Benchmark expert says his millennium-problem example aged too fast
Princeton benchmark researcher Ofir Press quipped that Millennium Prize problems would take 100 years to saturate as benchmarks, then admitted he was too conservative as frontier models already excel at finding counterexamples and disproving conjectures.
2026-09-09 ~ 2026-09-09 · 3 related posts
- Ofir Press jokes his "millennium prizes would take 100 years to saturate" benchmark line aged badly — OfirPress · 2026-09-09
- Benchmark researcher Ofir Press jokes he'll stop saying millennium problems are too hard to saturate — OfirPress · 2026-09-09
- Frontier models ace counterexamples but lag on closed-form math, benchmark designer notes — evijit · 2026-09-09