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 independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only.
Decides
choice, score, noul, classify, extract, route
choice, score, noul, classify
Architecture
gliner2
open-jev
Fine-tuned from
fastino/gliner2-large-v1
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Fastino
—
Input price
—
—
Decision accuracy
60.2%
85.4%
Calibration error
—
0.022
Valid action rate
—
—
Median latency
38.3 ms
28 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 open-jev-deberta-v3-large?
gliner2-5-decide is from Fastino Labs and open-jev-deberta-v3-large from Kotoba Labs. gliner2-5-decide has open weights and a hosted API; open-jev-deberta-v3-large 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 434M.
Which is more accurate, gliner2-5-decide or open-jev-deberta-v3-large?
They report on different suites — gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets), open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, gliner2-5-decide or open-jev-deberta-v3-large?
gliner2-5-decide: Hosted, price not published, or free to self-host. open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, gliner2-5-decide or open-jev-deberta-v3-large?
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 ms at the median and gliner2-5-decide in about 38.3 ms — measured on different hardware, so treat it as a rough guide.
Can I run gliner2-5-decide or open-jev-deberta-v3-large locally?
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Evaluation suite
Fastino fast-decisions suite (17 datasets)
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
