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.
FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated.
Decides
noul, choice, score
choice, score, noul
Architecture
clef
lumma-fev
Fine-tuned from
cloudflare/clef-flash
frontiersmind/lumma-0.6b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
97.0%
64.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
45.8 ms
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 lumma-fev?
bev is from Berget AI and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer noul, choice and score questions. lumma-fev is the smaller model, at 649M parameters to 9.0B.
Which is more accurate, bev or lumma-fev?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), lumma-fev 64.0% on typed-decisions (maker's table; split not stated) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev or lumma-fev?
bev: Free (open weights). lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev or lumma-fev locally?
Yes, both: systemone pull berget-ai/bev and systemone pull frontiersmind/lumma-fev download the weights.
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
