Loading comparison…
HEAD TO HEAD
Avishek Biswas: bev-decider and Maziyar Panahi: modernjev-decide, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | avishek-biswas/bev-decider | maziyar-panahi/modernjev-decide |
|---|---|---|
| Summary | A 0.4B decision model made from the first 20 layers of Qwen3-0.6B plus a small attention head that compares options. It answers choice, noul and score questions in one pass, and choice order cannot change its answer by construction. Non-commercial licence. | 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 | choice, score, noul | choice, rank, route |
| Architecture | bev-decider | modernjev |
| Fine-tuned from | qwen/qwen3-0.6b | answerdotai/modernbert-base |
| License | cc-by-nc-4.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 74.7% | 73.4% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own | AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) |
| Latest version | 2026.09 | 2026.09 |
| Variants | LICENSE-Qwen | — |
| Size of latest version | 940.1 MB | 574.1 MB |
| Files | 8 | 5 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, non-commercial, 478m | 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-decider is from Avishek Biswas and modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice questions. Only bev-decider answers score and noul. Only modernjev-decide answers rank and route. modernjev-decide reads up to 4K tokens of state, against 2K tokens for bev-decider. modernjev-decide is the smaller model, at 150M parameters to 478M. bev-decider is licensed cc-by-nc-4.0; modernjev-decide, apache-2.0.
They report on different suites — bev-decider 74.7% on avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own, 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-decider: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull avishek-biswas/bev-decider and systemone pull maziyar-panahi/modernjev-decide download the weights.