Repo · Benchmarks & research
shade-arena-jev-monitor
Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.
Open github.com ↗How builders describe it
A fork of the SHADE-Arena public split that evaluates TypeSafe Jev as a monitor for covert agent sabotage, against Gemini 2.5 Flash and Pro. Thirteen hand-built transcripts across three tasks, 353 tool calls, and a full LaTeX report.
The decision Jev makes
Benchmark questions with known answers, to check accuracy and confidence.
Where it fits
Head-to-head tests, calibration studies and independent research into how well Jev decides, how fast, and at what cost. All 682 benchmarks & research projects →
Related projects
Benchmarks & researchMicaA 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.GitHub · ★ 37 · akivet
Benchmarks & researchawesome-jev-papers📄 Research papers on Jev, TypeSafe's System One model, and the open models built in its shape.GitHub · ★ 5 · OmniJev
Benchmarks & researchjev-typesafe-real-financial-use-casesFifty real-world financial use cases for TypeSafe's Jev model: typed, structured LLM answers over ledgers, fraud, portfolios, trades and filings,…GitHub · ★ 3 · IslamBaraka90
Benchmarks & researchjev-healthcare-labOpen experiment comparing TypeSafe Jev vs DeepSeek on 96 healthcare tasks across 12 scenarios (quality, latency, cost) with per-task data and…GitHub · JuneYaooo
Benchmarks & researchtypesafe-jev-ecosystemExplore the TypeSafe Jev ecosystem: open-source integrations, compatible decision models, SDKs, agent tools, and research.GitHub · ★ 4 · VoltAgent
Benchmarks & researchBeelineBenchHow well do decision models plan across a multi-step problem?GitHub · ★ 3 · kyle-pena-nlp