Jev capability atlas

A bilingual (Traditional Chinese / English) evidence map of where Jev holds up and where it breaks, with API-call receipts under suites/. Its thesis: success tracks whether the answer is derivable from the supplied state rather than from outside knowledge.

Notes

AG News 91%, Banking77 87%, DAIR Emotion 48%; average reported confidence 0.819.

author demo — Result shown by its author. About this label

Destinations

Filed under

• #benchmark
• #calibration
• #github

In collections

• Benchmarks & independent tests →