A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.
TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decider
neohorse
Fine-tuned from
qwen/qwen3.5-2b-base
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.2%
75.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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 decider and neohorse-jev?
decider is from Mapika and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider is the smaller model, at 1.9B parameters to 4.0B.
Which is more accurate, decider or neohorse-jev?
They report on different suites — decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11), neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decider or neohorse-jev?
decider: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or neohorse-jev locally?
Yes, both: systemone pull mapika/decider and systemone pull tokenrhythm/neohorse-jev download the weights.
