GLiNER2.5-Decide vs Sieve 9B
Sieve 9B is more accurate on the Jev Decision Index, Sieve 9B is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | GLiNER2.5-Decide | Sieve 9B |
|---|---|---|
| Provider | Fastino | Sthānika AI |
| Decision Index score | 10.1 | 41.7 |
| Calibration error (ECE) | 0.088 | 0.043 |
| Median latency (p50) | 23 ms | 50 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 486M | 10B |
| 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 Sieve 9B more accurate?
Sieve 9B scores higher on the Jev Decision Index (41.7 vs 10.1).
Which is better calibrated, GLiNER2.5-Decide or Sieve 9B?
Sieve 9B has the lower expected calibration error (0.043 vs 0.088), so its stated confidence is closer to how often it is right.
Is GLiNER2.5-Decide or Sieve 9B 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.