Baseten: Joey 1 vs Baseten: Mammoth 1
Baseten: Joey 1 is cheaper per 1,000 decisions. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | Baseten: Joey 1 | Baseten: Mammoth 1 |
|---|---|---|
| Provider | Baseten | Baseten |
| Decision Index score | — | 68.4 |
| Calibration error (ECE) | — | 0.041 |
| Median latency (p50) | — | 220 ms |
| Cost per 1,000 decisions | $0.0020 | $0.020 |
| Parameters | — | — |
| Open weights | — | — |
| Question types | — | Choice (one of N options), Score (ordered rubric), Yes / no |
| Mechanism | — | Decoder LM with a decision readout |
| License | — | — |
FAQ
Is Baseten: Joey 1 or Baseten: Mammoth 1 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, Baseten: Joey 1 or Baseten: Mammoth 1?
No calibration difference between Baseten: Joey 1 and Baseten: Mammoth 1 is recorded yet.
Is Baseten: Joey 1 or Baseten: Mammoth 1 cheaper per 1,000 decisions?
Baseten: Joey 1 is cheaper: about $0.0020 vs $0.020 per 1,000 decisions at 200 input tokens each.
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.