FrontierMath Tier 4 fully solved: GPT-6 Astra cracks the last problem standing
Jsevillamol · x · 2026-09-11
Epoch AI reports that every FrontierMath Tier 4 problem has now been solved by AI, with GPT-6 Astra solving the last one, authored by Jay Pantone. The benchmark's designer adds: the set was built in the o4-mini era with a slow solve rate expected; his January prediction of saturation within nine months proved accurate despite some invalidated problems.
- He admits he still can't solve most of the problems himself, and probably never will.
- Combined with FirstProof results, the chance of finding a problem with a known answer that no vanilla or harnessed AI model can solve is near zero.
- Mathematicians often noted AI found unintended shortcuts on Tier 4 problems — not so for this last one.
His takeaway: our understanding of what is truly hard in mathematics needs a complete rethink.
Related event: GPT-6 Astra Solves Final Problem, FrontierMath Tier 4 Fully Saturated(5 posts)→
More from AGI Musings
- Replit CEO on YC rejections, London office, and 'AI psychosis' among frontier researchers — amasad · 2026-09-11
- Frontier lab's 'AI will make everyone rich, healthy, and free' sparks comms debate — MxMnr · 2026-09-11
- Frontier AI company shares 'Our convictions' statement — MxMnr · 2026-09-11
- Replit CEO backs Sacks: AI 'extinction risk' is not remotely real — amasad · 2026-09-11
- Study something unusual: why Hieroglyphic Luwian beats another ML course — begusgasper · 2026-09-11
- Anthropic Pretraining Researcher Resigns, Slams Labs Racing Toward Superintelligence — nabla_theta · 2026-09-11