Skip to content

Open research problems solved by AI (FrontierMath Erdős)

Share of 68 significant open Erdős problems a model solves with a machine-checked proof, in one attempt with a ~$300 budget.

Topics: Mathematics, Benchmarks

What this measures: Unlike exam-style tests, nobody knew the answers to these problems when the test was made. A model only scores if the Lean proof checker accepts its proof or disproof.

0%5%10%15%20%

Plotted at model release dates (the benchmark launched 1 September 2026, so earlier models were evaluated retroactively). Outside the official one-attempt rules, 17 of the 68 problems have now been solved by some means, including 12 credited to OpenAI's 6 October research release. Contamination risk grows as solutions are published.

Source: Epoch AIData as of 9 Nov 2026
Show data table and sources
DateLabelValue
23 Apr 2026GPT-5.50%
3 Sept 2026GPT-6 Astra (pre-release)2.9%
29 Sept 2026GPT-6.1 Sol4.4%

Entries with this chart