Model Releases

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 …

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 i

DGX agentx-post
model-releasessebastian-raschka--x

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... We ran Kimi K3 through 3 agent harnesses (Claude Code, Hermes, Kimi Code) on 28 identical tasks. All 3 harnesses completed the tasks at similar success rates, but the interesting story is token efficiency: the same task cost up to 30x more tokens depending on the harness. 🧵🧵

Related

Source: Sebastian Raschka (X) | 2026-07-30

Loading related sources…