HEAD TO HEAD
Ruoxi Qiu: canopy-jev and Fastino Labs: gliner2-5-decide, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | camellia86/canopy-jev | fastino-labs/gliner2-5-decide |
|---|---|---|
| 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. | Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations. |
| Decides | choice, noul, score | choice, score, noul, classify, extract, route |
| Architecture | canopy-jev | gliner2 |
| Fine-tuned from | qwen/qwen3.8-27b | fastino/gliner2-large-v1 |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights + hosted API |
| Hosted by | — | Fastino |
| Input price | — | — |
| Decision accuracy | 87.4% | 60.2% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | 38.3 ms |
| p95 latency | — | — |
| Evaluation suite | JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer | Fastino fast-decisions suite (17 datasets) |
| Latest version | 0.1.0 | 2026.09.25 |
| Variants | LICENSE, NOTICE, artifacts, licenses | encoder_config |
| Size of latest version | 24.1 MB | 1.8 GB |
| Files | 11 | 6 |
| Downloads | 0 | 75 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, adapter, shared-state, 27b | system-one, encoder, deberta, extraction, gliner, 340m |
| 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 gliner2-5-decide from Fastino Labs. canopy-jev has open weights you can download and run; gliner2-5-decide has open weights and a hosted API. Both answer choice, noul and score questions. Only gliner2-5-decide answers classify, extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 27B.
They report on different suites — canopy-jev 87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer, gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets) — so the numbers do not rank them. Test both on your own labelled examples.
canopy-jev: Free (open weights). gliner2-5-decide: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull camellia86/canopy-jev and systemone pull fastino-labs/gliner2-5-decide download the weights.