X · @rasbt
· X / Twitter
Consistent with what I found with Qwen3.6 a while back: Claude Code uses 2-3x as many tokens than (many) other harnesses at similar success rate. – Un…
Consistent with what I found with Qwen3.6 a while back: Claude Code uses 2-3x as many tokens than (many) other harnesses at similar success rate.- Unoptimized?- Buggy?- Deliberate (coz that helps it in more challenging cases)?Need to find some time to investigate more...Composio: We ran Kimi K3 through 3 agent harnesse