NEAR AI's open-source Lean agent solves all of Putnam Bench for just $111
lukaszkaiser · x · 2026-09-06
NEAR AI's Lean agent solved ALL problems on Putnam Bench—672 problems from the hardest undergraduate math competition in the world—for a total of $111, at 1/250 the cost of the second cheapest submission. The project is fully open source, showing how formal proof agents are driving down the cost of hard mathematical reasoning.
More from coding & agent
- Juggling ChatGPT, Claude and agents, users hunt for a unified AI memory setup — utkuaytac · 2026-09-06
- A 3-person team can't make multi-agent coding work: three context-sharing attempts failed — Practical_Sink401 · 2026-09-06
- Villager sim game built locally on 16GB VRAM with Qwen3.8-27B Q3 quant at 75 tok/s — Fancy-Snow7 · 2026-09-06
- mitsuhiko uses AI agent to build Java-style virtual threads for Python — mitsuhiko · 2026-09-06
- Two-person team spent 12 days and $400+ credits making a 6-min AI short film with Codex + Seedance 2.5 — APPSO · 2026-09-06
- AI Coding Will Prevent Expertise: The 'Expert Novice' Paradox in Dev Skills — bibryam · 2026-09-06