pplx-decider Beats Jev by 40% Recall in Unofficial Test, But Decision Models Still Immature

Mark Tenenholtz reported that the decision model pplx-decider achieved 40% higher recall than Jev on his private benchmark, though he concluded that decision models still have a long way to go.

2026-10-20 ~ 2026-10-20 · 2 related posts

• Private evals: pplx-decider shows 40% recall gain over Jev decision models — marktenenholtz · 2026-10-20

1 near-duplicate retellings: marktenenholtz