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.
A family of open System One models by Mark Marosi that softmax option-letter logits at an answer slot: decider-0.8b, 2b, 4b and 35b-a3b on Qwen3.5 bases, decider-12b on Gemma-4-12B-it, and training-free readouts of larger chat models. This page carries decider-2b v11.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
bekko
decider
Fine-tuned from
cross-encoder/ettin-reranker-400m-v1
qwen/qwen3.5-2b-base
License
Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
75.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
5 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 decider?
bekko-system-one is from Yuichi Tateno (hotchpotch) and decider from Mapika. Both have open weights you can download and run. Both answer choice, noul and score questions. Only decider answers classify and route. bekko-system-one is the smaller model, at 395M parameters to 1.9B. bekko-system-one is licensed other; decider, apache-2.0.
Which is more accurate, bekko-system-one or decider?
Only decider publishes an accuracy figure (75.2% on Decider regression set, 28 held-out tasks (decider-2b v11)); bekko-system-one does not, so there is no comparison to make without your own test.
Which is cheaper, bekko-system-one or decider?
bekko-system-one: Free (open weights). decider: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bekko-system-one or decider locally?
Yes, both: systemone pull hotchpotch/bekko-system-one and systemone pull mapika/decider download the weights.
p95 latency
5.4 ms
—
Evaluation suite
The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026)