GLiNER2.5-Decide vs Torchcast Decision 27B
Torchcast Decision 27B is more accurate on the Jev Decision Index, Torchcast Decision 27B is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | GLiNER2.5-Decide | Torchcast Decision 27B |
|---|---|---|
| Provider | Fastino | Torchcast AI |
| Decision Index score | 10.1 | 61.5 |
| Calibration error (ECE) | 0.088 | 0.024 |
| Median latency (p50) | 23 ms | 100 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 486M | 28B |
| 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 | cc-by-nc-4.0 |
FAQ
Is GLiNER2.5-Decide or Torchcast Decision 27B more accurate?
Torchcast Decision 27B scores higher on the Jev Decision Index (61.5 vs 10.1).
Which is better calibrated, GLiNER2.5-Decide or Torchcast Decision 27B?
Torchcast Decision 27B has the lower expected calibration error (0.024 vs 0.088), so its stated confidence is closer to how often it is right.
Is GLiNER2.5-Decide or Torchcast Decision 27B 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.