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.
A rank-16 LoRA on Qwen3.5-4B built for the JevBench setting. A document, a policy and a question go in; a calibrated distribution over the option letters comes out of one forward pass. Research and demo use only.
Decides
choice, score, noul, classify, extract, route
choice, score, noul, classify
Architecture
gliner2
hopper
Fine-tuned from
fastino/gliner2-large-v1
qwen/qwen3.5-4b
License
apache-2.0
Research and demo use only (training data includes RACE, non-commercial); serving code Apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Fastino
—
Input price
—
—
Decision accuracy
60.2%
68.5%
Calibration error
—
0.102
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 hopper?
gliner2-5-decide is from Fastino Labs and hopper from HopitAI. gliner2-5-decide has open weights and a hosted API; hopper 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. gliner2-5-decide is licensed apache-2.0; hopper, other.
Which is more accurate, gliner2-5-decide or hopper?
They report on different suites — gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets), hopper 68.5% on JevBench public hard tier (111 items, measured by the authors) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, gliner2-5-decide or hopper?
gliner2-5-decide: Hosted, price not published, or free to self-host. hopper: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or hopper locally?
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull hopit-ai/hopper download the weights.
Evaluation suite
Fastino fast-decisions suite (17 datasets)
JevBench public hard tier (111 items, measured by the authors)
