index / etsabary/system-1-decision-benchmark
system-1-decision-benchmark
System 1 text decisions: 56 routes, including 30 hosted decision models, 22 local configurations on RTX 2060 and Apple M2, and four reasoning-off LLM references. 1,342 questions across 31 categories; accuracy, speed and cost.
Research and EvalsUnclearListedHTML
Repository
Stars3
LanguageHTML
LicenseMIT
Created2026-10-15
Last pushed2026-10-30
Officialno
Judgment
Genuine Jev project0.72
gate 0.5
Uses Jev at runtime0.33
Is a meta list0.12
Is a reimplementation0.30
Quality scales
Substance2.21 / 3
gate 0.5
Docs1.75 / 3
Novelty2.61 / 3
Composite score0.76
Category distribution
Research and Evals1.00
SDKs and Clients0.00
Integrations0.00
Agent and Dev Tooling0.00
Applications0.00
Games and Simulation0.00
Learning0.00
Other0.00
Assigned categoryResearch and Evals
Category probability1.00
Category confidence1.00
PatternUnclear
Pattern confidence0.22
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
Provenance
Modeljev-1.14.0
Question setv2
Judged at2026-10-30 12:12 UTC