Loading comparison…
HEAD TO HEAD
Berget AI: bev and Convai Innovations: laya, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | berget-ai/bev | convai-innovations/laya |
|---|---|---|
| Summary | 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 open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU. |
| Decides | noul, choice, score | choice, score, noul, classify, route |
| Architecture | clef | laya |
| Fine-tuned from | cloudflare/clef-flash | answerdotai/modernbert-large |
| 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 | — | 39.5 ms |
| p95 latency | — | — |
| Evaluation suite | Berget held-out risk split (16,902 questions; same operations-traffic corpora as training) | — |
| Latest version | 2026.09 | 2026.09.25 |
| Variants | — | multilingual, tokenizer, typed-decisions, eval, encoder |
| Size of latest version | 339.0 MB | 2.2 GB |
| Files | 3 | 19 |
| Downloads | 0 | 139 |
| Stars | 0 | 0 |
| Tags | system-one, lora, clef, guardrails, safety, swedish, 9b | system-one, encoder, modernbert, rlcd, multilingual, 421m |
| Updated | Oct 7, 2026 | Oct 7, 2026 |
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.
bev is from Berget AI and laya from Convai Innovations. Both have open weights you can download and run. Both answer noul, choice and score questions. Only laya answers classify and route. laya is the smaller model, at 421M parameters to 9.0B.
Only bev publishes an accuracy figure (97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)); laya does not, so there is no comparison to make without your own test.
bev: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull berget-ai/bev and systemone pull convai-innovations/laya download the weights.