Checked 20 September 2026
Alternatives to laya
Grouped by the reason you would actually switch, not by a leaderboard position that does not exist yet.
laya is open weights already, so switching is about fit rather than about control.
The reasons to move are narrow: a licence you can ship, a size you can afford, a format you can deploy, or an architecture whose confidence you trust. Each group below is one of those reasons.
1 of the 134 projects in our directory reference laya, 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.
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.
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.
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-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.
LFM2.5-350M-RLCD
A typed-decision model from notnotsamuel, 354M parameters. Licensed other, check before commercial use.
modernbert-ja-310m-jev
modernbert-ja-310m fine-tuned to return typed decisions, 315M parameters. Licensed cc-by-sa-4.0, check before commercial use.
laya-vision-smolvlm-256m
SmolVLM-256M-Instruct fine-tuned to return typed decisions, 237M parameters. Licensed cc-by-nc-sa-4.0, check before commercial use.
system-one-mini
distilbert-base-uncased fine-tuned to return typed decisions, 69M parameters.
system-one-distilled
deberta-v3-xsmall-zeroshot-v1.1-all-33 fine-tuned to return typed decisions, 71M parameters.
The honest caveat
None of these has been benchmarked against laya 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
laya vs Jev
Side by side on licence, architecture, size and what has been measured.
laya vs Qwen-2.5-1B-RLCD
Side by side on licence, architecture, size and what has been measured.
laya vs cua-s1-forms
Side by side on licence, architecture, size and what has been measured.
laya 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.