wangmt 在 佬们，有没有消息，deepseek-code Harness 工具什么时候出来啊，官方发的v4flash评分很高啊 中发帖

*For public Code Agent tasks, V4-Flash was tested using our upcoming DeepSeek Harness (minimal mode) 
framework. Settings: max tier, topp=0.95, temperature=1.0. 
** DSBench-FullStack (full-stack dev) & DSBench-Hard (Coding Agent challenges) are our internal benchmark sets. 
 [image]
 
 
Back to Top