index / chenyuwang166-oss/metask-jev-rain-12B-trained
metask-jev-rain-12B-trained
MeTask 12B structured decision service: judgments and option probabilities, with downloadable weights for private deployment. Organizer-measured JevBench Capability Score 77.9, #6 and top entry labeled 12B (2026-10-17); model card and leaderboard in README.
Research and EvalsInfraReviewPython
Repository
Stars0
LanguagePython
LicenseNOASSERTION
Created2026-10-11
Last pushed2026-10-17
Officialno
Judgment
Genuine Jev project0.47
gate 0.5
Uses Jev at runtime0.38
Is a meta list0.03
Is a reimplementation0.79
Quality scales
Substance2.11 / 3
gate 0.5
Docs2.22 / 3
Novelty1.74 / 3
Composite score0.68
Category distribution
Research and Evals0.68
Other0.16
Applications0.13
Integrations0.02
SDKs and Clients0.01
Agent and Dev Tooling0.00
Games and Simulation0.00
Learning0.00
Assigned categoryResearch and Evals
Category probability0.68
Category confidence0.63
PatternInfra
Pattern confidence0.45
Curation
StatusReview
Reasongenuine 0.47 below 0.5
README pickno
Overridenone
Sources
- search:jev in:name,description,readme created:2026-10-11
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-10-19 11:47 UTC