Bespoke Nimble 9B v2 vs GLiNER2.5-Decide
Bespoke Nimble 9B v2 is more accurate on the Jev Decision Index, Bespoke Nimble 9B v2 is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | Bespoke Nimble 9B v2 | GLiNER2.5-Decide |
|---|---|---|
| Provider | Bespoke Labs | Fastino |
| Decision Index score | 42.1 | 10.1 |
| Calibration error (ECE) | 0.024 | 0.088 |
| Median latency (p50) | 77 ms | 23 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 10B | 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 Bespoke Nimble 9B v2 or GLiNER2.5-Decide more accurate?
Bespoke Nimble 9B v2 scores higher on the Jev Decision Index (42.1 vs 10.1).
Which is better calibrated, Bespoke Nimble 9B v2 or GLiNER2.5-Decide?
Bespoke Nimble 9B v2 has the lower expected calibration error (0.024 vs 0.088), so its stated confidence is closer to how often it is right.
Is Bespoke Nimble 9B v2 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.