All projects

jev-sim

dashbi1/jev-sim

Jev-compatible /v1/systemone server reading typed decisions from LLM logits, benchmarked against TypeSafe's Jev on the same items via JevBench

Python
Stars
1
Forks
0

Why it is listed

The README describes Jev-sim as a wire-compatible reimplementation that reads typed decisions from LLM logits and includes a comparison with Jev; compatibility was not tested here.

Related projects

  • system-one-playground

    Run the new wave of decision models (Laya, Decider, Kev, Jev) side by side on your Mac. Structured input in, calibrated probabilities out, with honest accuracy, calibration, latency and memory numbers.

    Shared topics: benchmark, calibration, classification

  • typed-decision-bench

    Bench of typed decision models: Jev vs OpenJev vs Laya, small local LLMs and cheap hosted LLMs on the same zero-shot classification tasks, in English and French.

    Shared topics: benchmark, calibration

  • snake-arena-jev-vs-llms

    How many decisions can a model make in a minute, and what do they cost? Jev, a System One decision model, raced against six LLMs on the same Snake boards.

    Shared topics: benchmark, calibration