Least sycophantic modern open LLM?

So Kimi K2 is outdated, and so is GPT OSS 120b. Which of the modern open weights models can boast the least sycophancy? I need this both for creative/research assistant usage (sycophancy led me down blind alleys of my own bad ideas many times) and agentic coding (more sycophancy less bug noticing).

中文全文翻译正在补齐，可先查看下方英文原文。

So Kimi K2 is outdated, and so is GPT OSS 120b. Which of the modern open weights models can boast the least sycophancy? I need this both for creative/research assistant usage (sycophancy led me down blind alleys of my own bad ideas many times) and agentic coding (more sycophancy less bug noticing).