1

Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents

huggingface.co

Doc2Harness is a two-stage benchmark designed to evaluate long-horizon harness engineering for large language model-driven coding agents, where a build model constructs a candidate harness from a contract skeleton and development document, and the frozen harness is then tested end to end using a scripted mock model.

Sign in to suggest

Key sources

  1. SOURCEhuggingface.co
Markdown