GLiNER2.5-Decide vs Kodiak v0.2 1B (accuracy)
Kodiak v0.2 1B (accuracy) is more accurate on the Jev Decision Index, Kodiak v0.2 1B (accuracy) is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | GLiNER2.5-Decide | Kodiak v0.2 1B (accuracy) |
|---|---|---|
| Provider | Fastino | Cortex Agent LLC |
| Decision Index score | 10.1 | 13.9 |
| Calibration error (ECE) | 0.088 | 0.077 |
| Median latency (p50) | 23 ms | 142 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 486M | 3B |
| 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) | Encoder classifier |
| License | apache-2.0 | apache-2.0 |
FAQ
Is GLiNER2.5-Decide or Kodiak v0.2 1B (accuracy) more accurate?
Kodiak v0.2 1B (accuracy) scores higher on the Jev Decision Index (13.9 vs 10.1).
Which is better calibrated, GLiNER2.5-Decide or Kodiak v0.2 1B (accuracy)?
Kodiak v0.2 1B (accuracy) has the lower expected calibration error (0.077 vs 0.088), so its stated confidence is closer to how often it is right.
Is GLiNER2.5-Decide or Kodiak v0.2 1B (accuracy) 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.