Claude Code Burns 2-3x More Tokens Than Other Agent Harnesses
RexDouglass · x · 2026-07-31
Developer rasbt found in testing that Claude Code consumes 2-3x more tokens compared to other agent harnesses at similar success rates.
A previous benchmark by Composio corroborates this: running the same model (e.g., Kimi K3) through different harnesses on 28 identical tasks showed up to a 30x difference in token consumption, despite similar completion rates. This highlights the massive cost impact of an agent harness's orchestration strategy.
Related event: Composio Test: Agent Frameworks Show 30x Token Gap(7 posts)→
More from coding & agent
- Connected steps are not a workflow: nobody designs the handoff — usehive · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Running PolyStrata + Cline coding agent on a $0-fancy laptop at ~90 tok/s — rpwoerk · 2026-10-16
- How do you attribute agent gains: model training or infrastructure? — jrxna · 2026-10-16
- Feed Claude your books, blogs and top engineers' code for claude.md — 'it now writes better code than me' — blaizedsouza · 2026-10-16
- Open-source /label plugin auto-names and colors Claude Code sessions in one step — hermanschutte · 2026-10-16