GLiNER2.5-Decide vs Jevstral 8B
Jevstral 8B is more accurate on the Jev Decision Index, Jevstral 8B is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | GLiNER2.5-Decide | Jevstral 8B |
|---|---|---|
| Provider | Fastino | AmirBraham |
| Decision Index score | 10.1 | 32.2 |
| Calibration error (ECE) | 0.088 | 0.047 |
| Median latency (p50) | 23 ms | 28 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 486M | 8B |
| 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 |
| Mechanism | Span encoder (GLiNER family) | Decoder LM with a decision readout |
| License | apache-2.0 | apache-2.0 |
FAQ
Is GLiNER2.5-Decide or Jevstral 8B more accurate?
Jevstral 8B scores higher on the Jev Decision Index (32.2 vs 10.1).
Which is better calibrated, GLiNER2.5-Decide or Jevstral 8B?
Jevstral 8B has the lower expected calibration error (0.047 vs 0.088), so its stated confidence is closer to how often it is right.
Is GLiNER2.5-Decide or Jevstral 8B 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.