Riemann-bench: frontier models jump from under 5% to over 70% in six months, NS and UGC solved
echen · x · 2026-10-21
Surge AI's Riemann-bench tests whether AI can tackle research-level problems from top mathematicians, beyond Olympiad math. Six months ago models scored under 5%; today they're above 70% (no 10,000-agent stacking allowed), and Navier-Stokes and UGC have been solved. The team's internal betting pool: the Riemann Hypothesis falls within a year, P vs NP last among Millennium Problems. The benchmark is featured in this year's State of AI report, whose slide also shows FrontierMath Tier 4 going from GPT-5's 22% to GPT-6.1 Sol's 100% in fourteen months, with AI supplying nine of 41 unsolved research solutions.
More from Models
- Ex-Google insider: compute bottlenecks go beyond power; open models replacing frontier APIs — xiaosun86 · 2026-10-21
- Fable 5.5 leak: litellm code shows Anthropic model in staging, launch tipped for Oct 27 — imjustnewatai · 2026-10-21
- Open models below 4-bit struggle at self-iterating 3D asset generation, HF dev finds — mervenoyann · 2026-10-21
- Researcher Finds Two Windows 0-Days, First in 76 Minutes with a Frontier Model — moyix · 2026-10-21
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21