Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet.
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, noul, score
choice, score, noul, classify, extract, route
Architecture
bekko
gliner2
Fine-tuned from
cross-encoder/ettin-reranker-400m-v1
fastino/gliner2-large-v1
License
Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Fastino
Input price
—
—
Decision accuracy
—
60.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
5 ms
38.3 ms
p95 latency
5.4 ms
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 bekko-system-one and gliner2-5-decide?
bekko-system-one is from Yuichi Tateno (hotchpotch) and gliner2-5-decide from Fastino Labs. bekko-system-one has open weights you can download and run; gliner2-5-decide has open weights and a hosted API. Both answer choice, noul and score questions. Only gliner2-5-decide answers classify, extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 395M. bekko-system-one is licensed other; gliner2-5-decide, apache-2.0.
Which is more accurate, bekko-system-one or gliner2-5-decide?
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); bekko-system-one does not, so there is no comparison to make without your own test.
Which is cheaper, bekko-system-one or gliner2-5-decide?
bekko-system-one: 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.
Which is faster, bekko-system-one or gliner2-5-decide?
By their publishers’ figures, bekko-system-one answers in about 5 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 bekko-system-one or gliner2-5-decide locally?
Yes, both: systemone pull hotchpotch/bekko-system-one and systemone pull fastino-labs/gliner2-5-decide download the weights.
—
Evaluation suite
The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026)
