index / bansal1600/jev-as-a-judge-benchmarking
jev-as-a-judge-benchmarking
A customer-support triage agent running on a local Ollama model, evaluated with deterministic checks plus LLM-as-a-judge, with full tracing in LangSmith.
Research and EvalsFeature ScoringListedPython
Repository
Stars0
LanguagePython
LicenseApache-2.0
Created2026-09-22
Last pushed2026-09-22
Officialno
Judgment
Genuine Jev project0.87
gate 0.5
Uses Jev at runtime0.69
Is a meta list0.03
Is a reimplementation0.07
Quality scales
Substance1.52 / 3
gate 0.5
Docs2.80 / 3
Novelty2.40 / 3
Composite score0.70
Category distribution
Research and Evals1.00
Other0.00
Applications0.00
Games and Simulation0.00
Agent and Dev Tooling0.00
SDKs and Clients0.00
Learning0.00
Integrations0.00
Assigned categoryResearch and Evals
Category probability1.00
Category confidence1.00
PatternFeature Scoring
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 at2026-09-23 11:41 UTC