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 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
Decides
choice, score, noul, classify, extract, route
choice, rank, route
Architecture
gliner2
modernjev
Fine-tuned from
fastino/gliner2-large-v1
answerdotai/modernbert-base
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Fastino
—
Input price
—
—
Decision accuracy
60.2%
73.4%
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 modernjev-decide?
gliner2-5-decide is from Fastino Labs and modernjev-decide from Maziyar Panahi. gliner2-5-decide has open weights and a hosted API; modernjev-decide has open weights you can download and run. Both answer choice and route questions. Only gliner2-5-decide answers score, noul, classify and extract. Only modernjev-decide answers rank. modernjev-decide is the smaller model, at 150M parameters to 340M.
Which is more accurate, gliner2-5-decide or modernjev-decide?
They report on different suites — gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets), modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, gliner2-5-decide or modernjev-decide?
gliner2-5-decide: Hosted, price not published, or free to self-host. modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or modernjev-decide locally?
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull maziyar-panahi/modernjev-decide download the weights.
—
Evaluation suite
Fastino fast-decisions suite (17 datasets)
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
