HEAD TO HEAD
Convai Innovations: laya and StartLux: startlux-decision, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya | startlux/startlux-decision |
|---|---|---|
| Summary | 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. | 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, score, noul, classify, route | choice, score, noul |
| Architecture | laya | startlux-decision |
| Fine-tuned from | answerdotai/modernbert-large | — |
| License | apache-2.0 | cc-by-nc-4.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 88.3% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 39.5 ms | 26 ms |
| p95 latency | — | — |
| Evaluation suite | — | JevBench public set (231 items; 204 correct), maker's run |
| Latest version | 2026.09.25 | 2026.10 |
| Variants | multilingual, tokenizer, eval, typed-decisions, encoder | LICENSE, NOTICE, startlux_decision |
| Size of latest version | 2.2 GB | 8.7 GB |
| Files | 19 | 23 |
| Downloads | 419 | 3 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, rlcd, multilingual, 421m | system-one, qwen, non-commercial, gguf, cuda-graphs, vision, mlx, 4.7b |
| Updated | Nov 19, 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.
laya is from Convai Innovations and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya answers classify and route. startlux-decision reads up to 256K tokens of state, against 512 tokens for laya. laya is the smaller model, at 421M parameters to 4.7B. laya is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); laya does not, so there is no comparison to make without your own test.
laya: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, startlux-decision answers in about 26 ms at the median and laya in about 39.5 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull convai-innovations/laya and systemone pull startlux/startlux-decision download the weights.