A 0.6B decision model on Qwen3-0.6B-Base from the DocsGPT team. Give it a state and typed questions (yes/no, a choice of up to 16 options, a 3- or 4-level score) and it returns calibrated probabilities in one pass, for RAG and agent checks.
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, rank, route
choice, score, noul, classify, route
Architecture
arc-decide
neohorse
Fine-tuned from
qwen/qwen3-0.6b-base
tokenrhythm/neohorse-1-4b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
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 arc-decide and neohorse-jev?
arc-decide is from Arc53 and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only arc-decide answers rank. arc-decide is the smaller model, at 600M parameters to 4.0B. arc-decide is licensed mit; neohorse-jev, apache-2.0.
Which is more accurate, arc-decide or neohorse-jev?
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); arc-decide does not, so there is no comparison to make without your own test.
Which is cheaper, arc-decide or neohorse-jev?
arc-decide: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or neohorse-jev locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull tokenrhythm/neohorse-jev download the weights.
—
Evaluation suite
—
JevBench public set (231 items), vLLM, maker's run
