CalibratedDecisions.

Repo · Benchmarks & research

jevbench (Leanmcp)

Open framework and dataset for benchmarking typed decision models (Jev 1.13, Liquid D1, djev, Laya, Clef, pplx-decider and others) across science,…

Open github.com ↗

From the repository

Open benchmark for typed decision models: Liquid D1, Jev, djev and Laya on 12 tasks

benchmarkcalibrationclassificationdecision-modelsevaluationllmllm-evaluation

How builders describe it

Open benchmark for typed decision models: Liquid D1, Jev, djev and Laya on 12 tasks.
Open framework and dataset for benchmarking typed decision models (Jev 1.13, Liquid D1, djev, Laya, Clef, pplx-decider and others) across science, tool calling, business, selection, ranking and judging clusters, with a paper and results site.

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