A 0.4B decision model made from the first 20 layers of Qwen3-0.6B plus a small attention head that compares options. It answers choice, noul and score questions in one pass, and choice order cannot change its answer by construction. Non-commercial licence.
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.
Decides
choice, score, noul
choice, score, noul, classify, extract, route
Architecture
bev-decider
gliner2
Fine-tuned from
qwen/qwen3-0.6b
fastino/gliner2-large-v1
License
cc-by-nc-4.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Fastino
Input price
—
—
Decision accuracy
74.7%
60.2%
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 bev-decider and gliner2-5-decide?
bev-decider is from Avishek Biswas and gliner2-5-decide from Fastino Labs. bev-decider has open weights you can download and run; gliner2-5-decide has open weights and a hosted API. Both answer choice, score and noul questions. Only gliner2-5-decide answers classify, extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 478M. bev-decider is licensed cc-by-nc-4.0; gliner2-5-decide, apache-2.0.
Which is more accurate, bev-decider or gliner2-5-decide?
They report on different suites — bev-decider 74.7% on avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own, gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev-decider or gliner2-5-decide?
bev-decider: Free (open weights). gliner2-5-decide: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run bev-decider or gliner2-5-decide locally?
Yes, both: systemone pull avishek-biswas/bev-decider and systemone pull fastino-labs/gliner2-5-decide download the weights.
Evaluation suite
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
