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.
Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking.
Decides
noul, choice, score
choice, score, noul, rank, classify, route
Architecture
clef
clm
Fine-tuned from
cloudflare/clef-flash
qwen/qwen3-8b
License
apache-2.0
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 bev and clm?
bev is from Berget AI and clm from Contrastive-LM. Both have open weights you can download and run. Both answer noul, choice and score questions. Only clm answers rank, classify and route. clm is the smaller model, at 8.0B parameters to 9.0B.
Which is more accurate, bev or clm?
Only bev publishes an accuracy figure (97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)); clm does not, so there is no comparison to make without your own test.
Which is cheaper, bev or clm?
bev: Free (open weights). clm: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev or clm locally?
Yes, both: systemone pull berget-ai/bev and systemone pull contrastive-lm/clm download the weights.
—
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
