An embedding model turned decision model. Qwen3-Embedding-4B with a merged LoRA, driven by the open JevEmbed toolkit, which scores Choice, Score and Noul questions from embedding similarity and returns a distribution without generating text.
An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.
Decides
choice, score, noul, classify
choice, score, noul, classify, route
Architecture
jevembed
laya
Fine-tuned from
qwen/qwen3-embedding-4b
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
85.9%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
39.5 ms
p95 latency
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between jevembed and laya?
jevembed is from HIT-TMG (Lychee Team) and laya from Convai Innovations. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only laya answers route. jevembed reads up to 1K tokens of state, against 512 tokens for laya. laya is the smaller model, at 421M parameters to 4.0B.
Which is more accurate, jevembed or laya?
Only jevembed publishes an accuracy figure (85.9% on JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging); laya does not, so there is no comparison to make without your own test.
Which is cheaper, jevembed or laya?
jevembed: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jevembed or laya locally?
Yes, both: systemone pull hit-tmg/jevembed and systemone pull convai-innovations/laya download the weights.
—
Evaluation suite
JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging
