Skip to content
Evaluation & TrainingJev Decision IndexHF Decision Index

Decision Index

A Hugging Face leaderboard that scores open reproductions of Jev on the same frozen decision suite.

Category
Evaluation & Training
Also known as
Jev Decision Index, HF Decision Index
Related terms
4
Directory entries
2
Docs
huggingface.co
Added
2026-10-11

Definition

Maintained by multimodalart on Hugging Face, the Decision Index (current edition 0.3.1) ranks open models on a frozen suite of more than 130,000 decisions, with five capability categories and a separate vision board. The suite is built from jev-1.13.0 as its reference edition.

It is the board where the open ecosystem argues about parity: entrants include Laya, Kev, decider, d1, and dozens of small checkpoints, and it is the reference Liquid AI cited when it said d1 was the first model to beat Jev on the index.

Tagsevaluationbenchmarksopen-models

From the Jev directory

An unofficial Hugging Face space that tracks open Jev reproductions and scores the ones that finished a frozen benchmark suite.
Jev Benchmarks & EvaluationsPlayground#community#evaluation#open-models
Community
Liquid AI's 3.12B decision model built on LFM2.5-VL: state plus typed questions in one forward pass with zero output tokens, 48.57 on Decision Index 0.2.1 and 8 ms per decision on an RTX 4090.
Jev Models & Reimplementations#community#open-models#local
Community

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai