ezjev 4B s2 vs GLiNER2.5-Decide
ezjev 4B s2 is more accurate on the Jev Decision Index, ezjev 4B s2 is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | ezjev 4B s2 | GLiNER2.5-Decide |
|---|---|---|
| Provider | everettjf | Fastino |
| Decision Index score | 43.9 | 10.1 |
| Calibration error (ECE) | 0.063 | 0.088 |
| Median latency (p50) | 36 ms | 23 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 5B | 486M |
| Open weights | Yes | Yes |
| Question types | Choice (one of N options), Score (ordered rubric), Yes / no | Choice (one of N options), Score (ordered rubric), Yes / no, Extraction (typed spans) |
| Mechanism | Decoder LM with a decision readout | Span encoder (GLiNER family) |
| License | other | apache-2.0 |
FAQ
Is ezjev 4B s2 or GLiNER2.5-Decide more accurate?
ezjev 4B s2 scores higher on the Jev Decision Index (43.9 vs 10.1).
Which is better calibrated, ezjev 4B s2 or GLiNER2.5-Decide?
ezjev 4B s2 has the lower expected calibration error (0.063 vs 0.088), so its stated confidence is closer to how often it is right.
Is ezjev 4B s2 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.