TSR Desk · mathematics · 24 September 2026, 01:00 UTC
FrontierMath Erd\H{o}s
- What
- FrontierMath Erd\H{o}s
- Who
- arxiv.org
- When
- 23 September 2026, 04:00 UTC
- Category
- Mathematics
- Primary source
- https://arxiv.org/abs/2609.25050
- What is not known
- This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
We introduce FrontierMath Erd\H{o}s (FME), a benchmark of 68 Erd\H{o}s problems that are open as of August 2026. It comes from a paper posted to arXiv on 23 September 2026. To solve a task in FME, AI systems must resolve (prove or disprove) one of the 68 conjectures in the proof assistant Lean. Our 68 problems were selected by the second author among 652 open problems on erdosproblems.com for their mathematical interest and difficulty. AIs have recently resolved several open problems in mathematics, but these demonstrations fall short of a systematic study of AI capabilities. FME evaluates every AI model on the same fixed problems, autonomously and under the same budget. We evaluated five AIs with a budget of \$300 per problem. One (GPT-6 Astra) scored 3%, and all others scored 0%.
Why it counts
We introduce FrontierMath Erd\H{o}s (FME), a benchmark of 68 Erd\H{o}s problems that are open as of August 2026.
Sources
Primary source: primary source
What is not known
This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
No clip. The article still stands.