GLiNER2.5-Decide vs Solomon v1.1
Solomon v1.1 is more accurate on the Jev Decision Index, Solomon v1.1 is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | GLiNER2.5-Decide | Solomon v1.1 |
|---|---|---|
| Provider | Fastino | Doccy Health |
| Decision Index score | 10.1 | 43.2 |
| Calibration error (ECE) | 0.088 | 0.081 |
| Median latency (p50) | 23 ms | 224 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 | apache-2.0 |
FAQ
Is GLiNER2.5-Decide or Solomon v1.1 more accurate?
Solomon v1.1 scores higher on the Jev Decision Index (43.2 vs 10.1).
Which is better calibrated, GLiNER2.5-Decide or Solomon v1.1?
Solomon v1.1 has the lower expected calibration error (0.081 vs 0.088), so its stated confidence is closer to how often it is right.
Is GLiNER2.5-Decide or Solomon v1.1 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.