Loading comparison…
HEAD TO HEAD
Fastino Labs: gliner2-5-decide and SAGEA: mira, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | fastino-labs/gliner2-5-decide | sagea/mira |
|---|---|---|
| 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. | Small open typed-decision model with calibrated probabilities, first-class Nepali coverage. |
| Decides | choice, score, noul, classify, extract, route | choice, score, noul, classify, route |
| Architecture | gliner2 | mira |
| Fine-tuned from | fastino/gliner2-large-v1 | jhu-clsp/mmbert-small |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights + hosted API | Open weights |
| Hosted by | Fastino | — |
| Input price | — | — |
| Decision accuracy | 60.2% | 74.5% |
| Calibration error | — | 0.025 |
| Valid action rate | — | 100.0% |
| Median latency | 38.3 ms | 30 ms |
| p95 latency | — | 43 ms |
| Evaluation suite | Fastino fast-decisions suite (17 datasets) | s1-decision-bench |
| Latest version | 2026.09.25 | 0.1.4 |
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 mira from SAGEA. gliner2-5-decide has open weights and a hosted API; mira has open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only gliner2-5-decide answers extract.
They report on different suites — gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets), mira 74.5% on s1-decision-bench — 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. mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, mira answers in about 30 ms at the median and gliner2-5-decide in about 38.3 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull sagea/mira download the weights.
| Variants | encoder_config | — |
|---|
| Size of latest version | 1.8 GB | 568.9 MB |
|---|
| Files | 6 | 13 |
|---|
| Downloads | 26 | 7 |
|---|
| Stars | 0 | 1 |
|---|
| Tags | system-one, encoder, deberta, extraction, gliner, 340m | routing, nepali, nepal, calibration, cpu |
|---|
| Updated | Oct 1, 2026 | Oct 1, 2026 |
|---|