← Back to feed

Evalship – find the flaws in your LLM evals

AI · Products · 2026-11-04 10:03

Evalship是一款面向大模型评测的工具,可在配置阶段修正评测缺陷,并持续监控每次运行结果,辅助优化提示词与模型。

Source: evalship.com


Auto-generated summary for reference only. RSS