Test Shows Claude Code Consumes 6x More Tokens Per Task Than Kimi Code
zainhas · x · 2026-07-30
Testing data from Composio reveals massive differences in token consumption among coding agents performing the same tasks. The median task in Claude Code consumed roughly 340k tokens, compared to just 61k in Kimi Code.
Factoring in model pricing, the average cost per task was only $0.22 for Kimi Code, versus $2.00 for Claude Code. Input tokens typically make up about 95% of the workload in agentic operations.
Related event: Composio Test: Agent Frameworks Show 30x Token Gap(7 posts)→
More from coding & agent
- Reflection's Beam, a 501B-parameter open MoE model with 1M context, lands on Hugging Face under Apache 2.0 — QGallouedec · 2026-10-16
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- Office-editing tool calls need file, worktree and unit: lessons from dsh-univer-office — FunDistribution6537 · 2026-10-16
- Architect MD workflow: Gemini one-shot outputs that beat Opus, via 5-lens plan critique — oikk01 · 2026-10-16
- Prove a coding agent actually ran the tests: check artifacts, not approvals — ComprehensiveShake76 · 2026-10-16
- Building an acceptance harness for AI spreadsheet edits: allowlists, recalc checks, idempotency — ukdicha-modakkk · 2026-10-16