Back to benchmarks & research
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.

Added
2026-09-17
Language
Python
Stars at snapshot
0
Explore repository

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement.

  • Benchmarks & research

    SemIf

    Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

    Python 2,126Details
  • Benchmarks & research

    jev-eval-agent

    Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.

    HTML 95Details
  • Benchmarks & research

    typesafe-ai-benchmark

    This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.

    TypeScript 33Details
  • Benchmarks & research

    jev-on-a-laptop

    Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.

    Python 21Details
  • Benchmarks & research

    open-jev (JoshuaSP)

    Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results

    Python 19Details
  • Benchmarks & research

    openvons

    openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド

    Python 10Details