G-harness-evals: Which agent harness does tasks best, for the least cost?
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
A benchmark by Garry Tan's g-harness-evals project compares agent harnesses (Claude Code, Codex, Hermes Agent, OpenClaw, and QM's Pi loop) on 20 public multi-user tasks, holding the model fixed at Opus 5.5 or GPT-6.1 Sol.