Checked 20 September 2026
Open-source alternatives to Jev
Grouped by the reason you would actually switch, not by a leaderboard position that does not exist yet.
Jev is a hosted API. Everything below is an open-weight model you run yourself.
Replacing a hosted call with local weights trades a key, a round trip and a vendor version number for the operational cost of running a model. That is usually the right trade at volume and the wrong one while you are still finding out whether the decision is even worth automating.
109 of the 134 projects in our directory reference Jev, so there is working code to read before you commit either way. Full detail on the model itself is on its page.
Licensed for commercial use
Apache-2.0 or MIT. Start here if this is going into a product, because licence rules a model out faster than any benchmark.
laya
The most-liked open-weight decision model of the post-Jev wave, a 421M ModernBERT-large encoder. The base release of a three-model family.
Qwen-2.5-1B-RLCD
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions.
cua-s1-forms
A System One model narrowed to one job, filling forms. MIT licensed, and the clearest example in the directory of the interface spreading past the benchmark it was born on.
laya-multilingual
The only multilingual decision model we have found, a 322M encoder on mmBERT. Also the one our English-only test set cannot say anything useful about.
decider-2b
The most-downloaded open-weight decision model in the post-Jev wave. A Qwen3.5-2B decoder fine-tuned to emit typed decisions, and the largest member of a three-model family.
laya-typed-decisions
The Laya variant tuned on the typed-decisions benchmark, and the only open model whose card publishes head-to-head numbers against Jev. One of those numbers is the reason we started measuring.
Ship in a runnable local format
GGUF, MLX, ONNX or Core ML builds exist, so you can run one without assembling a Python serving stack first.
Smaller and cheaper to run
Fewer parameters, so cheaper per decision at volume. Whether they give up accuracy for it is unmeasured.
laya
The most-liked open-weight decision model of the post-Jev wave, a 421M ModernBERT-large encoder. The base release of a three-model family.
laya-multilingual
The only multilingual decision model we have found, a 322M encoder on mmBERT. Also the one our English-only test set cannot say anything useful about.
decider-2b
The most-downloaded open-weight decision model in the post-Jev wave. A Qwen3.5-2B decoder fine-tuned to emit typed decisions, and the largest member of a three-model family.
laya-typed-decisions
The Laya variant tuned on the typed-decisions benchmark, and the only open model whose card publishes head-to-head numbers against Jev. One of those numbers is the reason we started measuring.
open-jev-deberta-v3-large
A DeBERTa-v3-large encoder positioned as an open reimplementation of Jev. The highest ratio of likes to downloads in the directory, which is usually what a credible claim looks like early.
LFM2.5-350M-RLCD
A typed-decision model from notnotsamuel, 354M parameters. Licensed other, check before commercial use.
The honest caveat
None of these has been benchmarked against Jev by anyone independent, including us. This page groups candidates by facts you can check. It cannot tell you which one holds up on your traffic, and anyone presenting a ranking here is guessing.
Compare them head to head
Jev vs laya
Side by side on licence, architecture, size and what has been measured.
Jev vs Qwen-2.5-1B-RLCD
Side by side on licence, architecture, size and what has been measured.
Jev vs cua-s1-forms
Side by side on licence, architecture, size and what has been measured.
Jev vs laya-multilingual
Side by side on licence, architecture, size and what has been measured.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.