bobcat-1.3 vs Decider 31B (NVFP4)
Decider 31B (NVFP4) is more accurate on the Jev Decision Index, Decider 31B (NVFP4) is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | bobcat-1.3 | Decider 31B (NVFP4) |
|---|---|---|
| Provider | sanghwa-na | Mapika |
| Decision Index score | 64.8 | 66.0 |
| Calibration error (ECE) | 0.102 | 0.024 |
| Median latency (p50) | 64 ms | 72 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 31B | 33B |
| 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 |
| Mechanism | Decoder LM with a decision readout | Decoder LM with a decision readout |
| License | apache-2.0 | apache-2.0 |
FAQ
Is bobcat-1.3 or Decider 31B (NVFP4) more accurate?
Decider 31B (NVFP4) scores higher on the Jev Decision Index (66.0 vs 64.8).
Which is better calibrated, bobcat-1.3 or Decider 31B (NVFP4)?
Decider 31B (NVFP4) has the lower expected calibration error (0.024 vs 0.102), so its stated confidence is closer to how often it is right.
Is bobcat-1.3 or Decider 31B (NVFP4) 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.