Study: coding agent frameworks have little effect on pass rates
What happened
Liu 和 Han 的研究用 Claude Code、OpenCode、mini-SWE-agent 三个框架跑 Qwen3.6、Qwen3.8、Deepseek-V4-Flash、GLM-5.3-Flash、HY4-Preview 等模型，发现换框架带来的成绩变化与同一配置重跑一次的波动相当，在 447 个任务上最重和最轻的框架差距不到 2 分。
From The Decoder
Timeline
Follow the reports to see the event from each side.
- The DecoderFancy harnesses make coding agents more expensive but not better, study finds
A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup. Cost per task, however, can triple, driven mainly by the system prompt that gets resent with every step.
Heat of this event
Current heat 9·Peak in the comparable range 10（Oct 24 19:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.