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.
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.
Decides
choice, score, noul, classify, rank, route
noul, choice, score
Architecture
arc-decide
clef
Fine-tuned from
qwen/qwen3-0.6b-base
cloudflare/clef-flash
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
97.0%
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 bev?
arc-decide is from Arc53 and bev from Berget AI. Both have open weights you can download and run. Both answer choice, score and noul questions. Only arc-decide answers classify, rank and route. arc-decide is the smaller model, at 600M parameters to 9.0B. arc-decide is licensed mit; bev, apache-2.0.
Which is more accurate, arc-decide or bev?
Only bev publishes an accuracy figure (97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)); arc-decide does not, so there is no comparison to make without your own test.
Which is cheaper, arc-decide or bev?
arc-decide: Free (open weights). bev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or bev locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull berget-ai/bev download the weights.
—
Evaluation suite
—
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
