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.
An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only.
Decides
noul, choice, score
choice, score, noul, classify
Architecture
clef
open-jev
Fine-tuned from
cloudflare/clef-flash
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
97.0%
85.4%
Calibration error
—
0.022
Valid action rate
—
—
Median latency
—
28 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 open-jev-deberta-v3-large?
bev is from Berget AI and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer noul, choice and score questions. Only open-jev-deberta-v3-large answers classify. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 9.0B.
Which is more accurate, bev or open-jev-deberta-v3-large?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev or open-jev-deberta-v3-large?
bev: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev or open-jev-deberta-v3-large locally?
Yes, both: systemone pull berget-ai/bev and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
