Berget AI's System One model for gating agent commands: a LoRA adapter and a fine-tuned joint schema head on Cloudflare's Clef-Flash that answer noul, choice and score questions over a state in one forward pass. Trained on Swedish and English operations decisions.
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
noul, choice, score
choice, score, noul, classify, route
Architecture
clef
neohorse
Fine-tuned from
cloudflare/clef-flash
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
97.0%
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 bev and neohorse-jev?
bev is from Berget AI and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer noul, choice and score questions. Only neohorse-jev answers classify and route. neohorse-jev is the smaller model, at 4.0B parameters to 9.0B.
Which is more accurate, bev or neohorse-jev?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), 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, bev or neohorse-jev?
bev: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev or neohorse-jev locally?
Yes, both: systemone pull berget-ai/bev and systemone pull tokenrhythm/neohorse-jev download the weights.
—
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
JevBench public set (231 items), vLLM, maker's run
