LiquidAI d1-omni-600M vs GLiNER2.5-Decide
LiquidAI d1-omni-600M is more accurate on the Jev Decision Index, GLiNER2.5-Decide is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | LiquidAI d1-omni-600M | GLiNER2.5-Decide |
|---|---|---|
| Provider | Liquid AI | Fastino |
| Decision Index score | 11.8 | 10.1 |
| Calibration error (ECE) | 0.128 | 0.088 |
| Median latency (p50) | 11 ms | 23 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 587M | 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 | Encoder classifier | Span encoder (GLiNER family) |
| License | lfm1.0 | apache-2.0 |
FAQ
Is LiquidAI d1-omni-600M or GLiNER2.5-Decide more accurate?
LiquidAI d1-omni-600M scores higher on the Jev Decision Index (11.8 vs 10.1).
Which is better calibrated, LiquidAI d1-omni-600M or GLiNER2.5-Decide?
GLiNER2.5-Decide has the lower expected calibration error (0.088 vs 0.128), so its stated confidence is closer to how often it is right.
Is LiquidAI d1-omni-600M 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.