Sieve 9B v2 vs Celeris-1 Decision
Sieve 9B v2 and Celeris-1 Decision have no measured difference in accuracy, calibration or cost in our data yet.
| Spec | Sieve 9B v2 | Celeris-1 Decision |
|---|---|---|
| Provider | Sthānika AI | Celeris |
| Decision Index score | 50.9 | — |
| Calibration error (ECE) | 0.073 | — |
| Median latency (p50) | 51 ms | — |
| Cost per 1,000 decisions | — | $0.0080 |
| Parameters | 10B | — |
| Open weights | Yes | No |
| Question types | Choice (one of N options), Score (ordered rubric), Yes / no | Choice (one of N options), Score (ordered rubric), Yes / no |
| Mechanism | Decoder LM with a decision readout | Diffusion LM |
| License | apache-2.0 | proprietary |
FAQ
Is Sieve 9B v2 or Celeris-1 Decision 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, Sieve 9B v2 or Celeris-1 Decision?
No calibration difference between Sieve 9B v2 and Celeris-1 Decision is recorded yet.
Is Sieve 9B v2 or Celeris-1 Decision 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.