HEAD TO HEAD
Ruoxi Qiu: canopy-jev and Convai Innovations: laya, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | camellia86/canopy-jev | convai-innovations/laya |
|---|---|---|
| Summary | Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens. | 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 | choice, noul, score | choice, score, noul, classify, route |
| Architecture | canopy-jev | laya |
| Fine-tuned from | qwen/qwen3.8-27b | answerdotai/modernbert-large |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 87.4% | — |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | 39.5 ms |
| p95 latency | — | — |
| Evaluation suite | JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer | — |
| Latest version | 0.1.0 | 2026.09.25 |
| Variants | LICENSE, NOTICE, artifacts, licenses | multilingual, tokenizer, eval, typed-decisions, encoder |
| Size of latest version | 24.1 MB | 2.2 GB |
| Files | 11 | 19 |
| Downloads | 0 | 431 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, adapter, shared-state, 27b | system-one, encoder, modernbert, rlcd, multilingual, 421m |
| Updated | Oct 7, 2026 | Nov 22, 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.
canopy-jev is from Ruoxi Qiu and laya from Convai Innovations. Both have open weights you can download and run. Both answer choice, noul and score questions. Only laya answers classify and route. laya is the smaller model, at 421M parameters to 27B.
Only canopy-jev publishes an accuracy figure (87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer); laya does not, so there is no comparison to make without your own test.
canopy-jev: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull camellia86/canopy-jev and systemone pull convai-innovations/laya download the weights.