher tracked recent math problems successfully solved by AI, with the total number reaching 27. These achievements demonstrate the breakthroughs of large models in rigorous logical reasoning.
Among the 16 specifically analyzed problems:
- Resolution Methods: 9 were disproved by counterexamples (56.3%), and 7 were solved through rigorous proofs (43.8%).
- Formal Verification: 10 problems have formal proofs (62.5%), and 8 found exact finite witnesses.
- Problem Difficulty: Among the 11 problems with known posing dates, they had been open for an average of 47 years.
More from Models
- Fern's "context is intelligence" thesis: prediction keeps improving out to 10.2M tokens — bneyshabur · 2026-10-26
- Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context — bneyshabur · 2026-10-26
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26