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
- Claude Code overtakes Cursor and Copilot in job-post mentions ahead of Anthropic IPO — antgoldbloom · 2026-11-19
- Dev submits PR adding periodic checkpoints to GKE sandboxes so agents don't lose progress — yoimnotkesku · 2026-11-19
- AWS adds private CA support to Bedrock AgentCore Identity for connecting agents to self-hosted IdPs — AWS ML Blog · 2026-11-19
- Orchestrator's Cloud Agents graduate from beta to general availability — julianweisser · 2026-11-19
- Zero users, 33 pages shipped: dev crowdsources audit for AI-agent trust schema — TheHamzaShahbaz · 2026-11-19
- She vibecoded her own photobooth with Claude Code — and shared the prompt — toolstelegraph · 2026-11-19