HEAD TO HEAD
Maziyar Panahi: modernjev-decide and StartLux: startlux-decision, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | maziyar-panahi/modernjev-decide | startlux/startlux-decision |
|---|---|---|
| Summary | 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. | StartLux's decision family in six sizes, 0.8B to a 35B-A3B mixture of experts. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server. Text, JSON or images, up to 256K tokens. |
| Decides | choice, rank, route | choice, score, noul |
| Architecture | modernjev | startlux-decision |
| Fine-tuned from | answerdotai/modernbert-base | — |
| License | apache-2.0 | cc-by-nc-4.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 73.4% | 88.3% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | 26 ms |
| p95 latency | — | — |
| Evaluation suite | AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) | JevBench public set (231 items; 204 correct), maker's run |
| Latest version | 2026.09 | 2026.10 |
| Variants | — | LICENSE, NOTICE, startlux_decision |
| Size of latest version | 574.1 MB | 8.7 GB |
| Files | 5 | 23 |
| Downloads | 0 | 3 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, cross-encoder, tool-routing, preview, 149.6m | system-one, qwen, non-commercial, gguf, cuda-graphs, vision, mlx, 4.7b |
| 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.
modernjev-decide is from Maziyar Panahi and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice questions. Only modernjev-decide answers rank and route. Only startlux-decision answers score and noul. startlux-decision reads up to 256K tokens of state, against 4K tokens for modernjev-decide. modernjev-decide is the smaller model, at 150M parameters to 4.7B. modernjev-decide is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
They report on different suites — modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split), startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run — so the numbers do not rank them. Test both on your own labelled examples.
modernjev-decide: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull maziyar-panahi/modernjev-decide and systemone pull startlux/startlux-decision download the weights.