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 ↗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 332 benchmarks & research projects →
Related projects
Benchmarks & researchJev 1.13.0 against Hopper on Benchmark HeavenHopper wins three columns, Jev keeps Intelligence.Site · Benchmark Heaven
Benchmarks & researchValenTrain a Jev-like multimodal model by yourself.GitHub · ★ 51 · Liuziyu77
Benchmarks & researchjev-dimabsaTypeSafe Jev baseline for DimABSA (SemEval-2026 Task 3) subtask 1: zero-shot and 3-shot valence-arousal regression.GitHub · ★ 6 · ZhangYiqun018
Benchmarks & researchreflexbenchReflexBench — open benchmark and evaluation harness for System One models and typed decision engines.GitHub · ★ 4 · brida-ai
Benchmarks & researchjev-guardrailsResearch/eval repo that runs the same mock carrier support agent and 25 behavioural guardrail rules behind two backends—chat-model JSON judge vs…GitHub · ★ 3 · deepansh-saxena
Benchmarks & researchtypesafe-jev-calibrate-for-code-reviewAbout calibrating Jev for code reviews.GitHub · ★ 3 · Selmar