index / softpudding/jev-frontier-100
jev-frontier-100
100 original tasks comparing Jev with Qwen3.5 0.8B, 2B and 4B across three reasoning budgets; reproducible results and token logprobs.
Research and EvalsFeature ScoringListedPython
Repository
Stars0
LanguagePython
LicenseMIT
Created2026-09-19
Last pushed2026-09-19
Officialno
Judgment
Genuine Jev project0.97
gate 0.5
Uses Jev at runtime0.87
Is a meta list0.05
Is a reimplementation0.08
Quality scales
Substance2.03 / 3
gate 0.5
Docs2.77 / 3
Novelty2.93 / 3
Composite score0.83
Category distribution
Research and Evals1.00
Integrations0.00
Learning0.00
SDKs and Clients0.00
Games and Simulation0.00
Applications0.00
Other0.00
Agent and Dev Tooling0.00
Assigned categoryResearch and Evals
Category probability1.00
Category confidence1.00
PatternFeature Scoring
Pattern confidence0.64
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:topic:jev
- search:jev in:name,description,readme created:2026-09-19
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-09-19 10:54 UTC