NEAR AI's Lean Agent Solves All 672 PutnamBench Problems for $111, 250x Cheaper Than Rivals

According to NEAR Protocol co-founder Alex Skidanov, on September 6, NEAR AI's open-source Lean agent solved all 672 problems in the PutnamBench benchmark for $111, compared to $25,000 or more for competing systems—a 250x cost advantage. PutnamBench is a formal evaluation suite for AI theorem-provers, with problems encoded in Lean 4 requiring machine-verifiable mathematical proofs. The dramatic cost reduction enables broader access to AI verification tools and supports NEAR's vision around confidential and verifiable AI infrastructure.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments