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: Tests Show Massive Token Cost Gap Among AI Agent Frameworks(5 posts)→

Original post →

More from coding & agent

coding & agent channel →