GLiNER2.5-Decide vs Nirnaya 0.4B
GLiNER2.5-Decide is more accurate on the Jev Decision Index, Nirnaya 0.4B is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | GLiNER2.5-Decide | Nirnaya 0.4B |
|---|---|---|
| Provider | Fastino | kshitijthakkar |
| Decision Index score | 10.1 | 3.5 |
| Calibration error (ECE) | 0.088 | 0.046 |
| Median latency (p50) | 23 ms | 14 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 486M | 390M |
| 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 | — |
FAQ
Is GLiNER2.5-Decide or Nirnaya 0.4B more accurate?
GLiNER2.5-Decide scores higher on the Jev Decision Index (10.1 vs 3.5).
Which is better calibrated, GLiNER2.5-Decide or Nirnaya 0.4B?
Nirnaya 0.4B has the lower expected calibration error (0.046 vs 0.088), so its stated confidence is closer to how often it is right.
Is GLiNER2.5-Decide or Nirnaya 0.4B 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.