HEAD TO HEAD
Fastino Labs: gliner2-5-decide and TokenRhythm: neohorse-jev, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | fastino-labs/gliner2-5-decide | tokenrhythm/neohorse-jev |
|---|---|---|
| Summary | 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. | TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input. |
| Decides | choice, score, noul, classify, extract, route | choice, score, noul, classify, route |
| Architecture | gliner2 | neohorse |
| Fine-tuned from | fastino/gliner2-large-v1 | tokenrhythm/neohorse-1-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights + hosted API | Open weights |
| Hosted by | Fastino | — |
| Input price | — | — |
| Decision accuracy | 60.2% | 75.3% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 38.3 ms | — |
| p95 latency | — | — |
| Evaluation suite | Fastino fast-decisions suite (17 datasets) | JevBench public set (231 items), vLLM, maker's run |
| Latest version | 2026.09.25 | 2026.09 |
| Variants | encoder_config | backbone, SHA256SUMS, assets, dist, package, tokenizer, vision |
| Size of latest version | 1.8 GB | 8.5 GB |
| Files | 6 | 38 |
| Downloads | 72 | 3 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, deberta, extraction, gliner, 340m | system-one, qwen, multimodal, vllm, sglang, 4b |
| Updated | Nov 18, 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.
gliner2-5-decide is from Fastino Labs and neohorse-jev from TokenRhythm. gliner2-5-decide has open weights and a hosted API; neohorse-jev has open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only gliner2-5-decide answers extract. gliner2-5-decide is the smaller model, at 340M parameters to 4.0B.
They report on different suites — gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets), neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
gliner2-5-decide: Hosted, price not published, or free to self-host. neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull tokenrhythm/neohorse-jev download the weights.