index / hgqimo/JevRanker
JevRanker
Jev-style decision models as BlitzRank's compare oracle: k passages scored in one parallel forward pass, zero decoded tokens — 22x faster per match than a generative listwise LLM, at 2.9x its nDCG@10.
Research and EvalsRankingListedPython
Repository
Stars4
LanguagePython
LicenseMIT
Created2026-09-22
Last pushed2026-09-22
Officialno
Judgment
Genuine Jev project0.90
gate 0.5
Uses Jev at runtime0.89
Is a meta list0.03
Is a reimplementation0.77
Quality scales
Substance1.79 / 3
gate 0.5
Docs2.88 / 3
Novelty2.32 / 3
Composite score0.76
Category distribution
Research and Evals0.89
Integrations0.11
Other0.00
SDKs and Clients0.00
Games and Simulation0.00
Learning0.00
Agent and Dev Tooling0.00
Applications0.00
Assigned categoryResearch and Evals
Category probability0.89
Category confidence0.87
PatternRanking
Pattern confidence1.00
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:jev in:name,description,readme created:2026-09-22
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-09-22 11:44 UTC