2026-09-27 · America/Los_Angeles · 社区动态 · #7

autotrust/JEV-27B so far best open-source Jev model

Six public decision benchmarks, one protocol: JEV-27B averages 84.07, TypeSafe Jev 1.13 83.85 Close to Jev at the level of whole probability distributions: mean KL ≈ 0.017 on 25,376 held-out questions labelled with Jev's own outputs. An observer needs about 60 sampled decisions to gather one nat of evidence about which model produced them.

热度 46.0 / 100；排名与评分保留该期记录。