GPT-6 Astra Solves Final FrontierMath Tier 4 Problem, Saturating the Benchmark in ~14 Months
soumitrashukla9 · x · 2026-09-11
Epoch AI confirms GPT-6 Astra solved the last remaining FrontierMath Tier 4 problem, meaning AI has now solved every research-level math question on the benchmark — roughly 14 months after launch. The problems were designed to take expert mathematicians hours or days; mathematicians previously noted AI often found unintended shortcuts, but this final problem (by Jay Pantone) was solved without any. Another striking data point on how fast frontier benchmarks saturate.
Related event: GPT-6 Astra Solves Every FrontierMath Tier 4 Problem(4 posts)→
More from Models
- Models got less conversational as they got agentic — here's how to get a thinking partner back — evielync · 2026-09-11
- KV cache gets QAT too: why this model beats others at fp4 KV cache — stochasticchasm · 2026-09-11
- Dev finally ships his Tamagotchi-style IFS therapy app on the 5th try with GPT Astra — brandon_galang · 2026-09-11
- OpenAI pauses Pro subscription sign-ups citing system strain from demand — TechCrunch AI · 2026-09-11
- A 'Flash' Model Is Now 512GB — 100GB Used to Be Considered Huge — Terminator857 · 2026-09-11
- User suspects Ox Alpha and GLM 5.3 Flash outputs were secretly routed to Claude — liminal_bardo · 2026-09-11