agent-decision-3b vs agent-decision-9b
agent-decision-3b and agent-decision-9b have no measured difference in accuracy, calibration or cost in our data yet.
| Spec | agent-decision-3b | agent-decision-9b |
|---|---|---|
| Provider | grounded-ai | grounded-ai |
| Decision Index score | — | — |
| Calibration error (ECE) | — | — |
| Median latency (p50) | — | — |
| Cost per 1,000 decisions | — | — |
| Parameters | 3B | 9B |
| Open weights | Yes | Yes |
| Question types | — | — |
| Mechanism | — | — |
| License | — | — |
FAQ
Is agent-decision-3b or agent-decision-9b more accurate?
At least one of the two has no Jev Decision Index score yet, so their accuracy cannot be compared here.
Which is better calibrated, agent-decision-3b or agent-decision-9b?
No calibration difference between agent-decision-3b and agent-decision-9b is recorded yet.
Is agent-decision-3b or agent-decision-9b 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.