Composio's Kimi K3 test finds a 6x token gap between agent harnesses
Across 28 tasks, Kimi Code, Hermes and Claude Code finished at similar rates while median token use ranged from 61,000 to 340,000.
By Ryan Merket · Published
Primary source: Composio on X
Why it matters
Agent economics depend on orchestration as well as model pricing. A poorly matched harness can multiply token use while producing nearly the same completion rate.
Composio, the AI-agent infrastructure company founded by Soham Ganatra (@GanatraSoham) and Karan Vaidya (@KaranVaidya6), said Wednesday that Moonshot AI's Kimi K3 consumed nearly six times as many tokens in Claude Code as it did in Kimi Code while completing the same set of agent tasks at a similar success rate.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.