AI圈报
教程 / 实战普通

Withdrawing, and Sharing Everything We Measured: 1,800+ Trials of a 4B Quantized SWE Agent

信息来源:DEV Community·

内容摘要

Our best custom Gemma 4 agent scored 15/114 vs the zero-think baseline's 16/114. Aggregate results and six findings from 1,800+ trials — no task data, no code.
内容分类AI 教程与实战
内容层级普通情报
发布时间(北京时间)
本站收录时间(北京时间)
信息来源DEV Community
站内情报编号intel-34a2836db4c237869b4bd17d