GLiNER 2.5 base vs GLiNER2.5-Decide
GLiNER 2.5 base and GLiNER2.5-Decide have no measured difference in accuracy, calibration or cost in our data yet.
| Spec | GLiNER 2.5 base | GLiNER2.5-Decide |
|---|---|---|
| Provider | Fastino | Fastino |
| Decision Index score | — | 9.2 |
| Calibration error (ECE) | — | 0.088 |
| Median latency (p50) | — | 23 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 194M | 486M |
| Open weights | Yes | Yes |
| Question types | Choice (one of N options), Score (ordered rubric), Yes / no, Extraction (typed spans) | Choice (one of N options), Score (ordered rubric), Yes / no, Extraction (typed spans) |
| Mechanism | Span encoder (GLiNER family) | Span encoder (GLiNER family) |
| License | Apache 2.0 | apache-2.0 |
FAQ
Is GLiNER 2.5 base or GLiNER2.5-Decide more accurate?
At least one of the two has no Jev Decision Index score yet, so their accuracy cannot be compared here.
Which is better calibrated, GLiNER 2.5 base or GLiNER2.5-Decide?
No calibration difference between GLiNER 2.5 base and GLiNER2.5-Decide is recorded yet.
Is GLiNER 2.5 base or GLiNER2.5-Decide cheaper per 1,000 decisions?
A hosted price is not recorded for both models; open-weight models cost the compute you run them on.
Cost per 1,000 decisions assumes 200 input tokens per decision. Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.