amos-1-large vs GLiNER2.5-Decide
amos-1-large is more accurate on the Jev Decision Index, amos-1-large is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | amos-1-large | GLiNER2.5-Decide |
|---|---|---|
| Provider | Scira (mukaddamzaid) | Fastino |
| Decision Index score | 64.8 | 10.1 |
| Calibration error (ECE) | 0.032 | 0.088 |
| Median latency (p50) | 148 ms | 23 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | — | 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 | apache-2.0 | apache-2.0 |
FAQ
Is amos-1-large or GLiNER2.5-Decide more accurate?
amos-1-large scores higher on the Jev Decision Index (64.8 vs 10.1).
Which is better calibrated, amos-1-large or GLiNER2.5-Decide?
amos-1-large has the lower expected calibration error (0.032 vs 0.088), so its stated confidence is closer to how often it is right.
Is amos-1-large 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.