Loading comparison…
HEAD TO HEAD
Berget AI: bev and Maziyar Panahi: modernjev-decide, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | berget-ai/bev | maziyar-panahi/modernjev-decide |
|---|---|---|
| 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. | A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated. |
| Decides | noul, choice, score | choice, rank, route |
| Architecture | clef | modernjev |
| Fine-tuned from | cloudflare/clef-flash | answerdotai/modernbert-base |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 97.0% | 73.4% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | Berget held-out risk split (16,902 questions; same operations-traffic corpora as training) | AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) |
| Latest version | 2026.09 | 2026.09 |
| Variants | — | — |
| Size of latest version | 339.0 MB | 574.1 MB |
| Files | 3 | 5 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, lora, clef, guardrails, safety, swedish, 9b | system-one, encoder, modernbert, cross-encoder, tool-routing, preview, 149.6m |
| 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 modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice questions. Only bev answers noul and score. Only modernjev-decide answers rank and route. modernjev-decide is the smaller model, at 150M parameters to 9.0B.
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) — so the numbers do not rank them. Test both on your own labelled examples.
bev: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull berget-ai/bev and systemone pull maziyar-panahi/modernjev-decide download the weights.