index / cicilybiconcave74/jev-snips-benchmark
jev-snips-benchmark
Benchmark Jev's typed-question decision model on SNIPS intent detection and slot filling, testing accuracy with label names, definitions, and few examples.
Research and EvalsFeature ScoringListedPython
Repository
Stars0
LanguagePython
LicenseMIT
Created2026-07-24
Last pushed2026-11-05
Officialno
Judgment
Genuine Jev project0.73
gate 0.5
Uses Jev at runtime0.66
Is a meta list0.04
Is a reimplementation0.36
Quality scales
Substance2.42 / 3
gate 0.5
Docs1.73 / 3
Novelty1.32 / 3
Composite score0.64
Category distribution
Research and Evals0.99
Applications0.01
SDKs and Clients0.00
Integrations0.00
Agent and Dev Tooling0.00
Games and Simulation0.00
Learning0.00
Other0.00
Assigned categoryResearch and Evals
Category probability0.99
Category confidence0.99
PatternFeature Scoring
Pattern confidence0.58
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:topic:typesafe-ai
Provenance
Modeljev-1.14.0
Question setv2
Judged at2026-11-06 13:47 UTC