Epoch AI launches FrontierMath Erdős benchmark; GPT-6 Astra first to crack two problems
Jsevillamol · x · 2026-09-04
Epoch AI, with Thomas Bloom of erdosproblems.com, announced FrontierMath Erdős, a formal benchmark of 68 significant unsolved Erdős problems (open as of August 2026), formalized in Lean, requiring AI systems to prove or disprove them within a fixed budget.
Background: Erdős problems have become the de facto yardstick for AI math capability — Bloom's site catalogs 1,217 problems, 652 still unsolved. The new benchmark addresses curation rigor, verification, and replicability.
First result: GPT-6 Astra became the first model to crack problems from the set, solving one on graphs with infinite chromatic number (#74) and one in combinatorial number theory (#126), at a few hundred dollars each.
Related event: Epoch AI Launches FrontierMath Erdős Benchmark, Astra Solves 2 of 68(4 posts)→
More from Research
- Percolation Dynamics in Optimization: Variance Cascades in SGD, Adam and AdamW — Sai Niranjan Ramachandran · 2026-09-04
- Compile by Training: Distilling Natural-Language Specs into Local Neural Functions — UWaterloo · 2026-09-04
- CORD: Post-hoc Calibration Repair That Exactly Preserves Top-1 Predictions — Daehwan Kim · 2026-09-04
- Software World: A Simulated GitHub Ecosystem Run by Agents for Multi-Agent Research — PangWeiKoh · 2026-09-04
- HKU team launches The Imitator Game: a 4-level benchmark for intent-level robot imitation — YiMaTweets · 2026-09-04
- New paper: LLM outputs are far less diverse than their training data, and temperature tuning won't fix it — rohanpaul_ai · 2026-09-04