Jevals：用 Jev 做裁判的 LLM 评测框架

Sai Yashwanth @yashwanthsai29原推发布于 2026.09.18

在 X 上打开原推

I built Jevals, an evals framework for LLMs and AI agents. Instead of an LLM judge, grading runs on Jev. So every pass/fail comes with a calibrated confidence you can set a bar on. Cheaper and Faster.

这条是引用着另一条写的：「ChatGPT 联合发明人发布新模型 Jev」