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.
Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens.
Decides
noul, choice, score
choice, noul, score
Architecture
clef
canopy-jev
Fine-tuned from
cloudflare/clef-flash
qwen/qwen3.8-27b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
97.0%
87.4%
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 canopy-jev?
bev is from Berget AI and canopy-jev from Ruoxi Qiu. Both have open weights you can download and run. Both answer noul, choice and score questions. bev is the smaller model, at 9.0B parameters to 27B.
Which is more accurate, bev or canopy-jev?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), canopy-jev 87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev or canopy-jev?
bev: Free (open weights). canopy-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev or canopy-jev locally?
Yes, both: systemone pull berget-ai/bev and systemone pull camellia86/canopy-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; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
