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.
Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Decides
noul, choice, score
choice, score, noul, classify, route
Architecture
clef
mira
Fine-tuned from
cloudflare/clef-flash
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
97.0%
61.3%
Calibration error
—
0.083
Valid action rate
—
100.0%
Median latency
—
30 ms
p95 latency
—
43 ms
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
s1-decision-bench
Latest version
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 mira?
bev is from Berget AI and mira from SAGEA. Both have open weights you can download and run. Both answer noul, choice and score questions. Only mira answers classify and route.
Which is more accurate, bev or mira?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), mira 61.3% on s1-decision-bench — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev or mira?
bev: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev or mira locally?
Yes, both: systemone pull berget-ai/bev and systemone pull sagea/mira download the weights.
