All news

Matching stories Newest first

1. Oct 20
   HHugging Face PapersResearch

   OR-License benchmark tests LLM agents on real operations research engagements

   Across 11 frontier LLMs in coding-agent harnesses, several beat the expert reference on objective quality, but none matches its Deployment-Adjusted Quality score. 87 against the expert reference of 1.

   • Lab: Anthropic
   • Model: Claude Code
   • Topic: research
   • Topic: benchmark
   • Topic: agents