ThinkingCap-Qwen3.6-27B: same accuracy as base Qwen3.6 with ~50% fewer thinking
英文标题：ThinkingCap-Qwen3.6-27B: same accuracy as base Qwen3.6 with ~50% fewer thinking
We rigorously evaluate the resulting checkpoint across general reasoning, non-reasoning multiple-choice question answering, everyday multi-turn conversations, system prompt adherence, safety, math, code and agentic use cases. Due to the high variability of reasoning quality at Qwen-recommende
打开原文相关 7 · 机会 0
中文
We rigorously evaluate the resulting checkpoint across general reasoning, non-reasoning multiple-choice question answering, everyday multi-turn conversations, system prompt adherence, safety, math, code and agentic use cases. Due to the high variability of reasoning quality at Qwen-recommende
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
We rigorously evaluate the resulting checkpoint across general reasoning, non-reasoning multiple-choice question answering, everyday multi-turn conversations, system prompt adherence, safety, math, code and agentic use cases. Due to the high variability of reasoning quality at Qwen-recommende