Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations.
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.
Decides
choice, score, noul, classify, extract, route
choice, score, noul, classify
Architecture
gliner2
jevembed
Fine-tuned from
fastino/gliner2-large-v1
qwen/qwen3-embedding-4b
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Fastino
—
Input price
—
—
Decision accuracy
60.2%
85.9%
Calibration error
—
—
Valid action rate
—
—
Median latency
38.3 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 gliner2-5-decide and jevembed?
gliner2-5-decide is from Fastino Labs and jevembed from HIT-TMG (Lychee Team). gliner2-5-decide has open weights and a hosted API; jevembed has open weights you can download and run. Both answer choice, score, noul and classify questions. Only gliner2-5-decide answers extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 4.0B.
Which is more accurate, gliner2-5-decide or jevembed?
They report on different suites — gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets), jevembed 85.9% on JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, gliner2-5-decide or jevembed?
gliner2-5-decide: Hosted, price not published, or free to self-host. jevembed: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or jevembed locally?
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull hit-tmg/jevembed download the weights.
Evaluation suite
Fastino fast-decisions suite (17 datasets)
JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging
