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.
A 0.4B decision model made from the first 20 layers of Qwen3-0.6B plus a small attention head that compares options. It answers choice, noul and score questions in one pass, and choice order cannot change its answer by construction. Non-commercial licence.
Decides
noul, choice, score
choice, score, noul
Architecture
clef
bev-decider
Fine-tuned from
cloudflare/clef-flash
qwen/qwen3-0.6b
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
97.0%
74.7%
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 bev-decider?
bev is from Berget AI and bev-decider from Avishek Biswas. Both have open weights you can download and run. Both answer noul, choice and score questions. bev-decider is the smaller model, at 478M parameters to 9.0B. bev is licensed apache-2.0; bev-decider, cc-by-nc-4.0.
Which is more accurate, bev or bev-decider?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), bev-decider 74.7% on avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev or bev-decider?
bev: Free (open weights). bev-decider: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev or bev-decider locally?
Yes, both: systemone pull berget-ai/bev and systemone pull avishek-biswas/bev-decider download the weights.
—
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
